Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
piper
Convert text to speech using Piper, a fast, local, neural text-to-speech system with natural sounding voices. This skill is triggered when the user says things like "convert text to speech", "text to audio", "read this aloud", "create audio from text", "generate speech from text", "make an audio file from this text", or "use piper TTS".
majiayu000/claude-skill-registry 163
-
frontend--accessibility
Apply the Agent OS standard for frontend accessibility.
majiayu000/claude-skill-registry 163
-
hooks-validator
Validates React code for Rules of Hooks violations. Catches issues like hooks called after conditional returns that cause production crashes (React error
majiayu000/claude-skill-registry 163
-
business-logic-coder
Implement business logic with ActiveInteraction and AASM state machines. Use when creating typed operations, managing state transitions, or refactoring service objects. Triggers on interaction creation, state machines, workflows, or typed business operations.
majiayu000/claude-skill-registry 163
-
Skill Define
Validate and register new Claude Code Skill manifests (.skill.yaml) to ensure structure, inputs/outputs, and dependencies are correct.
majiayu000/claude-skill-registry 163
-
unit-executor
Execute exactly one runnable unit from `UNITS.csv` (first TODO whose dependencies are DONE), then update unit status and artifacts.
**Trigger**: unit executor, run one unit, next unit, step-by-step pipeline, 逐条执行, UNITS.csv.
**Use when**: 需要严格“一次只做一个 unit”（可审计、可中断），并遵守 checkpoints/HUMAN 阻塞逻辑。
**Skip if**: 要端到端自动跑（用 `research-pipeline-runner`）或 workspace 不存在。
**Network**: none.
**Guardrail**: 只执行一个 unit；满足验收且输出存在才可标 `DONE`；遇到 HUMAN checkpoint 必须停下。
majiayu000/claude-skill-registry 163
-
scribe-mcp-usage
Operate the local Scribe MCP tools for logging, project setup, manage_docs workflows, read_file usage, bridge integrations, and sentinel/project mode discipline. Use whenever you need to follow Scribe tool contracts, document management rules, or bridge development.
majiayu000/claude-skill-registry 163
-
always-works-testing
Default testing standard for all implementation work - ensures code actually works through mandatory execution validation before confirming to user. Applies automatically whenever writing, modifying, debugging, or implementing any code (scripts, APIs, UI, configs, data operations, logic changes). This is the baseline expectation, not an optional extra - every implementation must be verified through actual execution, not assumed correct.
majiayu000/claude-skill-registry 163
-
test-generation
Generate comprehensive test cases for code
majiayu000/claude-skill-registry 163
-
Implementation Planning Skill
実装タスクを計画的に進めるためのスキルです。複雑な実装や複数ステップを要するタスクの場合、まず計画を立ててから実装を進めます。
majiayu000/claude-skill-registry 163
-
neuropixels-analysis
Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.
majiayu000/claude-skill-registry 163
-
comprehensive-code-review
This skill should be used when reviewing pull requests, performing comprehensive code review, analyzing code changes before merge, or when the user asks for thorough/ultra-critical code review. Performs EXTREMELY CRITICAL 6-pass analysis identifying runtime failures, code consistency issues, architectural problems, environment compatibility risks, and verification strategies. Posts structured review as GitHub PR comment. Use when user asks to "review PR", "review this code", "review changes", "check this PR", "analyze PR", "post review", or for Phase 3 of devflow. Supports parallel review mode with multiplier (code-review-3, code-review 6X) for consensus-based reviews. This is an ultra-critical reviewer that does not let things slip and desires only perfection.
majiayu000/claude-skill-registry 163
-
Buildkite issue solver
Will utilise buildkite read only mcp server to solve specific buildkite issues encountered
majiayu000/claude-skill-registry 163
-
translate skill
Use this skill when you are doing localization and translation work.
majiayu000/claude-skill-registry 163
-
cracked-it-problem-solver
Complete strategic problem-solving methodology from "Cracked It!" by Garrette, Phelps & Sibony. Use when users need to solve complex ill-defined business problems, structure and analyze strategic issues, develop and validate solutions, or present recommendations persuasively. Covers the complete 4S Method (State, Structure, Solve, Sell) from problem definition through solution delivery. Use for strategy consulting, business analysis, decision-making, and solving wicked problems that resist simple frameworks.
majiayu000/claude-skill-registry 163
-
agent-33-skills-maker
Create Claude Desktop skills from descriptions, SOPs, or existing agents. Three modes - create from scratch, convert SOPs to skills, or migrate agents to skill format. Outputs ready-to-deploy .zip packages.
majiayu000/claude-skill-registry 163
-
task-expert
'Task as Code' management expert. Responsible for maintaining task files in the todos/ directory, ensuring continuous task IDs, clear statuses, and adherence to specifications.
majiayu000/claude-skill-registry 163
-
skill-usage
Core skills system that manages loading and using other skills through progressive disclosure. Load at startup to enable automatic skill discovery and invocation across all projects.
majiayu000/claude-skill-registry 163
-
agent-mcp-developer
Expert MCP developer specializing in Model Context Protocol server and client development. Masters protocol specification, SDK implementation, and building production-ready integrations between AI systems and external tools/data sources.
majiayu000/claude-skill-registry 163
-
tech-blog
Write technical blog posts with source code analysis OR doc-driven research. Use when user wants to explain system internals, architecture, implementation details, or technical concepts with citations.
majiayu000/claude-skill-registry 163
-
sentry-known-pitfalls
Execute common Sentry pitfalls and how to avoid them.
Use when troubleshooting Sentry issues, reviewing configurations,
or preventing common mistakes.
Trigger with phrases like "sentry mistakes", "sentry pitfalls",
"sentry common issues", "sentry anti-patterns".
majiayu000/claude-skill-registry 163
-
customer-expansion
Create expansion roadmaps, QBR templates, and upsell playbooks to grow existing customer revenue through strategic account development.
majiayu000/claude-skill-registry 163
-
searching-code
Intelligent codebase search via WarpGrep. Use when user asks "how does X work", "trace flow", "find all implementations", "understand codebase", or needs cross-file exploration in large repos (1000+ files).
majiayu000/claude-skill-registry 163
-
managing-session-continuity
Managing session continuity across Claude conversations by saving structured context (tasks, files, errors, git state) to JSON and loading in new sessions. Use when user asks how session continuity works, explaining session protocol functionality, understanding session state management, describing what gets saved in sessions, ending a session with unfinished work, starting a session with existing session-protocol.json, or when user mentions 'save progress', 'save session', 'save my work', 'continue later', 'session context', 'pick up where left off', 'load session', 'restore session', or explicitly invokes /save-session-protocol or /load-session-protocol commands.
majiayu000/claude-skill-registry 163