Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
bmad-wds-evolution
Add features to existing products through targeted changes
majiayu000/claude-skill-registry 163
-
speckit-taskstoissues
Convert tasks from tasks.md into GitHub issues. Use after task breakdown to track work items in GitHub project management.
majiayu000/claude-skill-registry 163
-
execute-plan
Execute implementation plan step-by-step - creates todos from plan, guides through tasks sequentially, runs until issue resolved.
TRIGGER when: user wants to execute the plan after /start-issue (e.g., "execute the plan", "execute plan for #23", "implement issue #23", "work on the plan").
DO NOT TRIGGER when: user just wants to plan (use /start-issue), review code (use /review), or finish work (use /finish-issue).
majiayu000/claude-skill-registry 163
-
script-agents
majiayu000/claude-skill-registry 163
-
video-render
Render videos using Remotion React-based video framework
majiayu000/claude-skill-registry 163
-
writing-plans
writing-plans
majiayu000/claude-skill-registry 163
-
comprehensive-review-pr-enhance
You are a PR optimization expert specializing in creating high-quality pull requests that facilitate efficient code reviews. Generate comprehensive PR descriptions, automate review processes, and ensure PRs follow best practices for clarity, size, and reviewability.
majiayu000/claude-skill-registry 163
-
revenuecat
RevenueCat metrics, customer data, and documentation search. Use when querying subscription analytics, MRR, churn, customers, or RevenueCat docs.
majiayu000/claude-skill-registry 163
-
image-analysis
Reference for auction item image analysis — what to look for in photos of auction items, how to extract catalog-relevant information from images, and how the extension's AI image analysis works.
majiayu000/claude-skill-registry 163
-
lp-do-critique
Hardnosed critic for lp-do-fact-find, lp-do-analysis, lp-do-plan, lp-offer, and process/skill documents. Surfaces weak claims, missing evidence, hidden assumptions, feasibility gaps, and unaddressed risks with no glazing.
majiayu000/claude-skill-registry 163
-
learn
Extract reusable knowledge from the current session into a persistent skill.
Use when you discover something non-obvious, create a workaround, or develop
a multi-step workflow that future sessions would benefit from.
majiayu000/claude-skill-registry 163
-
bc-security
Implement BigCommerce security — OAuth token management, API authentication, webhook verification, CSP, input validation, PCI compliance, and app security best practices. Use when hardening integrations or reviewing security posture.
majiayu000/claude-skill-registry 163
-
zip-unzip-file-compression-100mb
Use AgentPMT external API to run the Zip / Unzip - File Compression < 100MB tool with wallet signatures, credits purchase, or credits earned from jobs.
majiayu000/claude-skill-registry 163
-
logging-best-practices
Logging best practices focused on wide events (canonical log lines) for powerful debugging and analytics
majiayu000/claude-skill-registry 163
-
edictum-ee
Implement features in the Edictum Enterprise layer (ee/). Use when the task touches PII detection backends, enterprise audit sinks, server, auth, sequences, or NL authoring. ee/ imports from core freely.
majiayu000/claude-skill-registry 163
-
df:audit-milestone
Audit milestone completion against original intent before archiving.
Expensive operation that checks requirements coverage and cross-objective integration.
majiayu000/claude-skill-registry 163
-
crawl4ai
This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction patterns with schema generation for efficient, LLM-free extraction.
majiayu000/claude-skill-registry 163
-
Cross-Site Scripting and HTML Injection Testing
This skill should be used when the user asks to "test for XSS vulnerabilities", "perform cross-site scripting attacks", "identify HTML injection flaws", "exploit client-side injection vulnerabilities", "steal cookies via XSS", or "bypass content security policies". It provides comprehensive techniques for detecting, exploiting, and understanding XSS and HTML injection attack vectors in web applications.
majiayu000/claude-skill-registry 163
-
guidelines-advisor
Comprehensive smart contract development advisor based on Trail of Bits' best practices. Analyzes codebase to generate documentation/specifications, review architecture, check upgradeability patterns, assess implementation quality, identify pitfalls, review dependencies, and evaluate testing. Provides actionable recommendations. (project, gitignored)
majiayu000/claude-skill-registry 163
-
pydantic-models-py
Create Pydantic models following the multi-model pattern with Base, Create, Update, Response, and InDB variants. Use when defining API request/response schemas, database models, or data validation in Python applications using Pydantic v2.
majiayu000/claude-skill-registry 163
-
classify-lesson-types
Interview the user to classify each SLT by lesson type and build up lesson type heuristics.
majiayu000/claude-skill-registry 163
-
test-generator
Generate unit and integration tests for API routes, utilities, React components, and hooks. Use when asked to generate tests, write unit tests, create integration tests, add test coverage, or test a component/route/function.
majiayu000/claude-skill-registry 163
-
land-and-deploy
Land and deploy workflow. Merges the PR, waits for CI and deploy,
verifies production health via canary checks. Takes over after /ship
creates the PR. Use when: "merge", "land", "deploy", "merge and verify",
"land it", "ship it to production".
majiayu000/claude-skill-registry 163
-
anthropic_administrator-automation
Automate Anthropic Admin tasks via Rube MCP (Composio): API keys, usage, workspaces, and organization management. Always search tools first for current schemas.
majiayu000/claude-skill-registry 163