Skill Claude CodeCodex
Audit implementation fidelity against a DomainSpec spec and produce a classified alignment report.
not rated 24 1mo ago A 19 tokens
Skill Claude CodeCodex
Deterministic code spec traceability — extract source tags, validate against a schema, and detect drift vs the spec.
not rated 24 1mo ago A 31 tokens
Skill Claude Code
Use when: a terminal capability receipt, typed pre-execution prerequisite, or current Work-Pack execution binding names one next owner route and the caller needs exact admission checks, one bounded dispatch, and a joined owner receipt without owner impersonation.
not rated 24 1mo ago A 51 tokens
Skill Claude Code
Use when: claiming one GitHub Project issue, refining its context, invoking define/design/plan as needed, executing through Task Session, and opening a linked PR with verification evidence.
not rated 24 1mo ago A 42 tokens
Skill Claude Code
Resolve a normalized intent against one digest-bound finite route catalog and return a non-authorizing candidate, ambiguity, no-match, or invalid disposition.
not rated 24 1mo ago A 33 tokens
Skill Claude CodeCodex
Derive a typed metric-obligation inventory from a DomainSpec spec's aspect docs (the doc->metrics rule method).
not rated 24 1mo ago A 30 tokens
refine
07Skill Claude CodeCodex
Use when the user asks to run or test Arcanum refine, create a refinement seed, refine a vague target through the canonical discovery/design loop, or inspect the refine lifecycle using native skill execution and dispatch-spec validation.
not rated 24 1mo ago A 47 tokens
Skill Claude CodeCodex
Generate story-driven STORIES from DomainSpec aspect docs with mandatory slice coverage and a concept-coverage matrix.
not rated 24 1mo ago A 25 tokens
Skill Claude CodeCodex
Deterministically derive a test-obligation spec from a DomainSpec feature's aspect docs (no LLM in the derivation path).
not rated 24 1mo ago A 32 tokens
Skill Claude Code
Use when: translating UX research, accessibility standards, market practice, and Playwright browser evidence into validator-safe checks, fixture plans, or evidence reports for finished frontend interfaces.
not rated 24 1mo ago A 39 tokens
ux-lessons
11Skill Claude Code
Use when: turning a UI iteration session into saved lessons and reusable ux-patterns that later feed ux-evidence-validator and ui-prototyping-studio.
not rated 24 1mo ago A 36 tokens
Skill Claude Code
Use when routing a verification target to status-qualified owner lanes and joining native evidence receipts into a VERIFICATION-WEAVE parent receipt without promoting owner outputs.
not rated 24 1mo ago A 34 tokens
Skill Claude Code
Use when: polling the ide-extension manual session bridge, claiming and executing one ready request in the current session, or submitting a claimant-bound result or interruption.
not rated 24 1mo ago B 36 tokens
workbench-up
14Skill Claude Code
Use when: starting or checking the ide-extension local workbench, making a request available for open-poll bridge testing, or running a bounded local bridge smoke.
not rated 24 1mo ago A 36 tokens
Skill Claude Code
Use when: building a compact, task-ready context pack from selector-level evidence and obligation-linked excerpts.
not rated 24 1mo ago A 23 tokens
Skill Claude Code
Use when: validating or designing an Arcanum dispatch route that chains sigils, spells, owner capabilities, handoffs, gates, observability, techniques, and optional boundary/evidence contracts.
not rated 24 1mo ago A 42 tokens
Skill Claude Code
Use when: creating or evolving a project-agnostic implementation layering model for a feature, capability, product workflow, research workflow, infrastructure change, or system improvement. Builds layers from minimum working unit proof to progressive hardening using value/cost layer-boundary heuristics.
not rated 24 1mo ago A 58 tokens
Skill Claude Code
Use when: deriving post-run behavior signals from a sigil invocation envelope and appending reusable observability telemetry.
not rated 24 1mo ago A 26 tokens
task-session
19Skill Claude Code
Use when: executing or resuming one nearest evidence-backed bounded work-pack task or SWU end to end, or routing explicit until-blocker series intent to its owning spell.
not rated 24 1mo ago A 38 tokens
Skill Claude CodeCodex
The design principle behind Principle 5 (pairwise tension) of the subagents-strategy constitution. Use when designing the angle set for an n≥2 subject group (role investigate or evaluate) so the agents' micro-vectors are structurally opposed and their correlated bias cancels under composition — not merely…
not rated 24 1mo ago A 96 tokens
Skill Claude Code
Use when opening, serving, checking, listing, or stopping existing local HTML artifacts through a verified loopback server and direct browser handoff.
not rated 24 1mo ago A 32 tokens
Skill Claude Code
Operate the ui-prototyping-studio as Claude Code — generate UI variants and drive the explore/annotate/mutate loop through the studio CLI. Every change is reversible; the human owns the one irreversible edge (export). Use when a human asks to explore, annotate, or revise UI prototypes in this project.
not rated 24 1mo ago A 72 tokens
critique
23Skill Claude CodeCodex
Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks…
not rated 24 1mo ago A 107 tokens
dashboard
24Skill Claude CodeCodex
Admin / analytics dashboard in a single HTML file. Fixed left sidebar, top bar with user/search, main grid of KPI cards and one or two charts. Use when the brief asks for a "dashboard", "admin", "analytics", or "control panel" screen.
not rated 24 1mo ago A 57 tokens
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: