Merging with required validation green. Droid Auto Review was retried twice and failed before producing a review because DeepSeek V4 Flash rejected the action's ApplyPatch tool; the check is non-required per branch protection. The diff was independently inspected and local/repository validation passed.
* 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.
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>
All five findings from the droid-review run on 2db3bd0 resolved:
- [P1] Path re-selection moved before scoring: step 2 now re-runs the
SKILL.md path-selection rule against the inventoried surface, so step 3
scoring and the report's selected-path field no longer depend on a
value produced later in step 5.
- [P2] Tracking-system field added to delivery-packet.md group (a) and to
templates/delivery-packet.md, so the phase-1 intake gate has a defined
packet home for the field tracker-discovery.md requires.
- [P2] tracker-discovery eval aligned with the documented procedure: a
bare team-key identifier (ENG-482) is treated as ambiguous between
Jira and Linear; the requester's explicit confirmation is the
disambiguating evidence recorded in group (a).
- [P3/security] Detection signals weighted: request references are strong
evidence; repository content (CONTRIBUTING.md, config files) is a weak,
attacker-influenceable signal requiring corroboration before it alone
selects a system. Unrouted-system fallback constrained to the system's
verified official interface.
- [P3] Frontmatter description extended with the new trigger vocabulary
(mid-flight continuation, Linear/Jira/Notion routing), compressed to
stay within the 1024-char validator cap.
Generated catalog artifacts regenerated for the description change.
All validators re-run green locally; new head requires fresh CI.
Signed-off-by: Magnus Hedemark <magnus919@users.noreply.github.com>
* 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>
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.
Add the trigger/router SKILL.md (description, you-own/don't-own table, router
tables accounting for every bundled file, When-not-to-use, neighbor routing), the
human-facing README, the schema-valid evals manifest with six output-quality cases,
the root README catalog entry, the skill-triggers row, and regenerated llms.txt plus
the three marketplace/plugin artifacts.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-14 20:47:04 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Rework the description frontmatter of 4 moved skills (tailscale, and
workflow-architect sub-skills bundle-builder, interviewer, observer) so each
starts with a recognized imperative verb, and add "## When not to use" body
sections to all 13 moved skills surfaced by the flatten move (research-and-vault,
tailscale + its 7 sub-skills, workflow-architect + its 3 sub-skills) so every
one defines a negative boundary. Trigger vocabulary is preserved and every
description stays under 1024 chars. Regenerate llms.txt and
.claude-plugin/marketplace.json, which embed the tailscale description.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-14 16:13:32 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Add the semantic-spacetime skill skeleton: a thin SKILL.md router with
triggers/anti-triggers, Load By Need, Quick Start, Related Skills, gotchas,
and exit conditions; a human-facing README; MIT license; deep
provenance-marked theory references (foundations, glossary, bibliography);
the versioned sst-model-v1 template pair; a 6-case schema-v1 eval manifest;
the root README catalog entry; regenerated marketplace and llms artifacts;
and the skill-triggers row.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-12 22:33:47 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Add the promise-theory skill to the repository catalog: root README entry,
regenerated llms.txt and marketplace/plugin packaging, and a
references/skill-triggers.md row.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-11 23:41:52 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Add references/agent-evals.md documenting the official supabase/evals
harness: eval/experiment concepts, the tools and local-stack runtimes,
run and result-viewing commands, and a mapping of harness scenarios to
the skill's operating references. Route to it from the supabase
"Choose the path" table and from postgres, agent-evals-and-observability,
backend-engineering, and data-engineering. Add two eval cases covering
the new reference and keep the generated catalog artifacts current.
Closes#271
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-09 18:05:33 -04:00
Magnus HedemarkGitHubfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Rename the skill directory to writers-helper and update the name field,
eval manifest skill_name, skill README title and example paths, root
README catalog entry, and the skill-triggers index. Regenerate llms.txt,
.claude-plugin/marketplace.json, .codex-plugin/plugin.json, and
.agents/plugins/marketplace.json from their generators. Content is
unchanged.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-08 13:06:46 -04:00
Magnus HedemarkGitHubfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Add writing/, a comprehensive writer's personal skill distilled from a
44-book writing-craft and publishing library. Ships 10 expert references
(planning and research, craft and structure, prose and style, drafting,
editing and revision, blocks and prompts, habits and lifestyle,
publishing and career, genres and formats, pitfalls and solutions),
13 fill-in templates (premise canvas through book proposal, query
letter, and submission log), and 5 Python helper scripts (position-aware
prompt generator, session planner, manuscript stats analyzer, habit
journal, submission tracker). All content is original paraphrase and
synthesis; no copyrighted source material is reproduced.
Add the catalog entry at its sorted position and regenerate llms.txt,
.claude-plugin/marketplace.json, .codex-plugin/plugin.json, and
.agents/plugins/marketplace.json from their generators.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-08 12:53:55 -04:00
Magnus HedemarkGitHubfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* feat(skill): add genius-life core skill files
Add genius-life/SKILL.md and the six references/ files (creative-process,
practice-mode, development-mode, practices-catalog, evidence-basis,
scope-and-safety) as original synthesis from the mission research library,
with copyright-compliant paraphrase, named-fellow attribution, and honest
framing. Templates, README, evals, and catalog integration ship in later
features.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* feat(skill): add genius-life templates, README, and evals
Add six fillable worksheets (talent audit, session plan, project
worksheet, conditions audit, incubation log, risk and failure review),
a human-facing README with the repository's required sections, and a
12-case eval manifest covering both modes and the required boundary
behaviors.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* feat(skill): add genius-life to catalog and regenerate artifacts
Add the genius-life README catalog entry at its sorted position and
regenerate llms.txt, .claude-plugin/marketplace.json, .codex-plugin/plugin.json,
and .agents/plugins/marketplace.json from their generators.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
---------
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Add the personalized travel dossier skill, its portable evaluation cases, rendering and privacy helpers, tests, and synchronized discovery catalogs.
Authored by Jasper (AI agent on behalf of Magnus Hedemark).
2026-08-07 23:34:19 -04:00
Magnus HedemarkGitHubfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* feat(skill): add anydoc core content and references
Add the anydoc skill content tree: SKILL.md (progressive-disclosure index
with frontmatter per ALLOWED_FIELDS), human-facing README, the five reference
files (formats, cli-reference, errors, workflows, sources), 24 committed
fixtures (valid + error cases), and a fixture-grounded eval manifest with 8
cases. Every documented behavior, exit code, and error message was verified
against the real pinned CLI (npx -y @firecrawl/anydoc@0.1.6); verbatim --help
and error transcripts are reproduced character-for-character.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* feat(skill): add anydoc wrapper script and unit tests
Implements scripts/anydoc, a stdlib-only Python wrapper around the pinned
@firecrawl/anydoc@0.1.6 CLI: convert/batch/info subcommands, global
--json/--dry-run, input and output pre-validation, friendly hints for the
no-OCR/encrypted/malformed/unsupported error classes, Node >= 20 and npx
availability checks, deterministic batch output naming with documented
duplicate/collision behavior, and exit codes 0/1/2. Adds offline unittest
suite (46 tests, real-CLI tests skip when npx is unavailable) and keeps the
wrapper contract documented in cli-reference.md and errors.md.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* feat(skill): ratchet anydoc evals to 14 grounded cases
Verify the pre-authored 8-case manifest and extend it with six
high-signal cases (PDF lower-fidelity pipeline, legacy .ppt table
flattening, ODP same-serializer, RTF, EPUB, CSV header promotion),
each grounded in real pinned-CLI runs against the committed fixtures.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* feat(skill): integrate anydoc into repo catalog and artifacts
Add the sorted anydoc catalog entry to README.md (between agent-skills
and api-design-and-evolution), regenerate the tracked catalog artifacts
(.claude-plugin/marketplace.json, .codex-plugin/plugin.json,
.agents/plugins/marketplace.json, llms.txt) with the ruby generators,
and add a routing note to documents/SKILL.md pointing office-document
to-markdown conversion at the anydoc skill.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* fix(skill): polish anydoc wrapper timeout, JSON shape, and docs
- run_cli raises CliTimeoutError on the 120s timeout; convert/batch with
--json now emit one parseable JSON error envelope (error_class "timeout")
on stdout before exiting, so --json always yields exactly one JSON doc
- batch JSON failure entries (pre-validation and CLI) now carry error_class
("io" for missing/dir inputs, mapped classes for CLI failures), so all
batch failure entries share the same shape
- build_cli_command places -o/-f before the -- separator for dash-leading
filenames, so `convert -f csv -- -weird` converts instead of misparsing
("unexpected second input"); absolute-path inputs unchanged
- workflows.md vault-ingestion recipe globs notes/* instead of docs/* and
warns to run from a temp/vault dir, never touching repo-root docs/
- unit tests: +6 (timeout envelope x4, batch error_class shape,
dash-leading filename); suite grows 46 -> 52
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
---------
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* feat(validation): enforce 60K-char cap on skill reference files
Implements issue #277:
- validate-references.rb: new oversized_reference_errors check — every
references/*.md must be <= 60,000 characters; error reports path, size,
and the split-and-reindex remediation; wired into validate-skills.rb
- test-validate-skills.rb: 5 fixture tests (under-limit passes, over-limit
fails with path+size, exactly-at-limit passes, remediation message,
non-.md ignored); the suite now runs in validate.yml after the format
check (it was previously untested in CI)
- Docs: agent-skills/SKILL.md, agent-skills/references/best-practices.md,
and the AGENTS.md Format Compliance table document the cap and the
split-and-reindex procedure
- Compliance: split remote-systems-administration/references/ansible.md
and programming-principles/references/refactoring-guru.full.md into an
index + focused parts (content moved verbatim); SKILL.md routing,
README, and source-index references updated; pre-existing stale
refactoring-guru-smells.md reference repointed to the index
- Fix pre-existing quality-gate violations in the programming-principles
and remote-systems-administration descriptions (imperative verb +
negative boundary) so this PR's CI quality step passes; regenerated
llms.txt and marketplace artifacts
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* test(evals): add eval manifests to modified skills for ratchet
The eval-coverage ratchet requires schema-valid eval manifests for any
skill modified once coverage is past 50%. This PR modifies
programming-principles and remote-systems-administration (splitting
their oversized references), so add evals/evals.json to both:
- programming-principles: 6 output-quality cases (task-to-book mapping,
principled code review, refactor-vs-rewrite, no-op detection, rule
distillation, principle conflicts)
- remote-systems-administration: 6 output-quality cases (discovery
before change, smallest control plane, rollback planning, platform
identification, verification evidence, escalation on missing
authority)
Coverage: 87/145 (60.0%) schema-valid; ratchet clean.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
---------
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-04 22:39:14 -04:00
Magnus HedemarkGitHubfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* feat(skill): cross-pollinate the new tool wave into catalog routing
Wire the recent tool skill wave into the two-layer routing graph so the
new tool skills are reachable from the methodology skills that own their
domains, and vice versa:
- methodology -> tool down-routes: platform-engineering -> kubernetes,
terraform, telemetry, postgres, grafana; site-reliability-engineering ->
telemetry, grafana; data-engineering and backend-engineering -> postgres;
frontend-engineering -> mobile-development; verification-methodology ->
playwright, documents; technical-documentation -> documents
- neckbeard: add mobile-development and documents routing rows plus
change-surface coverage entries, and cross-link the lightweight
test-hardening path to qa-methodology's bounded mutation-review material
- collaboration layer: chief-of-staff-methodology -> slack/notion/email,
go-to-market -> crm, conditional-customer-success -> crm; fix the dead
seo-content-optimization reference in go-to-market (now seo-audit)
- references/skill-triggers.md: add trigger rows for the 14 new skills
- bring go-to-market's description up to the quality validator's
imperative-verb + negative-boundary requirement and regenerate catalogs
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* fix(skill): add eval manifest for technical-documentation
The eval-coverage ratchet fails on modified skills without a schema-valid
manifest once coverage passes 50%. technical-documentation was modified by
the routing cross-pollination change and lacked one; add six output-quality
cases covering README authorship, API reference generation, CLI help design,
agent-facing docs, documentation-site IA, and troubleshooting sections.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
---------
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-04 12:46:06 -04:00
Magnus HedemarkGitHubfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Adds five top-level operational tool skills, one per named tool:
- slack: messages, channels, threads, search, files, and webhook signature
verification (HMAC-SHA256) via a bounded, stdlib-only slack-cli.
- notion: pages, database queries, search, and guarded page updates via
notion-cli.
- email: transactional email via Twilio SendGrid (send, deliverability
bounces/spam reports, Signed Event Webhook verification with a
self-contained ECDSA P-256 verifier) via email-cli.
- crm: HubSpot CRM records, contact search, and deal pipeline views with
guarded stage updates via crm-cli.
- stripe: read-only-first balance, payment, and subscription queries with
a guarded period-end subscription cancellation via stripe-cli.
Each skill ships an executable script (--json output, --limit bounded reads,
--dry-run/--yes mutation gate), a human README with the five required
sections, a schema-v1 evals/evals.json with six output-quality cases, a dated
source index + operations reference, and a deterministic unittest suite run
by check-artifacts. All five are indexed in the top-level README and the
generated catalogs were regenerated. Eval coverage rises from 78/139 to
83/144.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-03 20:19:26 -04:00
Magnus HedemarkGitHubfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
ONE family skill covering iOS, Android, Flutter, and React Native with
per-framework references (ios.md, android.md, flutter.md, react-native.md),
shared scaffold/build/sign/test/ship workflow, mobile lifecycle, offline and
sync guidance, and mobile-specific testing. Ships a 5-heading human README and
a schema-v1 eval manifest with 6 cases covering build/sign, testing, and
store-readiness. Adds the README index entry and regenerates catalogs.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-03 19:48:20 -04:00
Magnus HedemarkGitHubfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* feat(skill): add vLLM inference-serving skill (#247)
Add a single-tool vllm skill covering Docker/Kubernetes deployment,
quantization-aware model configuration (tensor parallelism, KV cache),
the OpenAI-compatible API surface, throughput/latency benchmarking,
continuous batching tuning, GPU operation, and upgrade/rollback.
Ships a read-only vllm-health probe (stdlib-only, --json), fillable
serving-config and benchmark-run-record templates, seven dated
references with upstream sources, a human-facing README, tests, and a
schema-v1 eval manifest with six cases covering config, benchmarking,
and troubleshooting.
Route ml-engineering to the new skill via a resolvable link alongside
llama-cpp, add the vllm entry to the top-level README index, and
regenerate the tracked catalogs.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* fix(skill): emit timeout exit 124 and bound /metrics reads in vllm-health
Address the review observations on the bundled probe: requests that exceed
--timeout now raise ProbeTimeout and make the tool exit 124 as documented
(previously they surfaced as exit 1), and the metrics check reads at most
64 KiB of /metrics and reports truncation instead of reading the whole body.
Adds tests for both behaviors.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
---------
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-03 19:31:36 -04:00
Magnus HedemarkGitHubfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Adds one top-level telemetry skill covering the observability stack that
deploys as one unit: Prometheus (scrape config, recording/alerting rules,
relabeling, retention, HA), the OpenTelemetry Collector (pipelines,
receivers/processors/exporters, sampling, trace/span correlation), and Loki
(ingest, LogQL, retention, labels).
Ships the read-only telemetry-check script (stdlib-only, --json): Prometheus
rule sanity mirroring promtool check rules plus scrape-target reachability
probes, fixture-tested with 16 unittest/pytest cases. Includes five dated
references, a human-facing README, and six eval cases covering rule authoring,
pipeline design, and retention. Routes up to platform-engineering and grafana
without duplicating their content. Regenerates the llms.txt / marketplace /
plugin catalogs and adds the README index entry.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-03 19:29:39 -04:00
Magnus HedemarkGitHubfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Add a one-tool PostgreSQL operations skill: configuration review, index and
query-plan analysis, vacuum/bloat, WAL archiving + point-in-time recovery,
replication/failover, extensions, upgrades, and evidence-based diagnostics.
Ships the read-only pgdiag collector (stdlib, --json, --plan-for, --help
without a cluster), 9 dated references, tests, a human README, 6 eval cases,
and the top-level index + regenerated catalogs. Routes app data access to
backend-engineering and schema design to data-architect/data-engineering.
Closes#245
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Magnus HedemarkandGitHub
Magnus Hedemark