Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
generate-requirements
開発作業の要件定義書（requirements.md）を生成します。このスキルは単独で使用することも、generate-working-docsから呼び出されることもあります。
majiayu000/claude-skill-registry 163
-
identify
Identify friction points, bottlenecks, bugs, and technical debt. Use for audits, debugging sessions, when something feels wrong, or before major work to surface hidden issues. This is the second system in the 5-system framework.
majiayu000/claude-skill-registry 163
-
Collision-Zone Thinking
Force unrelated concepts together to discover emergent properties - "What if we treated X like Y?"
majiayu000/claude-skill-registry 163
-
detect-fed-unamortized-discount-pattern
檢查聯準會持有證券的未攤銷折價（Unamortized Discounts）是否出現與特定歷史危機期間相似的走勢模板，並用多指標交叉驗證是否真的屬於「金融壓力升高」而非單純會計/利率效果。
majiayu000/claude-skill-registry 163
-
multi-model-validation
Run multiple AI models in parallel for 3-5x speedup with ENFORCED performance statistics tracking. Use when validating with Grok, Gemini, GPT-5, DeepSeek, or Claudish proxy for code review, consensus analysis, or multi-expert validation. NEW in v3.1.0 - SubagentStop hook enforces statistics collection, MANDATORY checklist prevents incomplete reviews, timing instrumentation examples. Includes dynamic model discovery via `claudish --top-models` and `claudish --free`, session-based workspaces, and Pattern 7-8 for tracking model performance. Trigger keywords - "grok", "gemini", "gpt-5", "deepseek", "claudish", "multiple models", "parallel review", "external AI", "consensus", "multi-model", "model performance", "statistics", "free models".
majiayu000/claude-skill-registry 163
-
mkdocs-specific-rules
Defines specific rules related to MkDocs usage, including structure, plugins, themes, and customization configurations.
majiayu000/claude-skill-registry 163
-
dba-admin
DBA Admin Agent. 백업, 복구, 보안, 권한 관리를 담당합니다.
majiayu000/claude-skill-registry 163
-
epic-cli
Use the Epic CLI for project management, issue tracking, PR workflows, git worktrees, and debugging. Triggers on requests like "create a project", "start an issue", "work on PR", "create worktree", or "add debug statements".
majiayu000/claude-skill-registry 163
-
research-lookup
Look up current research information using Perplexity's Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter. Automatically selects the best model based on query complexity. Search academic papers, recent studies, technical documentation, and general research information with citations.
majiayu000/claude-skill-registry 163
-
describe-codebase
Generate an onboarding-level summary of a codebase for new developers, including architecture, patterns, and key entry points
majiayu000/claude-skill-registry 163
-
learning-data-collection
data-collection for evidence-based learning research and evaluation.
majiayu000/claude-skill-registry 163
-
rbac-permissions-architect
Use this skill when architecting new features within the RBAC modular permissions system. Guides architects through workspace design, feature definition, permission mapping, and role hierarchy. Critical for understanding Owner/Super Admin special roles, feature independence, and multi-tenant context isolation. Invoke when creating PRDs that involve permissions, workspaces, features, or role-based access control.
majiayu000/claude-skill-registry 163
-
micro-skill-creator
Rapidly creates atomic, focused skills optimized with evidence-based prompting, specialist agents, and systematic testing. Each micro-skill does one thing exceptionally well using self-consistency, program-of-thought, and plan-and-solve patterns. Enhanced with agent-creator principles and functionality-audit validation. Perfect for building composable workflow components.
majiayu000/claude-skill-registry 163
-
designing-experiments
Selects the appropriate quasi-experimental method (DiD, ITS, SC) based on data structure and research questions. Use when the user is unsure which method to apply.
majiayu000/claude-skill-registry 163
-
consistency-principle
Comportamientos y apariencias consistentes mejoran la usabilidad. Use cuando establezca patrones de diseño, defina guidelines, o evalúe coherencia del sistema.
majiayu000/claude-skill-registry 163
-
git-commit-helper
Generate conventional commit messages automatically. Use when user runs git commit, stages changes, or asks for commit message help. Analyzes git diff to create clear, descriptive conventional commit messages. Triggers on git commit, staged changes, commit message requests.
majiayu000/claude-skill-registry 163
-
review-claude-md-adherence
Verify code changes comply with CLAUDE.md instructions and project standards.
majiayu000/claude-skill-registry 163
-
learning-literature-review
literature-review for evidence-based learning research and evaluation.
majiayu000/claude-skill-registry 163
-
simple-fetch
Basic MCP skill demonstrating CLI-based execution pattern for fetching URL content
majiayu000/claude-skill-registry 163
-
validation-schemas
Enforces project Zod validation schema conventions when creating or modifying validation schemas. This skill ensures consistent patterns for drizzle-zod integration, custom zod utilities, schema composition, type exports, and form/action integration.
majiayu000/claude-skill-registry 163
-
convex-self-hosting
Guides self-hosted Convex deployment, authentication setup, environment configuration, troubleshooting, and production deployment considerations.
majiayu000/claude-skill-registry 163
-
refacter
Refacter code using complexity analysis and hotspot detection. Use when asked to refactor code, improve code quality, reduce complexity, or identify high-risk areas that need attention.
majiayu000/claude-skill-registry 163
-
ai-sdk-5
Vercel AI SDK 5 patterns. Trigger: When building AI features with AI SDK v5 (chat, streaming, tools/function calling, UIMessage parts), including migration from v4.
majiayu000/claude-skill-registry 163
-
containerize-apps
Containerizes applications with impact-aware Dockerfiles and docker-compose configurations. This skill should be used when containerizing projects for Docker, creating Dockerfiles, docker-compose files, or preparing applications for Kubernetes deployment. It performs impact analysis first (env vars, network topology, auth/CORS), then generates properly configured container configs. Invokes the impact-analyzer subagent for comprehensive project scanning.
majiayu000/claude-skill-registry 163