The catalog
610,220 rows, by stacks then stars
alexiolan/craft-skills/skills/browser-test Skill
18★ repoUse when a feature has been built and needs browser-based UI testing. Plans test scenarios, groups them into parallel batches, and dispatches multiple browser-tester agents simultaneously.
alexiolan/craft-skills/skills/llm-review Skill
18★ repoReference for local-LLM scripts. Calling skills run the bash commands inline in the main conversation — no dedicated agents. Covers the availability check, model loading, script execution, and unloading lifecycle.
alexiolan/craft-skills/skills/simplify Skill
18★ repoUse after implementation is complete to review changed code for reuse opportunities, quality issues, and architecture compliance. Identifies missed shared components, unnecessary complexity, and boundary violations.
alexiolan/craft-skills/skills/debug Skill
18★ repoUse when investigating bugs, errors, failing tests, or unexpected behavior. Enforces systematic root-cause investigation BEFORE attempting any fix. Invoke this skill before writing any fix code.
alexiolan/craft-skills/skills/finish Skill
18★ repoUse when implementation + verification are complete and the work needs to be integrated — commit, open a PR, merge, or clean up the branch. The final step of the craft pipeline (after develop/test/report). Works in the current checkout; no worktree assumption.
alexiolan/craft-skills/skills/bootstrap Skill
18★ repoLoaded at session start. Establishes awareness of craft-skills so the assistant invokes relevant skills before acting. Not invoked directly.
alexiolan/craft-skills/skills/graph-explore Skill
18★ repoReference for code-review-graph MCP queries. Calling skills run the graph tools inline via ToolSearch in the main conversation — no dedicated agents. Covers graph freshness, embedding setup, semantic search, and targeted queries.
alexiolan/craft-skills/skills/reflect Skill
18★ repoUse when auditing, improving, or maintaining project health — CLAUDE.md accuracy, memory hygiene, settings, plans, and pattern discovery. Invoke periodically or when the user asks to audit or improve their project configuration.
alexiolan/craft-skills/skills/aesthetic-direction Skill
18★ repoGenerate or verify the project's one-time AESTHETIC_DIRECTION.md — a design-language contract used by ux-brief and design-review. Invoked automatically by architect/craft when UI work is planned and .claude/aesthetic-direction.md does not yet exist. Auto-generates without blocking; user can refine the file later.
alexiolan/craft-skills/skills/reuse-index Skill
18★ repoStructured development skills for any project. Provides brainstorming, planning, parallel agent development, browser testing, systematic debugging, and self-improvement workflows.
alexiolan/craft-skills/skills/ux-brief Skill
18★ repoGenerate a structured UX brief for a feature before implementation — diagnosis + prioritized patches + success criteria — that downstream implementer agents (Sonnet, Qwen3.6, Haiku) execute without clarification. Invoked by architect/craft when the spec contains UI components. Solo frontend-design by default; combined mode (frontend-design + ui-ux-pro-max) for complex UI based on spec complexity tag.
alexiolan/craft-skills/skills/architect Skill
18★ repoUse when the user needs to plan and architect a new feature before implementation begins. This includes analyzing requirements, asking clarifying questions, and creating a detailed implementation plan aligned with the project's architecture. Invoke BEFORE any coding work starts.
alexiolan/craft-skills/skills/design-review Skill
18★ repoPost-develop visual regression + design-contract audit. Starts the dev server, captures screenshots of changed UI routes, and dispatches a Haiku-vision agent to compare the result against .claude/aesthetic-direction.md and the feature's ux-brief.md. Flags regressions before browser-test runs. Escalates to Sonnet or Opus only when Haiku flags issues.
alexiolan/craft-skills/skills/develop Skill
18★ repoUse when an approved implementation plan exists and is ready to be executed. Initializes shared state, dispatches parallel developer agents, performs integration review, and runs full verification (lint, tsc, format, build).
alexiolan/craft-skills/skills/craft Skill
18★ repoStructured development skills for any project. Provides brainstorming, planning, parallel agent development, browser testing, systematic debugging, and self-improvement workflows.
sgaunet/claude-plugins/plugins/software-engineering/skills/auto-mr Skill
18★ repoA curated collection of specialized Claude Code plugins designed to enhance your development workflow with intelligent agents, skills, and commands.
sgaunet/claude-plugins/plugins/go-specialist/skills/go-tool Skill
18★ repoA curated collection of specialized Claude Code plugins designed to enhance your development workflow with intelligent agents, skills, and commands.
sgaunet/claude-plugins/plugins/software-engineering/skills/detect-repo-host Skill
18★ repoA curated collection of specialized Claude Code plugins designed to enhance your development workflow with intelligent agents, skills, and commands.
sgaunet/claude-plugins/plugins/go-specialist/skills/go-blackbox Skill
18★ repoA curated collection of specialized Claude Code plugins designed to enhance your development workflow with intelligent agents, skills, and commands.
sgaunet/claude-plugins/plugins/go-specialist/skills/go-structure Skill
18★ repoA curated collection of specialized Claude Code plugins designed to enhance your development workflow with intelligent agents, skills, and commands.
sgaunet/claude-plugins/plugins/bash-specialist/skills/gum-beautify Skill
18★ repoA curated collection of specialized Claude Code plugins designed to enhance your development workflow with intelligent agents, skills, and commands.
sgaunet/claude-plugins/plugins/go-specialist/skills/go-bulma Skill
18★ repoA curated collection of specialized Claude Code plugins designed to enhance your development workflow with intelligent agents, skills, and commands.
understudylabs/understudy-agent-tools/skills/capture-evidence Skill
18★ repoUse when a developer wants to build an eval from their real LLM app before changing anything — "measure how my app is doing today", "build an eval from my workload", "we have no baseline", "is my current model actually good". Turns the workload into auditable local artifacts (harness, metric, frozen splits, baseline); has a public-benchmark on-ramp when no traces exist.
understudylabs/understudy-agent-tools/skills/check-routing-health Skill
18★ repoUse when a developer asks "is Understudy causing my errors", "which workloads are routed", "is my routing config actually taking effect", "is my provider healthy", "are there 500s on staging", "what's our error rate", "where is my gateway spend going", or wants self-service diagnostics without asking the team. Reads the hosted reporting endpoints with the developer's sk_* key.
understudylabs/understudy-agent-tools/skills/compare-model-sweep Skill
18★ repoUse when a developer wants to compare candidate models — any mix of local, gateway, or frontier — on the same eval and see quality, latency, cost, and reliability side by side. "Which model should I use", "sweep these models on my benchmark", "compare Gemma vs the frontier on my eval". To stand up and serve a local candidate first, use run-local-model-lab.
understudylabs/understudy-agent-tools/skills/compare-trajectories Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/curate-trajectories Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/design-simulated-environment Skill
18★ repoUse to build a simulated, seeded environment (AutomationBench / verifiers style) so any model can run a captured agentic workload end-to-end and be scored on final state — "simulate this workload's tools", "build a validator for these traces", "let a small model attempt the whole task", "score recall/precision against gold", or any handoff from understand-workload toward whole-case model comparison.
understudylabs/understudy-agent-tools/skills/deslop Skill
18★ repoUse when a user asks to "deslop", "de-AI", "make it sound human", remove AI patterns or tropes, clean up AI writing, review prose for authenticity, or draft substantial natural-sounding prose. Applies to papers, articles, memos, reports, newsletters, cover letters, and other edited writing.
understudylabs/understudy-agent-tools/skills/distill-classifier Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/export-trace Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/ingest-traces Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/inspect-billing-sources Skill
18★ repoUse when a developer wants to inspect Anthropic or Claude billing evidence from email, invoices, usage exports, or an authenticated billing website: "scan my Anthropic bills", "check billing emails", "look at the console usage page", "find spend hotspots from receipts". Optional, approval-gated evidence source for lower-Anthropic-bill audits.
understudylabs/understudy-agent-tools/skills/install-agent-adapter Skill
18★ repoUse when a developer wants to install, enable, update, reinstall, remove, or verify Understudy in a coding agent - "install Understudy", "add the Understudy skills", "make Claude/Cursor/Codex/OpenCode/Hermes/Devin see the skills". Chooses the requested agent platform and routes to the local install, reload, onboarding, and uninstall steps.
understudylabs/understudy-agent-tools/skills/install-codex-plugin Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/install-cursor-plugin Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/install-opencode-plugin Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/install-plugin Skill
18★ repoCompatibility shim for Claude Code installs. Use when a developer asks to install, update, enable, reinstall, remove, or verify the Understudy Claude Code plugin - "install Understudy in Claude", "add the Understudy skills", "why can't Claude see the skill". Route to install-agent-adapter with platform claude-code.
understudylabs/understudy-agent-tools/skills/instrument Skill
18★ repoUse when a developer's LLM app is running but has NO traces yet and wants capture flowing in about a minute with no code changes — "instrument my app", "start capturing my LLM calls", "I have no traces, get me some", "turn on tracing for my agent". Detects the provider SDK, redirects it through the Understudy gateway (capture on by default) via env vars, verifies a capture actually landed, then hands off to ingest-traces.
understudylabs/understudy-agent-tools/skills/ladder Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/latex-paper-polish Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/local-distillation-lab Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/lower-anthropic-bill Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/manage-local-models Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/onboard Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/operate-benchmark-lab Skill
18★ repoUse when a coding agent must operate the full benchmark lifecycle over local benchmark dirs — "build a benchmark from my traces and run models on it", "review and calibrate the eval", "queue a prompt experiment", "is an executor running", "read the rigor report". Covers traces → build-benchmark → review/feedback → calibration floors → candidate and prompt-override runs → rigor/CI reading → app-replay regression, via the benchmarks MCP server or CLI verbs, plus the run-executor daemon lifecycle.
understudylabs/understudy-agent-tools/skills/optimize-agentic-workload Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
Optimize local model compression
understudylabs/understudy-agent-tools/skills/optimize-local-model-compression Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/optimize-workload Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/plan-hosted-run Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/prepare-verifier-handoff Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/product-knowledge Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/ramp-and-verify Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/recursive-language-model Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/replay-app-harness Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/run-local-model-lab Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/share-savings Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/simulate-before-launch Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library
understudylabs/understudy-agent-tools/skills/understand-workload Skill
18★ repoUse when a developer wants a captured prompt, trace, or dataset explained before changing anything — "explain this prompt", "what is this trace actually doing", "decompose this workload", "help me understand this dataset before testing models". Builds a shared mental model (purpose, inputs, tools, success criteria) with the user through Q&A.
understudylabs/understudy-agent-tools/skills/understudy Skill
18★ repoPublic MIT-licensed Understudy agent tools and skill library