Skill Claude Code
WCAG 2.2 AA audit — perceivable, operable, understandable, robust criteria. Deep-dive for /launch-check accessibility.
not rated 533
+9
changed 4d ago A SkillSpector: pass 34 tokens
original MIT
533Stars on the repository
100Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
agdr
02Skill Claude Code
Browse / search / show / stats AgDRs across the portfolio — recalls "have we decided this before?".
not rated 533
+9
changed 4d ago A SkillSpector: pass 25 tokens
original MIT
Skill Claude Code
Analytics audit — SDK config, event naming, funnel completeness, dashboards. Deep-dive for /launch-check analytics.
not rated 533
+9
changed 4d ago A SkillSpector: pass 27 tokens
original MIT
Skill Claude Code
Record per-PR architecture-review approval for design-artifact PRs (required by the architecture gate). ONLY on an explicit per-PR architect "approved".
not rated 533
+9
changed 4d ago A SkillSpector: pass 35 tokens
original MIT
Skill Claude Code
Record per-PR design-review approval (UI merge gate). ONLY on an explicit per-PR designer "approved".
not rated 533
+9
changed 4d ago A SkillSpector: pass 26 tokens
original MIT
Skill Claude Code
Record per-PR CEO approval and merge in one turn. ONLY on an explicit per-PR "approved" — never on umbrella "go".
not rated 533
+9
changed 4d ago A SkillSpector: pass 33 tokens
original MIT
audit-deps
07Skill Claude Code
Audit dependencies for vulnerabilities, outdated packages, and license compliance.
not rated 533
+9
changed 4d ago A SkillSpector: pass 16 tokens
original MIT
bug
08Skill Claude Code
Create a structured bug ticket (Given/When/Then scenario, repro steps, severity).
not rated 533
+9
changed 4d ago A SkillSpector: warn 20 tokens
original MIT
c4
09Skill Claude Code
Generate C4 L1 (Context) + L2 (Container) Mermaid diagrams from a project's codebase. Structurizr DSL escape hatch (--dsl) for L3+ component precision.
not rated 533
+9
changed 4d ago A SkillSpector: warn 41 tokens
original MIT
challenge
10Skill Claude Code
Invoke The Contrarian (Naqid) to steelman-then-challenge an idea, feature, decision, or plan — surfaces assumptions, failure modes, and alternatives. Advisory only; never blocks a gate.
not rated 533
+9
changed 4d ago A SkillSpector: pass 44 tokens
original MIT
code-review
11Skill Claude Code
Review a PR for quality, security, and standards compliance. Invokes the Code Reviewer agent (Rex).
not rated 533
+9
changed 4d ago A SkillSpector: warn 25 tokens
original MIT
codify-rule
12Skill Claude Code
Turn a review comment that caught a Rex-miss into a draft handbook entry — Y/N gate, source-PR footer, bucket-routed.
not rated 533
+9
changed 4d ago A SkillSpector: warn 33 tokens
original MIT
Skill Claude Code
GDPR + ePrivacy audit — consent, privacy policy, data handling, right-to-deletion, DPAs. Deep-dive for /launch-check compliance.
not rated 533
+9
changed 4d ago A SkillSpector: warn 36 tokens
original MIT
debug
14Skill Claude Code
Hypothesis-driven debugging — architecture-first reading + evidence-before-fix. For bugs that resisted naïve fix attempts.
not rated 533
+9
changed 4d ago A SkillSpector: warn 25 tokens
original MIT
decide
15Skill Claude Code
Make a technical decision with structured reasoning and create an Agent Decision Record (AgDR).
not rated 533
+9
changed 4d ago A SkillSpector: warn 20 tokens
original MIT
Skill Claude Code
Review a technical design / migration AgDR / feature spec for architectural soundness BEFORE the Build phase. Invokes the Solution Architect agent (Tariq) — the non-code analog of /code-review.
not rated 533
+9
changed 4d ago A SkillSpector: warn 44 tokens
original MIT
design-sync
17Skill Claude Code
Sync a local component library to a claude.ai/design design-system project incrementally — one component at a time, never a wholesale replace. Drives the DesignSync tool.
not rated 533
+9
changed 4d ago A SkillSpector: pass 37 tokens
original MIT
dfd
18Skill Claude Code needs its repo
DFD with trust boundaries + data classifications (Mermaid + optional Threat Dragon JSON). Source-of-truth for /threat-model.
not rated 533
+9
changed 11d ago A SkillSpector: warn 30 tokens
original MIT
docs-audit
19Skill Claude Code
Diataxis docs audit — tutorials, how-to, reference, explanation; checks README, API docs, deployment guides, changelog, staleness.
not rated 533
+9
changed 4d ago A SkillSpector: pass 35 tokens
original MIT
eval-agents
20Skill Claude Code
Score a review agent (Rex/Hakim/Tariq) against a labeled PR corpus — ground-truth defect-set overlap, never a prose rubric. Headline metric is approve-precision.
not rated 533
+9
changed 4d ago A SkillSpector: warn 44 tokens
original MIT
Skill Claude Code needs its repo
Six-axis Feature Inventory (routes / models / jobs / tests / UI / docs) — a "what we must preserve" spec for greenfield rewrites.
not rated 533
+9
changed 4d ago A SkillSpector: pass 36 tokens
original MIT
fan-out
22Skill Claude Code
Spawn N parallel Agent calls in one message (per-task agent type, worktree isolation, background mode).
not rated 533
+9
changed 4d ago A SkillSpector: pass 24 tokens
original MIT
Skill Claude Code needs its repo
Per-feature Mermaid flowchart — routes / models / jobs / screens. Consumes /extract-features inventory.
not rated 533
+9
changed 4d ago A SkillSpector: warn 26 tokens
original MIT
feature
24Skill Claude Code
Create a structured feature ticket (user story, acceptance criteria, design notes) for a new user-facing feature.
not rated 533
+9
changed 4d ago A SkillSpector: warn 24 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: