Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
spec-driven-analytics
Orchestrate session data mining operations through a 7-phase workflow with structural anti-skip enforcement. Analyzes Claude Code history.jsonl files and workflow artifacts to deliver formatted, actionable analytics for workflow patterns, errors, decisions, and command sequences. Prevents token optimization bias through per-phase reference loading, checkpoint persistence, Execute-Verify-Record enforcement, and artifact verification. Use when analyzing session data, extracting workflow patterns, investigating error trends, or reviewing development decisions. Always use this skill when the user runs /analytics or mentions session analytics, workflow patterns, error mining, decision archive, or command sequence analysis.
majiayu000/claude-skill-registry 163
-
openstack-cinder
OpenStack Cinder block storage service. Provides persistent volume management for cloud instances including volume creation, snapshots, backups, LVM/iSCSI backend, volume types with QoS, encryption (LUKS), volume migration, and multi-backend support. Use for deploying, configuring, operating, and troubleshooting OpenStack block storage.
majiayu000/claude-skill-registry 163
-
blockrun
Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek")
majiayu000/claude-skill-registry 163
-
foundry
Self-writing meta-extension that forges new capabilities — researches docs, writes extensions, tools, hooks, and skills
majiayu000/claude-skill-registry 163
-
implement
Executes implement-stage loop workflow for the next scoped work item through stage-chain orchestration. Use when implement stage enters loop mode.
majiayu000/claude-skill-registry 163
-
openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
majiayu000/claude-skill-registry 163
-
seed-test-students
Guides you through seeding test students with specific profiles for manual testing of features. Use when you need to create seed data to test a feature in the browser, or when recommending which seed profiles to use for testing a feature.
majiayu000/claude-skill-registry 163
-
docker
Manage Docker containers, images, networks, and volumes using the Docker CLI.
majiayu000/claude-skill-registry 163
-
ad-review
Quality review ads before launch by verifying hook strength, checking proof elements, evaluating CTA effectiveness, and assessing visual quality and authenticity. Use as final check before launching creative or when reviewing team submissions.
majiayu000/claude-skill-registry 163
-
react-router-v7
React Router v7 best practices for data-driven routing. Use when implementing routes, loaders, actions, Form components, fetchers, navigation guards, protected routes, or URL search params. Triggers on createBrowserRouter, RouterProvider, useLoaderData, useActionData, useFetcher, NavLink, Outlet.
majiayu000/claude-skill-registry 163
-
AgentDB Reinforcement Learning Training
majiayu000/claude-skill-registry 163
-
assess-slts
Evaluate SLT quality across 5 dimensions with rewrite suggestions.
majiayu000/claude-skill-registry 163
-
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
majiayu000/claude-skill-registry 163
-
optimizing-attention-flash
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
majiayu000/claude-skill-registry 163
-
schema-analyzer
Analyze MongoDB collection schemas, infer data types, detect inconsistencies, and recommend schema design improvements. Use when the user asks about database structure, data modeling, schema validation, or wants to understand their MongoDB collections.
majiayu000/claude-skill-registry 163
-
ai-sdk-core
Build backend AI with Vercel AI SDK v6 stable. Covers Output API (replaces generateObject/streamObject), speech synthesis, transcription, embeddings, MCP tools with security guidance. Includes v4→v5 migration and 15 error solutions with workarounds.
Use when: implementing AI SDK v5/v6, migrating versions, troubleshooting AI_APICallError, Workers startup issues, Output API errors, Gemini caching issues, Anthropic tool errors, MCP tools, or stream resumption failures.
majiayu000/claude-skill-registry 163
-
debug-fetcher
Automated URL fetch failure handling with strategy exhaustion, memory learning, and human-in-the-loop recovery. Use when fetches fail and you need intelligent retry, pattern learning, and human collaboration.
majiayu000/claude-skill-registry 163
-
language-patterns
Provides language-specific patterns for TypeScript, Python, and React including idioms, best practices, and common patterns. Use when implementing features in these languages.
majiayu000/claude-skill-registry 163
-
python-module-to-package-refactor
Use when splitting a Python module (>400 LOC) into a package. mock.patch target update rules and checklist.
majiayu000/claude-skill-registry 163
-
sms-alert-automation
Automate SMS Alert tasks via Rube MCP (Composio). Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
spec-driven-cc-guide
Expert knowledge base for Claude Code Terminal — the CLI tool itself, not coding tasks. Implements 4 knowledge-retrieval phases with structural anti-skip enforcement using the Execute-Verify-Gate pattern at every step. Designed to prevent token optimization bias that causes reference file skipping by making every reference load mandatory and verifiable. MUST use this skill whenever the user asks about Claude Code features, configuration, setup, or troubleshooting. This includes: keyboard shortcuts not working (Option key, Alt+P, Shift+Enter, Ctrl+B), creating or configuring subagents/skills/commands/plugins, setting up hooks (PreToolUse, PostToolUse, HTTP hooks), installing or debugging MCP servers, GitHub Actions or GitLab CI/CD integration for PR reviews, switching models mid-conversation, undoing or rewinding Claude's changes, proxy/network configuration, permission modes, memory and CLAUDE.md setup, the /batch /simplify /debug bundled skills, git worktrees, agent teams, remote control, headless mode, or ANY question where the user is asking about how Claude Code works rather than asking Claude Code to do coding work. When in doubt about whether a question is about Claude Code itself vs. a coding task, prefer triggering this skill — it will not interfere with coding-focused responses.
majiayu000/claude-skill-registry 163
-
Coding Conventions
Automatically apply standard coding conventions when writing or modifying code. Use this skill when working with Python, TypeScript, JavaScript, Go, PHP, or creating git commits. Triggers include writing new code, refactoring existing code, or committing changes in supported languages.
majiayu000/claude-skill-registry 163
-
taggun-automation
Automate Taggun tasks via Rube MCP (Composio). Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
tmux
Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output.
majiayu000/claude-skill-registry 163