refs
217Skill Claude CodeCodex
Answer questions about a dependency's real source, history, and releases from the local checkouts managed by the refs CLI.
not rated 7
changed today A 26 tokens
original MIT
captain
218Skill Claude CodeCodex
Use this skill to run the Shipshape Captain role: human-facing discovery, durable specs and assets, Captain-only notes, blocker resolution, and outbound decisions. Default entry for new product intent and any user conversation.
not rated 7 1mo ago A 45 tokens
original 0BSD
shipshape
219Skill Claude CodeCodex
Use this skill to understand the Shipshape workflow, shared Articles of Agreement, and select the correct role skill: /captain, /qm, /crew, /boatswain, or /shipwright. Entry point when no role is active or the right role is unclear.
not rated 7 1mo ago A 58 tokens
original 0BSD
shipwright
220Skill Claude CodeCodex
Use this skill to run the Shipshape Shipwright role: in-harbour code inspection. Discovers existing behaviour and policy violations from production code, writes @captain-tagged scenario skeletons and @planks annotations for Captain review. Run for fitting out, onboarding an existing codebase, and between releases.
not rated 7 1mo ago A 66 tokens
original 0BSD
rigor3
221Skill Claude CodeCodex
Audit, score, remediate, and verify repositories across code hygiene, architecture hygiene, and engineering hygiene. Use for an explicit Rigor3 or three-hygiene request, a strict repository-wide quality audit, a cross-dimensional cleanup plan, or before-and-after verification. Do not use for an ordinary focused review…
not rated 7 21d ago A 78 tokens
original MIT
memory
222Skill Claude CodeCodex
Use Infinity Context MCP to search, propose, and manage durable project memory.
not rated 7 today A 17 tokens
original Apache-2.0
review-backend
223Skill Claude CodeCodex
Domain review checklist for the trovex backend — the Python/FastAPI + sqlite-vec/fastembed retrieval engine, the MCP server (trovex/trovexwrite/read/search/tag/delete + catalog resources), and the Active-Memory boot/capture loop. Applies to a diff touching src/trovex, scripts (CI guards), tests, benchmarks, deploy, or…
not rated 7 yesterday A 0 tokens
AGPL-3.0
review-frontend
224Skill Claude CodeCodex
Domain review checklist for the trovex web/ surface — the Vite/React/TypeScript landing + savings-calculator app AND the Vercel serverless API functions (web/api/.js) behind it (lead capture, Twenty-CRM mirror, inbound webhook, OG-card/badge generators). Applies to a diff under web/. Ordered highest-weight first: the…
not rated 7 yesterday A 0 tokens
AGPL-3.0
trovex
225Skill Claude CodeCodex
Token-efficient routing for a repo's Markdown docs. Use BEFORE reading or grepping any .md file to find the one canonical doc for a question — and to read it at the section level instead of whole. Trovex serves the single current doc per query (with a canonical/stale/duplicate freshness marker) for 60% fewer tokens…
not rated 7 yesterday A 0 tokens
AGPL-3.0
Skill Claude CodeCodex
Generates an AgenticBrowser Scripting DSL orchestration that implements a feature end-to-end — plan (if needed), TDD implementation, tests, and a lint/style-guide review pass — previews it as docs/scripting-features/feature- .scripting.md, and on user approval runs it via st-eval. Use this whenever the user wants to…
not rated 6
changed today A 224 tokens
Skill Claude CodeCodex
Build source-faithful and Dify-native frontend prototypes for Dify screens and proposed Dify features. Use when the user asks for Dify prototypes, Dify UI screens, Knowledge/Dataset/RAG prototype pages, login/default pages, navigation tabs, modals, tables, creation flows, or any frontend work that must follow Dify…
not rated 6 2mo ago A 89 tokens
original MIT
dify-rag-pm
228Skill Claude CodeCodex
Analyze, plan, design, and review Dify Dataset, Knowledge, and RAG product work. Use for Dataset lifecycle, Workflow Knowledge Retrieval nodes, field contracts, user stories, and KnowledgeFS-to-Dify product translation.
not rated 6 2mo ago A 52 tokens
original MIT
agent-loader
229Skill Claude CodeCodex
Load or list repo-scoped and user-scoped agent brains. Use when the user asks to load an agent by name, list available agents, inspect agent descriptions or workflows, or start a session or task with a personal agent brain.
not rated 6 2mo ago A 50 tokens
original MIT
Skill Claude CodeCodex
Preserve high-signal work context with local checkpoints and session crystals using the agent-crystallize CLI. Use before compaction, handoff, session end, cross-agent transfer, after major decisions/findings/failures, or when the user asks to checkpoint, crystallize, preserve context, save open loops, or create a…
not rated 6 20d ago A 76 tokens
fable-mode
231Skill Claude CodeCodex
MANDATORY before diagnosing any bug, debugging any failure, reviewing code, or making a non-trivial change — invoke FIRST, before reading code or proposing a cause; do not skip because the task "looks simple". Five-gate rigor protocol (scope, evidence, attack, verify, report) with per-task playbooks and tripwires.…
not rated 9 today A 108 tokens
original Apache-2.0
Skill Claude CodeCodex
Report the most fragile parts of this codebase, with evidence.
not rated 9 today A 20 tokens
original Apache-2.0
shadcn
233Skill Claude CodeCodex
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…
not rated 6 4d ago A 90 tokens
copy · 94% Apache-2.0
playwright-cli
234Skill Claude CodeCodex
Automate browser interactions, test web pages and work with Playwright tests.
not rated 6 4d ago A 19 tokens
copy · 92% Apache-2.0
react-doctor
235Skill Claude CodeCodex
Use when finishing a feature, fixing a bug, before committing React code, or when the user types /doctor, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.
not rated 6 4d ago A 70 tokens
copy · 100% Apache-2.0
Skill Claude CodeCodex
Orchestrate UI direction, composition, motion provider selection, implementation, and browser-proven quality for polished frontend work. Use when Codex needs to improve a visual surface with animation or interactive polish; when a request mixes design intent, component choice, browser validation, accessibility, or…
not rated 6 1mo ago A 111 tokens
original MIT
avo
237Skill Claude CodeCodex
Run an AVO evolutionary search where you are the variation operator. Use when the user asks to evolve, optimise, or improve a program against a benchmark with AVO — "run avo on game2048", "evolve the attention kernel", "continue the avo run", "do 10 more steps". Drives the loop via the avo MCP tools or the avo CLI.
not rated 8
+1 13d ago A 77 tokens
original Apache-2.0
handoff
238Skill Claude CodeCodex
Export or import local Waybill Bundles for unfinished coding-agent tasks. Use when the user asks for /handoff, /handoff export, /handoff import, or wants to continue from a Waybill bundle.
not rated 6 5d ago A 44 tokens
original Apache-2.0
waybill
239Skill Claude CodeCodex
Alias for the Waybill handoff workflow. Use when the user asks for /waybill, /waybill export, or /waybill import.
not rated 6 5d ago A 30 tokens
original Apache-2.0
before-you-build
240bin1874/before-you-build-skill
Skill Claude CodeCodex
Use before building or changing a product, feature, SaaS, AI app, side project, or startup idea to run a short demand, distribution, and failure-pattern reality check. Not for ordinary coding tasks where the decision to build is already clear.
not rated 5 2mo ago A 54 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: