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>
Adds references/vetting-third-party-skills.md with a dependency-style
vetting checklist (provenance, SKILL.md body, scripts, references),
safe first-run practice, and reporting guidance, citing the Snyk
ToxicSkills audit as the primary source for ecosystem risk statistics.
SKILL.md gains the match-prescriptiveness-to-fragility decision rule,
the run-vs-reference intent rule for bundled scripts, and an
Adopting Third-Party Skills section. README and eval manifest updated.
Closes#311
Quick Start now documents the --json and --dry-run flags with their
exact semantics (single JSON object on stdout; read-only no-write
guard) and points to `python3 scripts/promise-contract.py --help` for
the full flag list, so a no-prior-knowledge user can drive the CLI
end-to-end (VAL-USE-013). No other content changes.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-12 00:12:47 -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 promise-contract.py, a stdlib-only Python 3.10+ CLI that lints
promise-manifest v1 contracts (restricted-YAML or JSON) against the pinned
schema and renders a promise-graph summary. lint exits 0 on valid + full
coverage, 1 on lint errors/coverage gaps (accumulated, no fail-fast), and 2
on usage/IO errors; --json preserves the {valid, errors, warnings, coverage,
bindings} shape even on parse errors; --dry-run is a no-op guard. Robustness
handles empty/whitespace files, non-UTF-8 bytes, CRLF/BOM, JSON type errors,
and deep nesting without Python tracebacks.
Add tests/test_promise_contract.py covering valid contracts (YAML + JSON),
coverage gaps, schema violations, malformed input, --json, --dry-run, render,
and the robustness cases (empty, dup ids, bindings, enums, expires, encoding,
usage errors). 36 tests pass via unittest discover.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-11 23:32:21 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Add the three fillable templates (promise manifest YAML, agent contract,
promise review) and the human-facing README with the five required
sections. The manifest template is a lint-clean, fully covered example of
the pinned v1 schema with per-field comments; all intra-template id
references (accepts, expectations.about) resolve cross-agent. The contract
template carries the seven mandated sections with schema-aligned severity
and type vocabulary; the review template carries the five retrospective
sections with the three diagnosis categories.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Complete the seven-reference set for promise-theory. diagnosis-and-debugging.md
maps the Cemri et al. multi-agent failure taxonomy onto promise-theory breach
categories (specification issues ↔ broken promise bodies; inter-agent conflicts
↔ failed acceptance/incompatible co-languages; task verification problems ↔
missing assessment), adds withdrawal failure as a fourth promise-theoretic
class, documents a four-step diagnostic procedure (walk the promise graph →
check bindings → check evaluation loop → check withdrawal semantics) with a
worked example, and states the theory's limitations and open problems (no
coordination-quality benchmark, guarantees don't compose across handoffs, LLM
promises lack causal teeth, stochasticity, ambiguity. glossary.md defines all
27 architecture §4.2 terms as heading-/bold-led entries with citations plus a
related-terms section. Both files stay under 60k chars, resolve all backtick
*.md references and markdown links, and carry consistent EXTRAPOLATION /
[UNVERIFIED] provenance markers.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
EOF
)
2026-08-11 23:19:09 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Adds the three coordination references per architecture 4.2/6/7:
- agent-coordination.md: the core thesis with the fixed 11-concept mapping
table (concept -> concrete agent-coordination practice), the hybrid
human+agent boundary (humans as acceptors/evaluators, calibrated
subordination, causal vs moral responsibility, HITL escalation,
three-languages problem, swarms vs teams), the multi-agent lineage, and
the agent-council routing statement; cites Burgess arXiv:2604.10505 and
states the scarcity of direct literature.
- patterns.md: all seven canonical patterns with worked examples, the M12
ladder, the Ye & Tan contract tuple and lifecycle with degradation
semantics, the named ESCALATE-2 trigger, and the workflow-architect
routing via the bundles path.
- trust-and-verification.md: the two-component trust model, belief/evidence,
P_succ, verification rates as attention budgets incl. Dunbar budgets,
gameable assessment, semantic-promise measurement guidance, "confine,
don't convince", the versioned promise ledger, and routing to
agent-evals-and-observability and artifact-pyramids.
All files under the 60k-char reference cap with [UNVERIFIED]/EXTRAPOLATION
provenance markers per architecture 4.2.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-11 23:12:37 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Add the promise-theory skill's thin router (SKILL.md) and LICENSE per
architecture §4.1: frontmatter (name, trigger-oriented description with a
negative boundary, license MIT), a 8-line core-model summary with all six
mandated elements, all six use triggers, all five anti-triggers, a
Load-By-Need routing table covering the seven planned references, a Quick
Start (draft from template, lint with scripts/promise-contract.py),
cross-references to the six sibling skills, and all five gotchas. Grounded
in the mission research reports; sibling links resolve; references/*.md
links land with later reference features.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Fills the white space between sections with a bottom-of-page footer per
section: a content-derived field note (first anchor failure mode, first day
alternative, practical recheck item, or first skip reason) when one exists, a
next-section line with the following section's number, and a faint ghost
route mark. Footers hug the page bottom via flex column + margin-top auto;
multi-page sections carry the footer at the end of the section. Sheets fill
the print page so the footer lands at the bottom instead of floating.
Field notes repeat model content in one line and never invent new plans;
sections with nothing worth saying render the next-up line only. QA gate,
editorial reference, SKILL.md, and README updated; test suite extended to
cover footer presence, next-section wiring, and field-note content.
AI assistance: implementation and tests drafted by Jasper (Hermes Agent),
design reviewed and approved by Magnus Hedemark.
The reference's concepts, runtime descriptions, and commands are derived
from the supabase/evals README, which is Apache-2.0. Add an attribution
section to references/agent-evals.md with the license link and list the
harness repository in references/source-index.md, per the repository's
attribution convention.
Co-authored-by: factory-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>
Adds the visual deltas verified against the mock: a route journey line on the
cover for multi-stop trips, a color-coded trip-at-a-glance day strip after the
brief, pace and budget meters, ghost section numbers, a unified warm photo
grade on anchor images, and a lede drop cap. Day cards gain an optional kind
field (arrive, city, excursion, coast) that drives the strip colors; anchor
cards and the validator accept optional image fields. Photo-sourcing guidance
for free-license images added to the research reference, QA gate updated, and
the test suite extended to cover the new renderer and validator behavior.
AI assistance: implementation and tests drafted by Jasper (Hermes Agent),
design reviewed and approved by Magnus Hedemark.
2026-08-08 15:20:11 -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>
SkillOpt optimization of the travel-guide skill (3 autonomous greenfield epochs, 9/9 proposals accepted): page breaks ahead of all section headers, filesystem hygiene with dedicated working folders, sanitizer defaults redacting profile preferences/constraints, audience and private-by-default in the trip contract, process scaling for narrow questions, renderer-hang guidance, private-artifact image sourcing, shareable edition-phrasing review, and a narrow-question eval case.
Authored by Jasper (AI agent on behalf of Magnus Hedemark).
2026-08-08 03:01:24 -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).
* 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>
* fix: SkillOpt Epoch 1 — forward-deployed-engineering optimization
Inline the nine-stage contract table into SKILL.md (required question, minimum
output, stop condition per stage) with template links and the entry-evidence
rule; dedup the stage table out of references/lifecycle-and-artifacts.md into
a pointer. Name agent-evals-and-observability and production-readiness inline
in the applied-AI release gate (loading protocol step 5).
Validated: 2/2 held-out edits accepted (non-regression, all-pass baseline),
repo validators green (validate-skills, validate-skill-quality,
validate-bundles, validate-evals).
* fix: SkillOpt Epoch 2 — forward-deployed-engineering optimization
Add a 'Where to enter the lifecycle' table (existing state -> entry stage,
with the neckbeard route for bounded changes) and the entry-evidence rule for
mid-stream joins. Replace the flat 'When not to use' list with a proactive
Scenario | Reach for | Why routing table covering the six boundary routes.
Validated: 2/2 held-out edits accepted (non-regression, all-pass baseline)
plus a regression probe on epistemic labels; repo validators green.
* fix: SkillOpt Epoch 3 — forward-deployed-engineering optimization
Add references/worked-example-engagement.md, a fully synthetic depth
calibration artifact showing the charter, evidence-labeled ledger, stage
handoff, evaluation and release decision, adoption scorecard, outcome
measurement record, and productization record for one engagement. Add a File
map row, enumerate the templates row (surfacing engagement-status), and add a
depth-calibration pointer in the Lifecycle section.
Validated: 2/2 held-out edits accepted (non-regression, all-pass baseline);
repo validators green; sanitization scan clean (no private identifiers).
Fixes#289
- transcripts list: drop removed TranscriptsQueryScope type (scope is a
String in the live schema), require [String!] for organizers and
participants, add title/organizer-email/participant-email filters
- bites create: use the live transcript_Id argument name and the
BitePrivacy enum (public, team, participants)
- add ergonomic commands for documented gaps found in the audit:
askfred get, meetings update-channel, meetings share --expiry-days,
live add-to (addToLiveMeeting), live soundbite (createLiveSoundbite),
audio create-upload/confirm-upload (two-phase upload), users set-role
- add eval manifest (5 cases) to satisfy the modified-skill eval ratchet
- update SKILL.md, cli-reference, api-reference, source-index, workflows
to match the audited surface and record the 2026-08-05 schema audit
2026-08-05 22:29:36 -04:00
Magnus HedemarkGitHubfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
## What this adds
Implements the request in #287 and the Tier 1 audit gaps for the `linear` skill's `scripts/linear` CLI, reconciled against the live Linear GraphQL schema.
### New verbs
- `linear project update` — name, description, status, start/target dates, priority, with the same `--dry-run`/`--confirm` gate as issue mutations, and a local 255-character description guard matching Linear's `projectUpdate` limit (Linear rejects longer descriptions with a generic error).
- `linear issue archive` / `linear issue unarchive` — both gated, returning `IssueArchivePayload.entity`.
- `linear state list --team ENG` — first-class workflow-state discovery (previously states were only visible in the `issue move` failure path).
### Richer issue verbs
- `issue create` now accepts `--project`, `--parent`, `--assignee`, `--label` (repeatable), `--state`, `--due`.
- `issue update` now accepts `--assignee`, `--label` (add), `--remove-label`, `--due`, `--project`.
### Resolution rules (all require exactly one match, mirroring `resolve_team`)
- Project: UUID or exact name
- Parent: issue identifier or UUID
- Assignee: exact name, display name, or email (via `users`)
- Label: exact name within the issue's team (via `team.labels`)
- Workflow state: exact name within the issue's team (existing `team.states` resolver, now reusable for `--state` on create)
- Project status: exact name or type (via `projectStatuses`)
### Docs, tests, evals
- SKILL.md command map, state-change gate, and error/recovery sections; README; `domain-and-workflows.md` (project semantics + 255-char limit), `graphql-contract.md` (resolution queries), `integration-boundaries.md` (intentional exclusions list), `sources.md` (2026-08-05 schema re-verification note).
- 15 new offline tests (45 total) covering resolution, gates, dry-run intent, payload shapes, and field guards.
- Added a sixth eval case (`safe-project-and-issue-mutations`).
## Validation
- `python3 -m unittest linear/tests/test_linear.py` — 45/45 pass
- `python3 scripts/validate-evals.py`, `ruby scripts/validate-skills.rb`, `python3 scripts/check-artifacts.py`, `python3 scripts/eval-coverage.py --modified-from origin/main`, skill-quality validator, marketplace/codex/llms freshness, jscpd — all green locally
Closes#287
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>
Agent harnesses truncate file reads around ~60k characters, so the
largest dsm5 reference files (up to 132k chars) were being cut off
mid-file (reported: "The neurodevelopmental file was truncated").
- Split 15 reference files over 50k chars into a small index (original
filename preserved, so all existing links keep resolving) plus part
files of <= ~40k chars each, organized by disorder group
- Updated SKILL.md routing rows to point at indexes and read the part
for the condition; added large-file handling guidance
- Updated dsm5/README.md What You Get table; documented the size
convention in 00-overview-and-method.md (Maintaining this library)
- Verified: no reference file exceeds 50k chars (66 files), all 466
relative links resolve, validators pass, lookup.py lists all parts
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-04 22:10:15 -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>
* fix(calculator): honest burn-multiple and runway labels, surface model assumptions
- Burn Multiple now reports Graham's metric (net burn / net new ARR);
the net burn / MRR ratio is reported separately as Burn to Revenue.
The qualifier (efficient/healthy/warning/critical) is derived from the
real burn multiple, so DEAD verdicts no longer print 'efficient'.
- ALIVE verdicts no longer print a misleading 'Runway: 120 months'
(projection cap); output now shows 'Projected cash-out' with 'none
within the 10-year projection' when the company never runs out.
- Model assumptions (fixed/variable burn split, variable burn ratio,
growth decay, projection cap, safety buffer) are now surfaced in the
human report and in JSON model_assumptions.
- SKILL.md: fix dead paulgraham.com/default.html source URL to aord.html;
update output-field docs and examples to real model output.
- Add regression tests (tests/integration/test_default_alive.py).
Fixes#272Fixes#273
* docs(calculator): add When Not to Use boundary (validator requirement)
2026-08-04 11:30:05 -04:00
Magnus HedemarkGitHubfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
- vllm: rename test_empty_models_is_a_failure to
test_models_check_parses_from_stub and fix its misleading docstring;
it asserts positive-path parsing of the stub's served model list, not an
empty-models failure.
- stripe: pass cancel_at_period_end as the boolean True instead of the
string 'true', and normalize booleans to lowercase true/false during
form encoding so the wire payload stays Stripe-compatible.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-03 20:37:46 -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>
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
dependabot[bot]andGitHub