Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
Cost Optimization Analyzer
This skill should be used when the user asks to "analyze costs", "optimize infrastructure spending", "reduce operational expenses", "monitor API costs", "audit cloud resources", "optimize database queries", or needs comprehensive cost analysis and optimization recommendations.
majiayu000/claude-skill-registry 163
-
hygiene
Use when enforcing defensive coding practices that treat all data as untrusted — regardless of source. Covers sanitization, canonicalization, encoding, and validation of inputs AND outputs at every component boundary, including internal databases, caches, message queues, and inter-service calls.
USE FOR: data hygiene, sanitization, canonicalization, normalization, output encoding, trust boundaries, defense in depth, zero trust data handling, internal data validation, component boundary security
DO NOT USE FOR: specific injection attack patterns (use input-validation or owasp), cryptographic controls (use cryptography), API-level security headers (use api-security)
majiayu000/claude-skill-registry 163
-
monitoring-readiness
監視要件を定義し、アラート・メトリクス設定を提案
majiayu000/claude-skill-registry 163
-
priority-classification
Automatically classifies tasks into four priority levels (VERY IMPORTANT, HIGH, MEDIUM, LOW) based on due dates, urgency keywords, and explicit priority settings. Triggers special behaviors for VERY IMPORTANT tasks including notifications and visual emphasis.
majiayu000/claude-skill-registry 163
-
agentuity-cli-cloud-deployment-remove
Remove a specific deployment. Requires authentication. Use for Agentuity cloud platform operations
majiayu000/claude-skill-registry 163
-
nano-nets-automation
Automate Nano Nets tasks via Rube MCP (Composio). Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
autonomous-skill
Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Codex non-interactive mode with auto-continuation. Trigger phrases include autonomous, long-running task, multi-session, 自主执行, 长时任务, autonomous skill.
majiayu000/claude-skill-registry 163
-
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
majiayu000/claude-skill-registry 163
-
react-best-practices
Apply React and Next.js performance optimization guidelines from Vercel Engineering — 40+ rules covering components, data fetching, bundle optimization, and rendering. Triggers on React components, Next.js pages, bundle optimization, performance improvements, refactoring React code.
majiayu000/claude-skill-registry 163
-
video-production
Activate for video marketing strategy, script writing, video specifications for YouTube/TikTok/Instagram Reels/LinkedIn, production workflows, video optimization, thumbnail creation, and video repurposing. Used by content-creator and social-media-manager agents.
majiayu000/claude-skill-registry 163
-
dbt
dbt is a tool for transforming data in warehouses using SQL-based models, enabling testing and documentation.
majiayu000/claude-skill-registry 163
-
voice-call
Start voice calls via the OpenPaw voice-call plugin.
majiayu000/claude-skill-registry 163
-
design-md
Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files
majiayu000/claude-skill-registry 163
-
autonomous-skill
Execute long-running, multi-session tasks autonomously using Claude Code headless mode or in-session hook-based loops. Supports structured task decomposition (for complex projects) and lightweight Ralph-style iteration (for TDD, bug fixing, refactoring). Use this skill whenever the user says "autonomous", "long-running task", "multi-session", "run this in the background", "keep working on this", "batch process", "iterate until done", "ralph loop", or wants any task that requires sustained, unattended execution.
majiayu000/claude-skill-registry 163
-
update-docs
Update all documentation in docs and AGENTS.md files to match current codebase state. Use when user asks to update docs, refresh documentation, sync docs with code, or validate documentation accuracy.
majiayu000/claude-skill-registry 163
-
bluebubbles
iMessage via BlueBubbles server: self-hosted iMessage bridge, Android/web access, API
majiayu000/claude-skill-registry 163
-
stitch-a11y
Audits Stitch-generated components for WCAG 2.1 AA accessibility issues and applies fixes — semantic HTML, ARIA attributes, keyboard navigation, focus management, and screen reader support.
majiayu000/claude-skill-registry 163
-
k8s-quality-checklist
Review Kubernetes operators for safety, CRD quality, webhook correctness, RBAC scope, controller behavior, and local dev-loop readiness. Use when Codex is auditing an operator implementation or deciding whether a change is ready for testing or release.
majiayu000/claude-skill-registry 163
-
monitoring-alerting
Grafana alerts, Loki LogQL advanced queries, SLO dashboards, Telegram contact points, alerting rules for Laravel/Nginx/MySQL/Next.js
majiayu000/claude-skill-registry 163
-
documentation-creation
Create comprehensive project documentation from scratch. Use when setting up INITIAL documentation for a new project or building a complete documentation suite. NOT for updating existing docs (use documentation-sync instead). Covers project analysis, documentation structure, templates, and verification.
majiayu000/claude-skill-registry 163
-
root-cause-analysis
Problem solving using Fishbone (Ishikawa) diagrams and 5 Whys technique. Identifies root causes systematically and recommends corrective actions.
majiayu000/claude-skill-registry 163
-
unsafe-review
Comprehensive review of unsafe code — audits safety invariants, demands benchmark+ASM proof of performance benefit, and verifies Miri/Kani/fuzz/property test coverage for every unsafe block
majiayu000/claude-skill-registry 163
-
create-doc
Use when the user wants to save knowledge as a file so others don't have to rediscover it — "turn this into a doc", "write this up", "document how X works", "we figured this out and want to capture it", "nobody should have to figure this out again". Covers any request to create or update durable written artifacts: onboarding guides, runbooks, ADRs, API docs, architecture notes, postmortems, changelogs, setup guides. The trigger: user wants knowledge captured in a file for future reference, not just a conversation. Do NOT use when still making decisions (→ give-plan), just asking for explanation without a file (→ ask), or writing code (→ cook).
majiayu000/claude-skill-registry 163
-
add-event-type
Add a new event type to the frontend feed system with corresponding React component. Use when user mentions "new event", "add event type", "event block", "new block type", or wants to display new agent output types.
majiayu000/claude-skill-registry 163