Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
cloudflare-zaraz
Server-side tag management for third-party tools with edge execution, privacy controls, and near-zero performance impact
majiayu000/claude-skill-registry 163
-
okta
Manage users, groups, and applications via Okta API. Handle identity and access management.
majiayu000/claude-skill-registry 163
-
investigate
Systematically investigate bugs, test failures, build errors, performance issues, or unexpected behavior by cycling through characterize-isolate-hypothesize-test steps. Use when the user asks to "investigate this bug", "debug this", "figure out why this fails", "find the root cause", "why is this broken", "troubleshoot this", "diagnose the issue", "what's causing this error", "look into this failure", "why is this test failing", or "track down this bug".
majiayu000/claude-skill-registry 163
-
localsetup-humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing
text to make it sound more natural and human-written. Based on Wikipedia's
comprehensive "Signs of AI writing" guide. Detects and fixes patterns including:
inflated symbolism, promotional language, superficial -ing analyses, vague
attributions, em dash overuse, rule of three, AI vocabulary words, negative
parallelisms, and excessive conjunctive phrases.
majiayu000/claude-skill-registry 163
-
git-prune
This skill should be used when pruning local branches that have been deleted on the remote. It fetches remote changes, identifies stale local branches, and safely deletes them.
majiayu000/claude-skill-registry 163
-
traefik-rewrite-body-troubleshooting
Troubleshooting guide for the Traefik rewrite-body plugin (packruler/rewrite-body).
Covers two failure modes: (1) Compression failure — plugin logs "flate: corrupt input
before offset 5" when backends send gzip-compressed responses, corrupting response
bodies and breaking WebSocket connections, authentication flows, and mobile app
connectivity. (2) Silent skip — plugin silently skips content injection (rybbit
analytics, trap links, or any HTML rewriting) when the request Accept header doesn't
contain "text/html" (e.g., curl's default Accept: */*), making it appear broken
despite correct configuration.
majiayu000/claude-skill-registry 163
-
shipflow-deps
majiayu000/claude-skill-registry 163
-
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
majiayu000/claude-skill-registry 163
-
podcast-production-guide
Эксперт podcast production. Используй для создания подкастов, audio editing и distribution.
majiayu000/claude-skill-registry 163
-
ux-prototyping
Create interactive prototypes to test and refine digital product designs. Use for: wireframing, low/high-fidelity prototyping, user flows, interactive mockups, usability testing, design iteration, and stakeholder communication.
majiayu000/claude-skill-registry 163
-
time
LLM temporal reasoning scaffold for the temporal CLI.
majiayu000/claude-skill-registry 163
-
aget-file-issue
File issues with L520 governance compliance
majiayu000/claude-skill-registry 163
-
pdf-lab
Self-improving PDF extraction convergence loop. Diagnoses extraction failures by computing the delta between S00 estimates and actual extraction, reproduces issues on synthetic PDFs, discovers optimal parameters, and writes fixes back to the extractor pipeline code permanently.
majiayu000/claude-skill-registry 163
-
framework-selection
INVOKE THIS SKILL at the START of any LangChain/LangGraph/Deep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent skills.
majiayu000/claude-skill-registry 163
-
open-notebook
Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and summaries, creating multi-speaker podcasts from research, chatting with documents using context-aware AI, searching across materials with full-text and vector search, or running custom content transformations. Supports 16+ AI providers including OpenAI, Anthropic, Google, Ollama, Groq, and Mistral with complete data privacy through self-hosting.
majiayu000/claude-skill-registry 163
-
template-skill-congdon1207-agents-md-2
majiayu000/claude-skill-registry 163
-
fixing-accessibility
Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors. Use when adding interactive controls, forms, dialogs, or reviewing WCAG compliance.
majiayu000/claude-skill-registry 163
-
042-planning-openspec
Use when you need to take a `*.plan.md` file and turn it into OpenSpec change artifacts by validating OpenSpec installation, initializing or reusing an OpenSpec project, and creating or updating a change proposal/spec/tasks flow. Includes a concrete workflow based on `examples/requirements-examples/problem1/requirements/openspec`. Part of the skills-for-java project
majiayu000/claude-skill-registry 163
-
twelve-data-automation
Automate Twelve Data tasks via Rube MCP (Composio). Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
multi-agent-patterns
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
majiayu000/claude-skill-registry 163
-
tachyon-killer
General-purpose instability detector and killer. Tachyons are runaway modes -- imaginary mass, exponential growth, positive feedback disguised as negative. LRC resonance cancels instability without killing the system. GSO projection enforces symmetry constraints that eliminate entire classes of tachyon. What survives is the stable spectrum.
majiayu000/claude-skill-registry 163
-
code-review
Automated code review analyzing security, performance, maintainability, and test coverage. Activated during code reviews or when conducting analysis.
majiayu000/claude-skill-registry 163
-
50-execute-gated-150
[50] EXECUTE. Execute plans step-by-step with confirmation gates. Each step requires user approval before proceeding. Includes change management lifecycle (Pre-Change → During → Post-Change → Rollback). Use when implementing approved plans, deploying changes, or any multi-step execution requiring control and reversibility.
majiayu000/claude-skill-registry 163
-
bmad-sprint-status
Summarize sprint status and surface risks. Use when the user says "check sprint status" or "show sprint status"
majiayu000/claude-skill-registry 163