Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
building-skills-marketplace
Use when creating new Claude Code skills, setting up marketplace repositories, or packaging skills for distribution - complete workflow from skill creation to marketplace publication
majiayu000/claude-skill-registry 163
-
xterm-js
This skill should be used when working with xterm.js terminal implementations, React-based terminal applications, WebSocket terminal communication, or refactoring terminal-related code. It provides battle-tested patterns, common pitfalls, and debugging strategies learned from building production terminal applications.
majiayu000/claude-skill-registry 163
-
artifact-contract-auditor
Audit the workspace against the pipeline artifact contract (DONE outputs + pipeline target_artifacts).
Writes `output/CONTRACT_REPORT.md`.
**Trigger**: contract audit, artifact contract, missing artifacts, target_artifacts, CONTRACT_REPORT.
**Use when**: you want an auditable PASS/FAIL view of whether a workspace is complete and self-contained (end of run or before sharing).
**Skip if**: you are still intentionally mid-run and don’t care about completeness yet (but it’s still useful as a snapshot).
**Network**: none.
**Guardrail**: analysis-only; do not edit content artifacts; only write the report.
majiayu000/claude-skill-registry 163
-
harness
Automated quality check loops with escalation and fix sub-agents
majiayu000/claude-skill-registry 163
-
ln-210-epic-coordinator
CREATE/REPLAN Epics from scope (3-7 Epics). Batch Preview + Auto-extraction. Decompose-First Pattern. Auto-discovers team ID.
majiayu000/claude-skill-registry 163
-
flask-smorest-api
Set up Flask REST API with flask-smorest, OpenAPI docs, blueprint architecture, and dataclass models. Use when creating a new Flask API server, building REST endpoints, or setting up a production API.
majiayu000/claude-skill-registry 163
-
ncine-presentation
Slidev presentation documenting 14 years of nCine 2D game framework development.
majiayu000/claude-skill-registry 163
-
nushell-config-sync
Sync Nushell configuration files between the repo (os-config/nushell) and the system config path ($nu.config-path). Use when the user wants to push, pull, or diff nushell config files.
majiayu000/claude-skill-registry 163
-
narrative-conductor
Définit l'arc narratif complet et valide la cohérence narrative pour les épisodes NEW TEMPS X. Utilise ce Skill quand tu dois créer ou valider un arc narratif structuré en 7 actes, ou vérifier qu'un épisode respecte la structure narrative obligatoire et l'esprit Temps X.
majiayu000/claude-skill-registry 163
-
code-review
Reviews code for quality, security, and maintainability. Use after implementing features, completing significant work, or when user asks for code review.
majiayu000/claude-skill-registry 163
-
customizing-errors
Handle Zod validation errors with unified error API, custom messages, error formatting, and user-friendly display
majiayu000/claude-skill-registry 163
-
blog-scaffolding
Create new blog post structure for fabiorehm.com. Validates topic uniqueness, identifies personal angle, then creates scaffold through conversation.
Trigger phrases: "new post", "write about", "scaffold", "create post", "start writing", "new blog post"
majiayu000/claude-skill-registry 163
-
grimoire
Skill manager for Claude Code. Use when users want to list, search, install, update, remove, or create skills. Activated by requests like "install a skill", "what skills do I have", "find skills for X", "create a new skill", or "update my skills".
majiayu000/claude-skill-registry 163
-
validate-secrets
Validate SOPS encryption on secret files before committing. Use when staging secrets, committing encrypted files, or checking if secrets are properly encrypted. Prevents committing unencrypted secrets.
majiayu000/claude-skill-registry 163
-
verify
Verifies builds, recovers from errors, and applies review fixes. Use when user mentions ビルド, build, 検証, verify, エラー復旧, error recovery, 指摘を適用, apply fixes, テスト実行, tests fail, lint errors occur, CI breaks, テスト失敗, lintエラー, 型エラー, ビルドエラー, CIが落ちた. Do NOT load for: 実装作業, レビュー, セットアップ, 新機能開発.
majiayu000/claude-skill-registry 163
-
loogle
Search for Lean 4 and Mathlib theorems, lemmas, and definitions by type signature, name, or subexpression pattern. Use when the user asks to find a theorem, look up a Lean definition, search for lemmas, or needs help discovering Mathlib functions.
majiayu000/claude-skill-registry 163
-
s-work
General-purpose skill for Mechanic/Fen ecosystem work. Covers ecosystem context, development tools, component overview, and AFD principles. Use for everyday addon work, exploration, or when unsure which specialized skill to use. Triggers: work, build, develop, create, mechanic, fen, fencore, fenui, ecosystem, addon.
majiayu000/claude-skill-registry 163
-
spec-manager
MANDATORY specification writing skill. ONLY way to create/update specs.
Auto-invoke when:
- Creating specs: New projects, features ("I want to create XX")
- Updating specs: Feature additions, requirement changes, architecture updates
- Syncing specs: Major code changes (3+ files), refactoring, session end
- Keywords: specifications/spec/design/architecture/requirements/PRD
Outputs to .spec-manager/. Critical rules and workflow details in skill body.
majiayu000/claude-skill-registry 163
-
code-context-finder
Automatically find relevant context from knowledge graph and code relationships while coding. Detects when context would be helpful (new files, unfamiliar code, architectural decisions) and surfaces related entities, prior decisions, and code dependencies.
majiayu000/claude-skill-registry 163
-
langchain-orchestration
Comprehensive guide for building production-grade LLM applications using LangChain's chains, agents, memory systems, RAG patterns, and advanced orchestration
majiayu000/claude-skill-registry 163
-
prime-agent
Load project context including coding guidelines, styling rules, and folder structure before starting work.
majiayu000/claude-skill-registry 163
-
buck2-target-determination
This skill should be used when determining which Buck2 targets are affected by code changes for incremental builds and tests. Use this when users ask to test/build changed code, find affected targets, or run incremental workflows with jj revisions.
majiayu000/claude-skill-registry 163
-
meta-agent
Expert architect for generating OpenCode commands, skills, and sub-agent configuration files. Uses opencode-mastery skill for accurate OpenCode documentation. Use proactively when user wants to create, build, or generate new OpenCode components.
majiayu000/claude-skill-registry 163
-
render-output
Renders structured data to terminal with optimal formatting. Use when presenting agent results, displaying data to users, formatting command output, or showing validation reports. Transforms raw data into clear, scannable terminal output.
majiayu000/claude-skill-registry 163