Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
learn
Research a topic and grow your knowledge graph. Uses Exa deep researcher, web search, or basic search to investigate topics, files results with full provenance, and chains to processing pipeline. Triggers on "/learn", "/learn [topic]", "research this", "find out about".
majiayu000/claude-skill-registry 163
-
token-plan
Port of .claude/commands/token-plan.md for Codex.
majiayu000/claude-skill-registry 163
-
terraform-best-practices
Terraform infrastructure-as-code best practices for scalable and maintainable cloud infrastructure. Use when writing Terraform modules, managing infrastructure state, or implementing infrastructure automation at scale.
majiayu000/claude-skill-registry 163
-
readme
Generate self-contained README files that enable instant developer onboarding.
Use when creating or updating directory documentation.
Triggers: "create readme", "readme", "document directory", "write readme".
majiayu000/claude-skill-registry 163
-
erk-exec
Guide for erk exec subcommands. Use when running erk exec commands to understand syntax, find the right command for a task, or learn common workflows. Always check syntax with -h or load this skill before running erk exec commands.
majiayu000/claude-skill-registry 163
-
cloudflare-zero-trust
Protect internal apps with Cloudflare Access, device posture, and Zero Trust policies.
majiayu000/claude-skill-registry 163
-
ce-adr-gap-analyzer
Analyze ADR compliance by interpreting the ADR's intent, verifying that implementation and RTD satisfy every decision, and producing a dated gap report with only unresolved items.
majiayu000/claude-skill-registry 163
-
verify
Use before claiming work is done, fixed, or passing — requires running verification commands and confirming output before any success claim. Prevents false completion claims, unverified assertions, and "should work" statements.
majiayu000/claude-skill-registry 163
-
twilio-admin
Admin: sub-account lifecycle, usage monitoring, number management, compliance SHAKEN/STIR TCR, audit logs
majiayu000/claude-skill-registry 163
-
vercel-harden
Harden a Vercel deployment with security headers, CSP, bot protection, and deployment configuration
majiayu000/claude-skill-registry 163
-
project-retrospective
Generate LESSONS.md retrospective files that capture institutional knowledge, especially failures. Use when closing out journalism projects, investigations, events, or publications. Includes templates for research projects, event post-mortems, editorial tools, and publications.
majiayu000/claude-skill-registry 163
-
moai-lang-rust
Rust 1.92+ development specialist covering Axum, Tokio, SQLx, and memory-safe systems programming. Use when building high-performance, memory-safe applications or WebAssembly.
majiayu000/claude-skill-registry 163
-
vibe-handover-doc
Generates a session continuity document at the end of a long session or when switching context on a multi-session project. Enables seamless resumption.
majiayu000/claude-skill-registry 163
-
implement-task
Implement a single task using TDD (tests first, then minimal code).
majiayu000/claude-skill-registry 163
-
symptom-checker-triage
Suggest triage levels (Emergency, Urgent, Outpatient) based on red flag symptoms using a rule-based engine. For AI-assisted decision support only — not a substitute for professional medical diagnosis.
majiayu000/claude-skill-registry 163
-
Offline Sync Strategies
Advanced conflict resolution and data consistency patterns for offline-first architecture
majiayu000/claude-skill-registry 163
-
planning-with-files
将工作流转换为使用 Manus 风格的持久化 markdown 文件进行规划、进度跟踪和知识存储。适用于开始复杂任务、多步骤项目、研究任务，或者当用户提到规划、组织工作、跟踪进度或需要结构化输出时使用。
majiayu000/claude-skill-registry 163
-
freeze
Restrict file edits to a specific directory for the session. Blocks Edit and
Write outside the allowed path. Use when debugging to prevent accidentally
"fixing" unrelated code, or when you want to scope changes to one module.
Use when asked to "freeze", "restrict edits", "only edit this folder",
or "lock down edits".
majiayu000/claude-skill-registry 163
-
anti-reversing-techniques
Understand anti-reversing, obfuscation, and protection techniques encountered during software analysis. Use when analyzing protected binaries, bypassing anti-debugging for authorized analysis, or understanding software protection mechanisms.
majiayu000/claude-skill-registry 163
-
expo-deployment
Deploying Expo apps to iOS App Store, Android Play Store, web hosting, and API routes
majiayu000/claude-skill-registry 163
-
agent-backend-patterns
Backend architecture patterns and best practices for scalable server-side applications.
majiayu000/claude-skill-registry 163
-
input-validation
Use when implementing input validation and output encoding to prevent injection attacks. Covers validation strategies, context-specific output encoding, parameterized queries, and defense-in-depth approaches across all languages and frameworks.
USE FOR: input validation, output encoding, XSS prevention, SQL injection prevention, command injection prevention, parameterized queries, sanitization, allowlisting, content security policy
DO NOT USE FOR: authentication validation (use authentication), API rate limiting (use api-security), cryptographic validation (use cryptography)
majiayu000/claude-skill-registry 163
-
claude-d3js-skill
This skill provides guidance for creating sophisticated, interactive data visualisations using d3.js.
majiayu000/claude-skill-registry 163
-
land-adopt-expand-blueprint
Template for orchestrating phased motions across strategic SaaS accounts.
majiayu000/claude-skill-registry 163