Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
ask-peer
Consult with a peer engineer for plan review, code review, implementation discussions, or problem-solving brainstorming. Use when you need a second opinion, want to validate your approach, or check for overlooked issues.
majiayu000/claude-skill-registry 163
-
subagents-creator
Guide for creating Claude Code subagents (custom agents) - specialized AI assistants with isolated context. Use when the user wants to create, add, or configure a subagent/custom agent for Claude Code.
majiayu000/claude-skill-registry 163
-
pytorch-common-pitfalls
Fix common PyTorch bugs: percentile calculations, LayerNorm for Conv1d, buffer edge cases. Trigger when writing PyTorch code for RL or neural networks.
majiayu000/claude-skill-registry 163
-
ledger-registry
Reads /ledger/manifest.json, verifies per-ledger checksums, and returns the active ledger map. **Version:** 1.1 **Author:** Entropy Control Theory **License:** MIT **Based on:** Structure DNA v1.0 + PROFILE-GENERATOR-SPEC v1.0
majiayu000/claude-skill-registry 163
-
enhance-workflow
Analyze, refactor, and enhance existing Workscript workflow JSON files based on user feedback. Use when asked to improve, optimize, refactor, fix, or enhance an existing workflow. Triggers on requests like "improve this workflow", "optimize the X workflow", "add error handling to", "make this workflow more robust", "refactor for flat structure", or when users provide critique, suggestions, or requirements for workflow improvements. Complements the new-workflow skill by handling post-creation refinements.
majiayu000/claude-skill-registry 163
-
unified-search-discover
Progressive search and discovery with structured refinement workflows for file finding, content searching, and safe refactoring operations using fd/find, rg/grep, and ast-grep tools. Use when searching, discovering, or refactoring code with progressive refinement patterns.
majiayu000/claude-skill-registry 163
-
Go Complexity Reduction
This skill should be used when the user asks about "gocyclo", "funlen", "cyclop", "nestif", "cognitive complexity", "refactor long function", "reduce nesting", "complexity reduction", or needs guidance on simplifying complex Go code. Provides patterns and techniques for reducing Go code complexity while preserving behavior.
majiayu000/claude-skill-registry 163
-
infrastructure-standards
Infrastructure, cloud, and DevOps standards. Use when setting up new projects, configuring cloud resources, or working with IaC.
majiayu000/claude-skill-registry 163
-
technical-constitution
Generates technical implementation plans and architectural strategies that enforce the Project Constitution. Use when designing new features, starting implementation tasks, refactoring code, or ensuring compliance with critical standards like Testability-First Architecture, security mandates, testing strategies, and error handling.
majiayu000/claude-skill-registry 163
-
php-coding-standards
Invoke BEFORE writing PHP code. Provides coding standards and naming conventions.
majiayu000/claude-skill-registry 163
-
create-review-checklist
Generate review checklists for different change types. Use to customize review focus based on what was changed.
majiayu000/claude-skill-registry 163
-
honest-reflections
Systematic gap analysis for claimed vs actual work completion. Uses 100+ sequential thoughts
to identify assumptions, partial completions, missing components, and rationalization patterns.
Validates completion claims against original plans, detects scope deviations, reveals quality gaps.
Essential for self-assessment before declaring work complete. Use when: claiming completion,
final reviews, quality audits, detecting rationalization patterns in own work.
majiayu000/claude-skill-registry 163
-
understand-codebase
Use when exploring codebase, architecture, or call flows.
majiayu000/claude-skill-registry 163
-
sequentialthinking
Use this skill for systematic problem-solving through structured, iterative thinking. Break down complex problems, iterate on understanding, catch edge cases, and validate solutions comprehensively.
majiayu000/claude-skill-registry 163
-
story-refinement
majiayu000/claude-skill-registry 163
-
lottie
Renders After Effects animations as lightweight JSON on web and mobile using lottie-web. Use when adding vector animations, loading indicators, or complex motion graphics without video files.
majiayu000/claude-skill-registry 163
-
session-summary
End-of-session summary that logs work completed to Obsidian. Run this at the end of any Claude Code session to capture what you accomplished. Creates or appends to the daily session log.
majiayu000/claude-skill-registry 163
-
codex-read
Read and integrate response from Codex. Use when user says codex read, get codex response, or check codex results.
majiayu000/claude-skill-registry 163
-
semantic-code-hunter
Use when you need to find code by concept (not just text). Uses Serena MCP for semantic code search across the codebase with minimal token usage. Ideal for understanding architecture, finding authentication flows, or multi-file refactoring.
majiayu000/claude-skill-registry 163
-
skill-retrieval
Semantic search over skill libraries using ColBERT embeddings. Use when:
- "find a skill for..." or "search for skills that..."
- "what skill handles..." or "which skill can..."
- "index my skills" or "rebuild the skill index"
- "show me relevant skills for this task"
majiayu000/claude-skill-registry 163
-
cursor-reference-architecture
Execute reference architecture patterns for Cursor IDE projects. Triggers on "cursor architecture",
"cursor project structure", "cursor best practices", "cursor team setup". Use when working with cursor reference architecture functionality. Trigger with phrases like "cursor reference architecture", "cursor architecture", "cursor".
majiayu000/claude-skill-registry 163
-
epcp-workflow
Apply the Explore → Plan → Code → Commit workflow for tasks like implementing features, fixing bugs, refactors, or adding integrations. Use this when the user wants changes in a repo and wants higher reliability (read first, plan then commit/PR). Emphasize subagents for investigation during Explore, and use "think / think hard / think harder / ultrathink" during Plan when alternatives exist.
majiayu000/claude-skill-registry 163
-
prompt-optimizer
This skill should be used when users request help optimizing, improving, or refining their prompts or instructions for AI models. Use this skill when users provide vague, unclear, or poorly structured prompts and need assistance transforming them into clear, effective, and well-structured instructions that AI models can better understand and execute. This skill applies comprehensive prompt engineering best practices to enhance prompt quality, clarity, and effectiveness.
majiayu000/claude-skill-registry 163
-
Playwright Browser Automation
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
majiayu000/claude-skill-registry 163