Update every audited reference site to the six renamed skills:
root README headings and links (and drop the jira-jql entry ahead of
its absorption), references/skill-triggers.md rows for jellyfin and
tempest plus four new-name rows for ghost/jira/openlibrary/tmdb,
scripts/grandfathered-skills.txt pruned to the three retained *-cli
entries, pyproject.toml deptry exclusion jellyfin-cli -> jellyfin,
neckbeard routing seams, cli-builder example names, and the lastfm /
verification-methodology eval texts mentioning jellyfin.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-26 02:13:56 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Rename ghost-cli, jira-cli, jellyfin-cli, openlibrary-cli, tmdb-cli,
and tempest-cli to ghost, jira, jellyfin, openlibrary, tmdb, and tempest
via git mv. Rewrite frontmatter name fields to match new directories,
rename bundled scripts preserving executable bits, update internal
invocation strings and README quick-start examples, and relocate the
jellyfin pytest suite to jellyfin/scripts/ with its SCRIPT constant now
resolving to the renamed sibling script.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* feat(bmad): add BMad control-plane protocol skill
New standalone methodology skill that lets any agent run the BMad method
(Breakthrough Method of Agile AI-Driven Development) as a harness-agnostic
control-plane protocol: five-field intent contracts, direct/bounded/initiative
classification, review-as-triage, failure routing by layer, and autonomy gating
with machine-readable spec status.
- SKILL.md protocol core with progressive disclosure + When not to use
- README.md human-facing install guide
- 9 references: protocol, classification, spec, lifecycle, project-context,
review-and-failure-routing, autonomy, party-mode, adoption
- 4 templates: SPEC, INTENT, STORY, REVIEW
- scripts/check-spec.py + 16 tests (stdlib, deterministic spec validation)
- evals/evals.json: 9 output-quality cases
- Routing seams from bmad to adjacent skills and back from
spec-driven-development, product-shaping, implementation-planning, neckbeard
- Catalog updates: root README, skill-triggers, marketplace/plugin/llms.txt
Closes#399
* fix(bmad): address droid-review findings
- check-spec.py: skip headings inside fenced/indented code blocks so a spec
cannot PASS on section text that only appears in a code sample
- check-spec.py: catch UnicodeDecodeError on non-UTF-8 files and report FAIL
instead of crashing
- STORY.md template: add created key for resumability/traceability parity
- SPEC.md template: split in-progress and in-review status bullets
- add 2 regression tests (heading-in-fence, non-UTF-8)
* fix(bmad): address droid-review round 2
- check-spec.py: read specs with utf-8-sig so a UTF-8 BOM cannot silently
disable the frontmatter status check
- check-spec.py: handle standard YAML inline comments after status values
(status: draft # pending review) without a false FAIL
- references/protocol.md: make lifecycle phrasing consistent with
lifecycle.md — four phases plus a learning closeout
- add 2 regression tests (BOM, inline comment)
* fix(bmad): tolerate trailing whitespace on frontmatter delimiters
A spec whose --- delimiter lines carry trailing spaces or tabs would silently
disable the status check and let an invalid status PASS. Relax the delimiter
pattern and add a regression test.
* fix(bmad): ignore inline comments in quoted status values
* fix(bmad): tolerate leading blank lines before frontmatter
* fix(bmad): fail closed on unparseable frontmatter, matching fence markers
Address droid-review round 5 and 6 findings as a single closed class:
- Fail closed when a file opens with a --- delimiter that cannot be parsed,
so no whitespace/frontmatter permutation can silently disable the status
check (previously: unparseable frontmatter was treated as 'no status'
warning, letting an invalid status PASS).
- Track fence opener markers in collect_headings so a mismatched fence no
longer closes a code block early (false-PASS on missing sections) and an
unclosed fence no longer swallows real headings.
- Accept empty well-formed frontmatter (---\n---) and closing delimiters
without a trailing newline.
- STORY.md template: parent-spec points at the sibling SPEC.md.
- README: status vocabulary is not a strict linear chain; blocked is a
resumable routing signal.
Whitespace/frontmatter mutation sweep: 9 formatting variants x valid/invalid
status all verdict correctly; malformed delimiters fail closed. 29 tests.
- product-roadmapping-and-portfolio: name the bets boundary in "When Not
to Use" — this skill sequences strategic bets across cycles; shaping a
single bounded bet routes to product-shaping.
- product-shaping: sharpen the existing roadmapping boundary sentence to
spell out bet vs. sequences (appetite + circuit breaker vs.
continue/pause/kill across cycles).
- neckbeard README: route feature-sized work through product-shaping
between discovery (product-discovery) and specification
(spec-driven-development).
Docs-only routing seams per #394; no behavioral content changes.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Issue/ticket bodies emitted from a delivery run must be written for a cold
reader: a contributor with none of the session context and no access to the
agent's local artifacts. Encode this at the change-contract layer so any run
that emits tracker artifacts inherits it.
- templates/change-contract.md: new "Issue/ticket body (cold-reader
requirement)" section listing the five requirements (background naming the
investigation, complete inline evidence with file:line refs, reproduction
commands runnable by a stranger, acceptance-criteria checkboxes, no
agent-local paths or private-artifact references), plus a header-note
pointer with the litmus test.
- references/journey.md: journey-level statement of the requirement plus
pointers at phase 1 (intake output row) and phase 5 (verification-planning
output row) where tracker artifacts are emitted.
- evals/evals.json: add case cold-reader-issue-body-gate covering a body draft
that references off-repo artifacts ("artifact pyramid", local /tmp ledger,
detail available on request) and must be rejected/rewritten by the gate.
Closes#385
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Implements issue #378 (Finding F4 of the journey SDLC validation brief):
separate validation from verification in the change-request journey.
Gate 3 now requires that at least one SPEC.md acceptance criterion traces
to the requester's stated outcome/problem restated from primary evidence
in phase 2 - verification proves the build matches the spec; this
criterion proves it solves the requester's actual problem (15288/12207
validation vs. verification discipline).
- references/stages.md: authoritative new Gate 3 bullet (single source
of truth for gate definitions)
- references/journey.md: phase 4 Output and Gate rows aligned, deferring
to stages.md; phase-continuity and gate summary unchanged
- templates/change-contract.md: acceptance-criteria guidance requires a
criterion tracing to the Problem section
- templates/delivery-packet.md: acceptance-criteria mapping field asks
for the requester-outcome trace for the gate-3 verdict
- evals/evals.json: gate-3 assertions updated in four full-path cases;
all 13 case IDs stable
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
CI's changed-skill quality gate requires descriptions to begin with a
recognized imperative verb (repo AGENTS.md rule). The seam edit in this PR
made the file a changed skill, surfacing the pre-existing violation.
Implements issue #377 (journey dossier F2, ADAPT verdict): phase 9 closeout
now records lesson capture per stages.md Stage 6 "Deliver and learn" — either
the reusable lesson(s) and their durable destination (skill, memory, or
project docs), or an explicit "no reusable lesson identified" determination.
Mirrors skip transparency: silent omission is prohibited. Terminal-state
semantics stay intact — lessons are recorded IN the terminal record; a fired
trigger or follow-up starts a new change request via phase 1 intake.
- references/journey.md: phase 9 Output row gains the lesson-capture field;
phase-continuity row updated ("terminal; triggers and lessons recorded in
the terminal record").
- references/delivery-packet.md: group (i) row gains lesson capture; terminal
semantics cover lessons alongside triggers; skip-transparency doctrine
cross-referenced for closeout lessons.
- templates/delivery-packet.md: section (i) fillable "Lessons captured" field
with durable-destination note + example line.
- references/lifecycle.md: intro, terminal-states closeout note, and closeout
row aligned with the extended group-(i) field set.
- evals/evals.json: expected_output + assertions extended in bug-fix-
reproduction-regression and refactor-characterization-architecture-review
(13 IDs stable).
stages.md untouched: Stage 6 already mandates lesson capture; journey/packet
now consume it. README table unchanged (still accurate).
Closes#377
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Implements issue #376 (journey dossier F1, ADAPT-minimal verdict): phase 9
closeout now records rollback/follow-up triggers alongside terminal state +
release evidence, stating what would cause re-entry; operational discoveries
route to a NEW change request via phase 1 intake instead of resurrecting the
terminal packet. Terminal-state semantics stay intact.
- references/journey.md: phase 9 Output row gains trigger fields + new-CR
routing; phase-continuity row updated ("terminal; triggers recorded in the
terminal record").
- references/delivery-packet.md: group (i) row gains trigger fields; terminal
semantics clarify triggers are recorded in, not re-opening, the packet.
- templates/delivery-packet.md: section (i) fillable field + example.
- references/lifecycle.md: intro, terminal-states note, closeout row aligned.
- evals/evals.json: assertions extended in bug-fix-reproduction-regression,
schema-migration-rollback-release-readiness, release-authority-blocked-
terminal-state (13 IDs stable).
- research brief: F1 citation of "SKILL.md step 6" corrected to step 5.
No phase added; stages.md untouched (lesson capture is issue #377).
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Add NVIDIA SkillEvaluator as an advisory (non-blocking) Tier 1 gate on
PRs and pushes touching skill-relevant paths. Runs the documented
keyless check set (schema,pii,license,quality,unicode,lint) pinned to
skillevaluator v0.1.0 per changed skill, uploads JSON reports as an
artifact, and posts one advisory summary line per skill to the job log.
SkillSpector is deliberately not installed: upstream still ships it
"separately installed and unpinned", so the security scan is excluded
by design until a documented compatible pair exists.
Closes#383
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Convert the prose Scripts list into the formal table with copy-pasteable
invocations verified against each script --help, and add factual
Prerequisites and Limitations.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:38:55 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
This resource-based skill ships no scripts, so instead of an Available
Scripts table, document the resources it loads (sub-skill protocols,
references, generation templates), the agent capabilities it needs, and
its real limitations (Hermes-runtime targeting, observation-mode turn
threshold, inference-only discovery).
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:38:55 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Consolidate the two generation/post-processing scripts into the formal
Available Scripts table and add factual Prerequisites and Limitations,
slotting cleanly into the post-#382 references structure.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:38:43 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Document both previously undocumented pytest suites alongside the profiler
and reconciler in the formal table, and add factual Prerequisites and
Limitations.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:38:43 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Add factual Prerequisites and Limitations. Lead the description with an
imperative verb and add an explicit negative boundary to satisfy the
quality validator; keep trigger keywords intact.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:38:43 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Add schema-v1 evals/evals.json with six cases covering growth check-ins,
series trending with time-to-target, decision framing, projections, a
should-not-trigger case, and benchmark honesty. Fix documented flags that
do not exist in the script (--project-weeks/--target-revenue/--add-to-
weekly) to the real ones (--project-periods/--target-value/--dry-run).
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:38:43 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Formalize the woodpecker-doctor.py entry into an Available Scripts table,
add factual Prerequisites and Limitations, and normalize the negative-
boundary heading so the quality gate recognizes it.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:38:29 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Convert the prose Root Scripts list into the formal Available Scripts table
with copy-pasteable invocations, and add factual Prerequisites and
Limitations from compatibility frontmatter and bundle behavior.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:38:29 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Convert the implicit CLI documentation into the formal table (including the
previously undocumented test-lastfm.sh), add factual Prerequisites and
Limitations from compatibility frontmatter and known gotchas, and add the
missing negative-boundary section required by the quality gate.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:38:18 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Document the previously undocumented test-flaresolverr.sh alongside the CLI
in a formal Available Scripts table, and add factual Prerequisites and
Limitations derived from the skill real behavior.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Six schema-v1 eval cases grounded in real skill behavior: council
invocation and bootstrapping, convergence-diagnostic reading,
quick-mode selection, claims-verification discipline, profile-library
fallback, plus one should-not-trigger case for simple factual lookups.
Satisfies the eval-coverage ratchet for this modified skill.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:15:23 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Add an Available Scripts table for scripts/bootstrap.py with invocation
and run-when guidance; add Prerequisites and Limitations covering the
single-model debate design and claims-verification guardrail. Lead the
frontmatter description with the imperative verb Run and add an explicit
negative boundary so the changed skill passes the CI quality gate; all
trigger keywords are preserved.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:15:23 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Add an Available Scripts table covering risk_preflight.py,
temporal_split_audit.py, and the previously undocumented test_risk_scripts.py;
add Prerequisites and Limitations for the dependency-free first-pass scripts.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:15:06 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Document semantic-spacetime.py subcommands (lint/map/distance/trajectory/drift)
in an Available Scripts table with invocation and run-when guidance; add
Prerequisites and Limitations grounded in the CLI's read-only model analysis.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:15:06 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Document promise-contract.py (lint/render commands) in an Available
Scripts table with invocation and run-when guidance; add Prerequisites
and Limitations reflecting static validation scope and the not-contract-law boundary.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:15:06 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Document validate-capabilities.py in an Available Scripts table with
invocation and onboarding-timing guidance; add Prerequisites and
Limitations reflecting the no-capability fallback and nonclinical scope.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:14:57 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Document landscape_query.py in an Available Scripts table with a
copy-pasteable invocation and run-when guidance; add Prerequisites and
Limitations grounded in the tool's snapshot-based, read-only design.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:14:57 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Document validate-city-pack.py in an Available Scripts table with
invocation and workflow-step timing; add Prerequisites and Limitations
covering v1 geometry bounds, CPU rendering, and offline validation scope.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:14:30 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Document lookup.py in an Available Scripts table with invocation and
run-when guidance tied to the routing workflow; add Prerequisites and
Limitations reflecting the stdlib-only local-library search.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 23:14:30 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Convert the prose script list into an Available Scripts table covering
aeo_audit.py, build_prompt_matrix.py, and test_aeo_scripts.py with
copy-pasteable invocations and run-when guidance; add Prerequisites and
Limitations derived from the skill's compatibility notes.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Body was ~19.5k chars, past the new 20k token-budget gate. Collapses
Capability Discovery to a stub pointing at the existing
references/agent-capability-discovery.md, summarizes Apple Books
compatibility instead of duplicating its table, and moves the LLM
Configuration Convention plus the Knowledge Extraction Deep Dive into
references/llm-config-and-extraction.md. Keeps format essentials, the
script decision table, CLI examples, workflows, gotchas, and pitfalls,
and extends the references index with the two touched/new files; body
is now 16,261 chars.
Also adds evals/evals.json (6 output-quality cases incl. one
should-not-trigger case) to satisfy the eval-coverage ratchet.
The description previously started with "EPUB", which fails the
imperative-verb rule that CI enforces on every changed skill; it now
leads with "Read" while keeping all trigger keywords. Adds a
"When not to use" section (non-EPUB documents, DRM-locked books,
Kindle-native formats). Regenerates .claude-plugin/marketplace.json
and llms.txt accordingly.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 22:47:53 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Body was ~20.5k chars, past the new 20k token-budget gate. Moves the
five migration-type classifications into
references/migration-types.md and the structured planning field tables
into references/planning-fields.md (cross-referencing
templates/migration-plan.md). SKILL.md keeps triggers, boundaries,
the workflow skeleton with summaries pointing at existing references,
the Loading Guide (now including both new files), and specialist
routing; body is now 11,432 chars.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 22:47:16 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Body was ~24k chars, past the new 20k token-budget gate. Moves the
style-lane grammar + prompt cues + asset catalog into
references/style-lanes.md, the full visual system (palettes, mascot,
typography, textures, art style) into references/visual-system.md, and
post-processing modes/intensity calibration into
references/post-processing.md. SKILL.md keeps triggers, the negative
boundary, prompt templates, API notes, anti-patterns, compliance
checklist, and a Loading Guide table; body is now 12,042 chars.
Also adds evals/evals.json (6 output-quality cases incl. one
should-not-trigger case) to satisfy the eval-coverage ratchet, and adds
a "When not to use" section so the changed-skill quality gate passes.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-22 22:47:16 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Issue #382: the 500-line cap alone lets dense prose slip through, so
bodies are now measured in characters (~4 chars/token proxy for the
~5,000-token budget) after stripping YAML frontmatter. Bodies over
20,000 characters hard-error with split-into-references remediation,
mirroring the existing oversized-reference gate (#277).
Adds ReferenceFileScan.oversized_skill_md_errors next to
oversized_reference_errors, wired into the per-skill loop, with
Minitest coverage: under-limit passes, over-limit fails with path and
size, exactly-at-limit passes (strict >), huge-frontmatter/tiny-body
passes, missing-frontmatter stays silent (reported elsewhere), and
missing SKILL.md is ignored.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Pin copy-pasteable npx invocations to explicit versions so agents
executing them verbatim get reproducible behavior:
- playwright docs: npx playwright@1.62.1 (SKILL.md, README.md,
references 02-selectors / 05-ci-integration / 07-accessibility)
- mermaid-diagrams: @mermaid-js/mermaid-cli@11.16.0 (SKILL.md,
references/pdf-rendering-pipeline.md)
- hugo-theme seo-outputs-testing: @axe-core/cli@4.13.0
- agent-skills using-scripts.md: strengthen version-pinning bullet
into a normative rule for copy-pasteable commands
Reword the anydoc cli-reference "Version pinning" prose so the
anti-pattern is explained didactically without presenting an unpinned
command as a recipe; the @0.1.6 house pin is unchanged.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Document that a delegated research worker timeout is an interruption, not a
result: recover partial artifacts, resume from the last durable checkpoint,
and judge completion by evidence completeness rather than elapsed time.
Co-authored-by: factory-droid[bot] <138933558+factory-droid[bot]@users.noreply.github.com>
Comparative dossier mapping the nine-phase change-request journey against
ISO/IEC/IEEE 15288, ISO/IEC/IEEE 12207, CMMI-DEV V1.3, and ITIL 4, plus
Anthropic Building Effective Agents, the OpenAI practical guide to building
agents, and the Agent Skills specification.
Conclusion: no material structural gaps. Three ADAPT-class documentation
recommendations (phase-9 rollback/follow-up triggers, phase-9 lesson capture
aligned with stages.md Stage 6, requester-outcome traceability at gate 3);
retirement/decommissioning confirmed as deliberate scope boundary; gate
placement converges with published agentic practice.
Co-authored-by: factory-droid[bot] <138933558+factory-droid[bot]@users.noreply.github.com>
feat(neckbeard): position-assessment entry mode and tracker-neutral intake
Closes#371. Merged at head 5aee6fc after branch update from main; CI green at that SHA on the merged tree (validate, paired-eval-smoke, paired-eval-tests).
Six rounds of droid-review did not converge to zero findings; per the documented stop, the four remaining non-blocking prose-consistency findings (two touching trust-boundary doctrine) are recorded in the PR timeline as follow-up material for a separate reviewed change.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Add litellm/, an operational tool skill for the LiteLLM AI gateway (proxy)
and Python SDK, in the same vein as the vllm and llama-cpp engine skills.
Contents:
- SKILL.md: operating contract, operating loop, verification boundaries,
and hard boundaries; concise core sections routing depth to references
- README.md: human-facing install/use guide with required sections
- references/: nine dated, source-indexed references (source index,
quickstart + SDK, config & routing, keys/teams/budgets/spend, caching &
guardrails, observability & logging, deployment, security & public
hosting, troubleshooting), researched against litellm 1.97.0
(2026-08-22) including a live proxy probe of the health endpoints
- scripts/litellm-health: read-only GET-only probe (liveliness, readiness,
/v1/models, /model/info); stdlib-only Python 3.9+, --json, --help
without a server
- tests/test_litellm_health.py: 18 deterministic tests against a local
stub HTTP server, including the observed-traffic GET-only contract
- templates/proxy-config-record.md and proxy-deployment.md: fillable
records; the config record is the rollback unit
- evals/evals.json: schema_version 1, six output-quality cases
Also regenerates tracked catalog artifacts (.claude-plugin/marketplace.json,
.codex-plugin/plugin.json, llms.txt) and adds the root README catalog entry
plus the skill-triggers.md index row.
AI assistance: authored with AI assistance (Factory Droid) under human
direction; facts verified against litellm 1.97.0 and official docs dated
2026-08-22.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* fix: SkillOpt epoch 1 for AI operating economics
Promote cold-load entry points, quick-start reference routing, the minimum decision-record contract, and trigger-oriented progressive disclosure.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
* fix: SkillOpt epoch 2 for AI operating economics
Add review-depth selection, evidence-to-disposition guidance, and scenario-led routing across adjacent skills.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
* fix: SkillOpt epoch 3 for AI operating economics
Expose a minimum claim ledger and explicit closure conditions for every bounded disposition.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
* fix: resolve SkillOpt review consistency findings
Align entry-point paths, canonical step routing, claim-ledger fields, and triage disposition wording.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
* fix: resolve final SkillOpt disposition wording
Keep review-depth outputs inside the canonical disposition set and distinguish supported claims from permitted language.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
* fix: complete SkillOpt routing correction
Route triage through the outcome-map step and identify the evidence-classification step explicitly.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
* fix: complete AI economics review template
Add the minimum decision-record fields required by the optimized skill routing contract.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
---------
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
* feat: add AI operating economics skill
Add an evidence-led methodology for evaluating AI workflow value, cost, worker effects, quality guardrails, and authority expansion. Includes research references, durable decision templates, and six eval cases. AI assistance: Jasper, on behalf of Magnus Hedemark.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
* fix: resolve AI economics review findings
Align section numbering, evidence-language examples, and intervention-mode terminology identified by the exact-head review.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
---------
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
Add progressive DDIA handoff and focused replication, partitioning, fencing, and isolation eval coverage.\n\nAI-assisted: Jasper orchestrated implementation and verification with OpenCode.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
Add audience, narrative, hierarchy, representation, accessibility, uncertainty, review evidence, and eval coverage for C4 and Mermaid artifacts.\n\nAI-assisted: Jasper orchestrated implementation and verification with OpenCode.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
Add capability and portfolio mapping, state transitions, operating models, decision rights, stakeholder information, templates, evals, and neighboring-owner routing.\n\nAI-assisted: Jasper orchestrated implementation and verification with OpenCode.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
Replace board-centric defaults with consequence-driven governance modes, feedback loops, exceptions, and clear ownership boundaries.\n\nAI-assisted: Jasper orchestrated implementation and verification with OpenCode.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
Add a lifecycle method and reusable record for connecting architecture decisions to checks, evidence, review, exceptions, and retirement.\n\nAI-assisted: Jasper orchestrated implementation and verification with OpenCode.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
Add evidence lenses for characteristics, coupling, decomposition, data authority, workflows, health reporting, and eval coverage.\n\nAI-assisted: Jasper orchestrated implementation and verification with OpenCode.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
Add portfolio, lifecycle, topology, policy-placement, assessment, and eval guidance while preserving contract ownership boundaries.\n\nAI-assisted: Jasper orchestrated implementation and verification with OpenCode.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
Document scripts and templates and add a concrete Quick Start command.\n\nAI-assisted: Jasper implemented and verified this late-review follow-up.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
Add readiness, governance, recovery, pattern, workshop, and eval coverage for operational data architecture decisions.\n\nAI-assisted: Jasper orchestrated research, implementation, and verification with OpenCode.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
Merge authorized after exact-head validation and paired evaluation checks passed. The follow-up Droid review run on head df31b25 stalled in the model step and ended with an automation error; its actionable findings from the prior review were fixed and independently verified.
* feat(ascii-city-engine): deep enrichment — street furniture, signage, dense Raleigh
Enriches the merged v0.1 skill with a dense, real-data streetscape.
Schema (backward-compatible): props gain optional label + provenance; new
optional signs layer for street-name text; buildings gain name/address/use.
world.schema.json admits signs; all v0.1 packs still validate.
Validator: per-kind prop glyph map with unknown-kind flag; sign validation;
signs included in content-bounds; v0.1 guards (isinstance crash-guard,
O(n^2) DoS caps) intact.
Engine: spatially-indexed prop billboards (signals, trees, crossings, transit
stops, bollards, benches, hydrants) depth-tested at terrain(x,y);
perspective-projected street-name sign text as an overlay pass; road
surface-material and lit ground styling; crosswalk bands; wayfinding HUD
naming the current street and the building faced. Reads spawn + first tile
from manifest.json.
Raleigh sample regenerated dense (same authoritative bbox): 159 buildings
(64 named, addresses, uses), 899 surfaces (86 named, surface/lit/lanes),
298 props across 7 kinds, 29 real street-name signs. 520K, under 2 MB.
Docs + evals: contract/engine-architecture/gis-ingestion/raleigh-poc updated
for the new layers and acceptance checks; 2 new evals (no fabricated signage;
props anchored to terrain).
Verified: validator 1410 PASS / 0 FAIL; broken fixture + AttributeError repro
exit 1; 5000-vertex DoS rejected in 31 ms; node --check OK; HTTP smoke 200
on engine/manifest/tile; validate-skills.rb 154 green; eval-coverage passes;
blocklist clean; headless-Chrome render shows readable in-world 'North
Wilmington Street' sign, signals, crosswalks, and on-street HUD.
AI-assisted contribution (Hermes Agent, spec-driven-development pipeline).
* fix(ascii-city-engine): address droid-review findings on PR #322
1. [P1] facingBuilding(): wrap the heading delta to [-pi,pi] before taking
abs, so the Facing: HUD stops reporting a behind-the-camera building after
the player turns past ~180 degrees.
2. [P2] buildIndices(): rasterize surface polyline edges into grid cells so
long straight road segments register for surface styling and the On:
HUD street name, instead of only indexing endpoint vertices.
3. [P1] validator: guard the new props kinds comprehension and the props/
signs loops in all_points() against null, so 'props: null' or 'signs: null'
produce a structured FAIL instead of an uncaught TypeError traceback.
4. [P3][security] validator: enforce the previously-declared
MAX_FEATURES_PER_TILE (buildings+surfaces+props+signs) to keep the O(n^2)
geometry and duplicate-ID paths bounded in aggregate.
5. [P3] engine: paint marked crossings as a distinct ground band (=) instead
of a floating billboard, matching the documented crosswalk rendering.
6. [P3] eval: align prop-null-terrain expected_output with the render-time
skip behavior actually implemented.
Verified: dense pack 1411/0 exit 0; broken/crash/dos/null packs all exit 1
with clean FAIL reports (no tracebacks); JS node --check OK; validate-skills
154 green; blocklist clean.
* fix(ascii-city-engine): address droid-review round 2 on PR #322
1. [P1] Engine: skip crossing props in the billboard loop so crosswalks
render only as the documented ground band (no more floating '=' above
each of the 168 crossings — a regression from the prior fix).
2. [P3] Engine: nearestStreet() filters to kind==='road' so the HUD 'On:'
line names the street, not a named plaza/sidewalk ('Market Plaza' etc).
3. [P2] Validator: require each sign's text to be a recorded road name
(collected from surfaces), enforcing the documented never-invented
signage contract. A fabricated 'Made Up Avenue' sign now FAILs.
4. [P2][security] Validator: short-circuit the tile loop when
MAX_FEATURES_PER_TILE is exceeded, and replace O(n^2) duplicate-id
.count() scans with single-pass Counters, bounding the quadratic paths.
Verified: dense pack 1411/0 exit 0; fabricated-sign repro flags only the
injected sign and exits 1; broken/crash/dos/null packs all exit 1 with no
tracebacks; JS node --check OK; validate-skills 154 green; blocklist clean.
* fix(ascii-city-engine): address droid-review round 3 on PR #322
1. [P2] Validator: emit the signs rule unconditionally so a null/non-list
'signs' value FAILs instead of passing silently (was gated on a truthy
list check).
2. [P2] Validator: validate sign text against a pack-wide road-name set
gathered across all tiles, so a sign in one tile may name a road whose
surface lives in another (the documented multi-tile case).
3. [P2] Schema: require non-empty id/kind/text (minLength 1) on props and
signs so the schema and validator agree on empty-string rejection.
4. [P3] Engine: drop dead signGrid/IX.key (the sign overlay iterates
world.signs directly); cap edge-rasterization steps so a degenerate
resolution (0) or pathologically long edge cannot spin unboundedly.
5. [P3] Validator: unknown prop kinds now pass with a reported fallback-'?'
note instead of hard-failing, matching the documented fallback glyph and
the engine's behavior.
Verified: dense pack 1411/0 exit 0; signs:null FAILs; fabricated sign FAILs;
multi-tile sign-to-road reference PASSes; broken/crash/dos/null all exit 1;
JS node --check OK; validate-skills 154 green; blocklist clean.
* fix(ascii-city-engine): address droid-review round 4 on PR #322
1. [P2] Engine: render props as once-per-frame perspective-projected one-cell
billboards in an overlay pass (like signs) instead of during the ray march,
eliminating the multi-row vertical streak a close prop produced. Verified in
a live browser: signals/trees/crosswalks now render as discrete single cells.
2. [P3][security] Engine: bound aggregate rasterization in buildIndices() —
cap surfaces (5000) and cells per surface (40000) so a crafted pack cannot
freeze the tab on load (the validator's caps are not applied client-side).
3. [P2][security] Engine: guard sign text (missing/non-string text now skips
the sign instead of throwing in the rAF loop and freezing the view).
4. [P3] Validator: still collect building/surface IDs for oversized tiles so
pack-wide uniqueness detection runs even when the per-feature geometry checks
are short-circuited (duplicates in an over-cap tile are no longer hidden).
Verified: dense pack 1411/0 exit 0; live browser render shows discrete props
(no streaks); broken/crash/dos/null/nullsign/fabric all exit 1, valid
multi-tile pack exit 0; JS node --check OK; validate-skills 154 green;
blocklist clean.
* fix(ascii-city-engine): address droid-review round 5 on PR #322
1. [P2][security] Engine: guard terrain() against non-finite x/y and guard the
prop/sign overlay passes against non-array, non-object entries, so a
malformed pack (missing y, signs=42, null entries) degrades gracefully
instead of throwing in the rAF loop and freezing the view. Verified in a
live browser: a pack with signs=42 + a prop missing y renders with the
frame loop alive and no console errors beyond the favicon 404.
2. [P3] Engine: per-surface 'seen' set now dedupes cells across edges (was
per-edge), eliminating the repeated linear includes() scan that made the
rasterizer quadratic in the worst case.
3. [P3] Engine: raise the per-edge step cap to 20000 since the per-surface
cell cap bounds total work, so long edges are fully sampled at the 2-5 m
resolutions raleigh-poc.md recommends (fixes road-styling drops).
4. [P3] Validator: lower MAX_FEATURES_PER_TILE to 50,000 (shipped pack is
1,385), bounding the quadratic pair tests more tightly.
5. [P3] raleigh-poc: correct walkthrough step 3 — East Hargett sign is ~141 m
behind the spawn, not ahead; only North Wilmington is ahead. HUD count
guards signs/props as arrays.
Verified: dense pack 1411/0 exit 0; broken/crash/dos/null/nullsign/fabric all
exit 1, valid multi-tile pack exit 0; malformed-pack live render survives;
JS node --check OK; validate-skills 154 green; blocklist clean.
* fix(ascii-city-engine): address droid-review round 6 on PR #322
1. [P1] Engine: props/signs overlay passes now use the corrected perpendicular
distance (d*cos(ray_angle-heading)) for row projection, distance scaling,
and the depth test — matching the ray march — so FOV-edge objects project to
the right row and no longer falsely occlude or poison later depth tests.
2. [P2][security] Engine: terrain() guards malformed terrain metadata (missing
terrain/resolution, non-positive resolution, missing origin, null elevations),
so a crafted pack degrades to a clean error instead of freezing the tab.
Verified live: a resolution-0/null-elevations pack shows 'Cannot load...'
with no page errors.
3. [P3] raleigh-poc: walkthrough step 3 corrected — W/S only translate, so a
167-deg-off sign needs A/D rotation, not 'hold S'.
4. [P3][security] Validator: all_points() guards buildings/surfaces/props/signs
against truthy non-iterables (e.g. props=42), matching the other null guards,
so malformed packs report structured FAIL instead of an uncaught TypeError.
Verified: dense pack 1411/0 exit 0; crash/dos/null/nullsign/fabric/props42/
broken all exit 1 (no tracebacks); valid multi-tile exit 0; malformed-terrain
live render shows clean error, no freeze; JS node --check OK; validate-skills
154 green; blocklist clean.
* fix(ascii-city-engine): address droid-review round 7 on PR #322
1. [P2] Engine: spatial-index buildings (footprint bbox -> grid cells) so the
render loop and collision test find nearby buildings in O(nearby) instead of
scanning the whole O(buildings) list per ray sample. Browser-measured frame
cost dropped ~62ms (16 FPS) to 12.5ms mean (~80 FPS) on the dense pack.
2. [P2][security] Engine: terrain() guards null/ragged elevation rows, so a
pack with a null row degrades to a clean error instead of freezing the tab
(live-verified: null-row pack shows 'Cannot load...', no page errors).
3. [P2][security] Engine: cap sign text at 80 chars in the overlay pass, so a
pathological pack-supplied sign cannot drive an unbounded per-frame loop.
4. [P3] Validator: reference FALLBACK_GLYPH constant (was dead) in the
unknown-kinds report message.
5. [P3] raleigh-poc: fix stale expected validator tail (was 30/25; actual is
159/899, rules_passed=1411).
Verified: dense pack 1411/0 exit 0; crash/dos/null/nullsign/fabric/props42/
broken all exit 1, valid multi-tile exit 0; null-row pack shows clean error,
no freeze; ~80 FPS browser-measured on dense pack; JS node --check OK;
validate-skills 154 green; blocklist clean.
* fix(ascii-city-engine): address droid-review round 8 on PR #322
1. [P1][security] Engine: bound the building spatial-index rasterization with
MAX_BUILDING_PTS (2000) and MAX_BUILDING_CELLS (40000) and require >=3 finite
footprint points, so a ~100-byte crafted footprint cannot drive a ~1e10-
iteration synchronous hang on load (the surface rasterizer's cap, applied
to the building index I added in round 7).
2. [P2][security] Engine: facingBuilding() filters footprints to finite points
before reducing, so a building with a null element in its footprint no
longer throws in the rAF loop on frame 1.
3. [P2][security] Engine: collides() and pointNearPolyline() filter footprints/
polylines to valid array points before edge tests, so null footprint points
no longer throw once the player enters those cells.
4. [P3] Validator: correct the feature-cap comment to 'buildings + surfaces +
props + signs combined' (signs were already counted).
Verified: dense pack 1411/0 exit 0; ~85 FPS browser-measured (perf fix intact);
badfoot pack (null-point + missing-footprint buildings) renders with zero page
errors and frame loop alive; crash/dos/null/nullsign/fabric/props42/broken all
exit 1, valid multi-tile exit 0; JS node --check OK; validate-skills 154 green;
blocklist clean.
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
