Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
naming-improve
Improve variable and function naming with semantic analysis
majiayu000/claude-skill-registry 163
-
self-test-skill-invocation
Use when user asks to "test skill invocation framework" or mentions "canary skill test". This is a self-test skill to verify the test framework correctly loads and invokes skills.
majiayu000/claude-skill-registry 163
-
pre-flight-check
Checks essential information and project status before starting a task.
majiayu000/claude-skill-registry 163
-
sv-issue-tracking
Use sv task to manage work items and keep .tasks/ in sync with code changes.
majiayu000/claude-skill-registry 163
-
typescript-engineering
Comprehensive TypeScript engineering guidelines based on Google's TypeScript Style Guide. This skill should be used when writing TypeScript code, performing TypeScript code reviews, or answering questions about TypeScript best practices. Applies to .ts and .tsx files, and TypeScript configuration.
majiayu000/claude-skill-registry 163
-
warehouse-guide
Reference for the warehouse/inventory tracking system. Use when working with stock management, warehouse status, inventory consumption, or understanding how sales affect stock levels.
majiayu000/claude-skill-registry 163
-
ux-accessibility-patterns
Focus management, keyboard navigation, ARIA attributes, and screen reader considerations for TMNL
majiayu000/claude-skill-registry 163
-
youtube-video-editor
Edit YouTube videos using Ed Lawrence's retention-focused editing system with tournament-style thumbnail selection. Use when the user needs editing guidance, thumbnail creation, visual metaphor implementation, or production quality advice. Optimizes for viewer satisfaction through strategic cuts, pacing, and visual elements.
majiayu000/claude-skill-registry 163
-
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
majiayu000/claude-skill-registry 163
-
incident-response
Respond to production incidents systematically with triage, investigation, resolution, and post-mortem analysis to minimize downtime and prevent recurrence. Use when handling production outages, triaging incidents, investigating critical bugs, coordinating incident response, implementing hotfixes, conducting post-mortems, or establishing incident response procedures.
majiayu000/claude-skill-registry 163
-
implement-event-sourcing
Step-by-step guide for implementing event sourcing with event store, aggregate replay, snapshots, projections, and schema evolution.
majiayu000/claude-skill-registry 163
-
slo-implementation
Define and implement Service Level Indicators (SLIs) and Service Level Objectives (SLOs) with error budgets and alerting. Use when establishing reliability targets, implementing SRE practices, or measuring service performance.
majiayu000/claude-skill-registry 163
-
binary-reconnaissance
Initial reconnaissance on binaries including checksec, file analysis, strings, and symbols. First step for any new target.
majiayu000/claude-skill-registry 163
-
accessing-github-repos
GitHub repository access in containerized environments using REST API and credential detection. Use when git clone fails, or when accessing private repos/writing files via API.
majiayu000/claude-skill-registry 163
-
nodejs-package-json
Patch a Node.js project's package.json for standard build automation. Use when asked to add/standardize package.json scripts like prebuild/postbuild for TypeScript builds (rimraf dist + tsc-alias), adjust prebuild for Next.js (rimraf dist .next), or ensure an existing package.json pkg config includes required scripts/assets/targets/outputPath.
majiayu000/claude-skill-registry 163
-
when-chaining-agent-pipelines-use-stream-chain
Chain agent outputs as inputs in sequential or parallel pipelines for data flow orchestration
majiayu000/claude-skill-registry 163
-
nielsen-match-real-world
Asegura que el sistema use lenguaje y conceptos familiares para los usuarios. Use cuando escriba copy, diseñe iconografía, o estructure información para que coincida con modelos mentales del usuario.
majiayu000/claude-skill-registry 163
-
linear-issues-read
List and get Linear issues via CLI (read-only operations)
majiayu000/claude-skill-registry 163
-
retention-engagement
Help users improve retention and engagement metrics. Use when someone is dealing with churn, optimizing activation flows, building habit-forming products, or trying to increase user engagement and lifetime value.
majiayu000/claude-skill-registry 163
-
astro-forms
Form infrastructure for Astro. Zod validation, email, rate limiting, Turnstile, GDPR, Sheets. FAIL = no conversion.
majiayu000/claude-skill-registry 163
-
flow-nexus-neural
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus
majiayu000/claude-skill-registry 163
-
firebase
Firebase gives you a complete backend in minutes - auth, database, storage, functions, hosting. But the ease of setup hides real complexity. Security rules are your last line of defense, and they're often wrong. Firestore queries are limited, and you learn this after you've designed your data model. This skill covers Firebase Authentication, Firestore, Realtime Database, Cloud Functions, Cloud Storage, and Firebase Hosting. Key insight: Firebase is optimized for read-heavy, denormalized data. I
majiayu000/claude-skill-registry 163
-
build-standards
Build quality standards, validation checkpoints, and compilation requirements
majiayu000/claude-skill-registry 163
-
context-diet
Optimize Claude Code context window usage. Identify what to keep in context vs fetch on-demand. Use when context is bloated, responses are slow, hitting token limits, or want to slim down context.
majiayu000/claude-skill-registry 163