Wire the Phase 3 ratchet into CI by passing the PR base SHA to
eval-coverage.py --modified-from. Expand changed-skill detection from
SKILL.md-only diffs to the entire skill directory so that references,
scripts, fixtures, README, and eval manifest edits all count as
modifications. Add a monotonic coverage floor that fails CI when
coverage decreases between the base and candidate revisions.
Add script tests for ratchet-mode detection and coverage-decrease
behaviour. Update AGENTS.md and CONTRIBUTING.md to describe the
behaviour CI now enforces.
Closes#102
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
Align AGENTS.md and CONTRIBUTING.md with the description-quality gates (#97, #98), eval coverage ratchet (#99), and trigger-boundary and eval requirements (#100) merged today. Document that CI validates generated artifact freshness but does not regenerate; contributors run generators locally with --write.
Co-authored-by: magnus919 <magnus919>
Align the meta-skill workflow with the repository's description-quality and eval-coverage gates. Keep harness-specific trigger checks separate from portable output-quality evals.
Co-authored-by: magnus919 <magnus919>
Phase 1: New skills (not in grandfathered-skills.txt) must have
evals/evals.json with at least 5 test cases. All 107 existing skills
are grandfathered.
Phase 2: scripts/eval-coverage.py reports coverage (skills with/without
evals, case counts, reference-priority sorting). Added as informational
CI step.
Phase 3: Ratchet thresholds — at 25% coverage, modified skills without
evals get a warning; at 50%, they fail CI. Enforced via
--modified-from flag for PR-scoped checks.
Closes#90
Two new reference files extending qa-methodology into the reactive side
of its domain — diagnosing failures rather than designing strategy.
ci-failure-triage.md: systematic CI failure diagnosis — runner
availability checks, log triage (gh run view), exit 137 / container
termination evidence-first procedure, pre-existing vs regression
classification, flaky test management, and compose readiness corollary.
Distilled from accumulated CI-failure incident notes.
test-debugging.md: diagnosing broken tests — mock path binding after
module-to-package refactors, FastAPI startup race (mock state set before
TestClient context is overwritten), httpx mock transport pattern, test
execution integrity (collection count vs exit code), deterministic
integration seeds, API signature change fixture recovery, and uv
lockfile hygiene. Distilled from accumulated test-debugging incident
notes.
Both are technique libraries serving qa-methodology's existing domain,
not new standalone skills. SKILL.md reference table updated.
Signed-off-by: Magnus Hedemark <magnus919@pm.me>
Generate a root discovery catalog from public skill frontmatter and fail CI
when the committed index drifts. Add a fixture-based regression test for
bundle paths, nested-helper exclusion, normalized descriptions,
deterministic ordering, and stale-file recovery.
Closes#78
AI-assisted: yes (Jasper/Hermes Agent)
Co-authored-by: magnus919 <magnus919>
The generator used File.basename which stripped the bundles/ prefix,
emitting ./neckbeard instead of ./bundles/neckbeard. Codex discovered
92/96 skills — the 4 bundle entrypoints were missing because their
paths didn't resolve.
Verified with live Codex CLI: all 96 skills now discoverable.
AI-assisted: yes (Jasper/Hermes Agent)
* fix: SkillOpt Epoch 1 — neckbeard description trigger-verb-first
Move trigger verbs (fix/build/refactor/review/verify/release) to the front
of the description for better discoverability. Negative case (non-software
questions) now correctly rejected. Validation: 4/6 held-out tasks correct.
* fix: SkillOpt Epoch 2 — wire overlooked catalog specialists into routing
Add 6 stage-owning methodology skills to the routing table and SKILL.md
summary: secure-software-engineering, web-accessibility, qa-methodology,
product-design-and-ux, api-design-and-evolution, site-reliability-engineering.
Note product-methodology and c4-diagramming as narrower composers.
Baseline rollout showed security reviews, UI features, and regression-safety
questions all routed without their natural specialist. Validation: 6/6 held-out
routing tasks now route correctly (baseline 3/6). All additions are
agent-agnostic methodology skills; no Hermes/deployment/personal content.
* fix: SkillOpt Epoch 3 — align stages.md Stage 4 with expanded routing
Stage 4 execution flow now names the same specialists added to the routing
table in Epoch 2: secure-software-engineering and web-accessibility for
implementation, qa-methodology for verification, product-design-and-ux and
api-design-and-evolution for design, site-reliability-engineering for delivery.
Rollout confirmed the gap: an agent following stages.md alone would route a
security-sensitive change (untrusted input, trust-boundary crossing) with no
security specialist. Validation: PASS — stages.md now names the specialist.
* fix: SkillOpt final validation — remove Hermes-specific skill_view reference
Replace skill_view(name="neckbeard") with agent-agnostic "read SKILL.md"
in Quick Start. Public skill must not reference Hermes-specific APIs.
* chore: regenerate Claude marketplace for neckbeard description update
* feat: add Codex plugin packaging (single-plugin, metadata-only)
Adds .codex-plugin/plugin.json with a skills array listing all public
skills, plus .agents/plugins/marketplace.json for one-command install:
codex plugin marketplace add magnus919/agent-skills
codex plugin install magnus919
Same pattern as mattpocock/skills — one plugin, explicit skill paths,
no dist/, no curation, no duplication. Bundle-internal helpers excluded
by the shared glob. CI check mode fails if the manifest drifts.
Closes#79
AI-assisted: yes (Jasper/Hermes Agent)
* chore: trigger CI
* chore: regenerate Codex plugin manifest to include neckbeard bundle
* feat: add neckbeard, an evidence-driven SDLC skill bundle
A portable operating model for software delivery that routes a change through
framing, discovery, design, implementation, review, verification, delivery, and
learning. Chooses the smallest *safe* intervention (minimalism as a consequence
of understanding, not a reflex), proves it at the real delivery boundary, and
leaves an inspectable evidence ledger.
Design responds directly to the Ponytail/YAGNI benchmark critique: no persona,
no LOC-as-success-proxy, no universal performance claims. Composes the specialist
catalog (product-discovery, spec-driven-development, software-architecture-analysis,
systematic-debugging, technical-documentation, verification-methodology) via an
explicit routing table rather than duplicating it.
Ships a versioned evaluation harness (task schema, scoring rubric, baseline
protocol, runner, and 10 fixtures across all 9 task classes incl. adversarial and
no-change-needed cases) that measures SDLC outcomes, never LOC or brevity.
Closes#25
* chore: regenerate Claude marketplace for neckbeard
Adds .claude-plugin/marketplace.json exposing all 95 public skills as
installable plugins via /plugin marketplace add magnus919/agent-skills.
Metadata-only approach: each entry uses source './' + skills ['./<name>']
+ strict:false, so no per-skill plugin.json or directory restructuring is
needed. Bundle-internal helper skills are excluded; bundle entrypoints are
included.
- scripts/gen-claude-marketplace.rb: generates and validates the manifest
- CI step fails if marketplace.json drifts from the skill tree
- README: Claude Code install instructions
Closes#76
AI-assisted: yes (Jasper/Hermes Agent)
The catalog entries don't need individual install commands — the
general 'Hermes Agent' section already explains how skills load.
Per-skill snippets are noise that has to be maintained for every
new skill.
Accumulates conventional commits into a Release PR that bumps the
version and updates CHANGELOG.md. Nothing is tagged until a human
merges the Release PR.
Co-authored-by: Jasper <jasper@magnus919.com>
Adds a dependency-free task-oriented Linear GraphQL CLI, progressive-disclosure guidance, offline safety tests, public-schema validation, and SkillOpt-derived help and promotion-gate improvements.
Adds the public Vercel Eve Agent Skill, validated through three autonomous greenfield SkillOpt epochs and exact-head CI.\n\nAI-assisted contribution; binding self-review recorded on PR #55.
* feat: add portable ESP32 development skill
Add source-backed workflows, safe templates, native CLI routing, and a read-only preflight for ESP32 hardware and firmware work.\n\nAI assistance: research, drafting, implementation, and review used OpenAI Codex and delegated DeepSeek agents under human direction.
* docs: harden ESP32 family and security guidance
Add source-backed family traps, brownout, calibration, USB recovery, and security-mode boundaries found during independent review.\n\nAI assistance: independent audits and drafting used delegated DeepSeek agents and OpenAI Codex under human direction.
