Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
design-guards
Investigate a bug pattern audit report and design architectural guards (tests, contracts, structural changes) that provide immunity to each identified pattern. Use when user says "design guards", "design defenses", or wants architectural solutions for bug patterns.
majiayu000/claude-skill-registry 163
-
google-adk-python
Build AI agents with Google ADK Python (Agent Development Kit). Use for multi-agent systems, workflow agents (sequential/parallel/loop), Vertex AI deployment, tool integration, human-in-the-loop.
majiayu000/claude-skill-registry 163
-
create-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
majiayu000/claude-skill-registry 163
-
made-to-stick
Craft messages that are understood, remembered, and drive action using the SUCCESs checklist (Simple, Unexpected, Concrete, Credible, Emotional, Stories). Use when the user mentions "make it memorable", "sticky messaging", "tagline", "value proposition", "why the message isnt landing", "knowledge curse", "surprise gap", or "concrete language". Also trigger when writing pitch decks, simplifying complex product explanations, or making presentations more compelling and memorable. For narrative brand frameworks, see storybrand-messaging. For viral sharing, see contagious.
majiayu000/claude-skill-registry 163
-
market-mapping
Search for companies in a target market, find key buyers at each, and produce a segmented market map with the option to create a lead list.
majiayu000/claude-skill-registry 163
-
jira-automation
Automate Jira tasks via Rube MCP (Composio): issues, projects, sprints, boards, comments, users. Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
mobile-first-design
Design for mobile devices first, then scale up to larger screens. Create responsive interfaces that work seamlessly across all device sizes.
majiayu000/claude-skill-registry 163
-
review-and-promote-traces
Judge flagged trace outputs and promote judged items back to datasets. Use when an evaluation run requires human judgment or when review queue items need to be judged for promotion into the dataset.
majiayu000/claude-skill-registry 163
-
complexity
Analyze code complexity and find refactor targets using radon/gocyclo. Triggers: "complexity", "analyze complexity", "find complex code", "refactor targets", "cyclomatic complexity", "code metrics".
majiayu000/claude-skill-registry 163
-
hourly-monitor
Check Hive test progress, update documentation, and commit with standardized message.
majiayu000/claude-skill-registry 163
-
paywall-upgrade-cro
When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates. Also use when the user mentions "paywall," "upgrade screen," "upgrade modal," "upsell," "feature gate," "convert free to paid," "freemium conversion," "trial expiration screen," "limit reached screen," "plan upgrade prompt," or "in-app pricing." Distinct from public pricing pages (see page-cro) — this skill focuses on in-product upgrade moments where the user has already experienced value.
majiayu000/claude-skill-registry 163
-
pmtl-production-ready
PMTL_VN production-ready operating skill. Use for implementation, debugging, hardening, monitoring, deployment-impacting changes, or release-minded code review. This is the high-agency umbrella skill for turning PMTL work into production-safe work with explicit verification and documented recovery paths.
majiayu000/claude-skill-registry 163
-
af-configure-cognito-auth
Configure Cognito User Pools with custom attributes and auth triggers. Use when setting up authentication flows, managing user groups, or applying CDK escape hatches for GainInsight Standard projects.
majiayu000/claude-skill-registry 163
-
project-init
Skill conversationnel interactif pour initialiser un nouveau projet ou onboarder un projet existant avec les standards evan-workflow. Guide l'utilisateur a travers des questions sur le stack, les technos, les conventions, puis genere tous les fichiers de configuration Claude Code (CLAUDE.md, settings.json, .claudeignore, .gitignore, structure). Propose intelligemment les technos documentees dans evan-workflow en priorite, avec des alternatives. Si une techno non documentee est choisie, propose de la documenter automatiquement. Ce skill devrait etre utilise quand l'utilisateur veut creer un nouveau projet, initialiser Claude Code sur un projet existant, ou configurer les standards evan-workflow.
majiayu000/claude-skill-registry 163
-
remotion-best-practices
Best practices for Remotion - Video creation in React
majiayu000/claude-skill-registry 163
-
opened-identity
Understand OpenEd's identity, values, and strategic narrative. This skill guides content creation aligned with Open Education philosophy, messaging framework, and audience understanding. Essential context for all OpenEd communication and content strategy.
majiayu000/claude-skill-registry 163
-
Prompt Engineering Skill
Craft effective prompts that get the best results from language models.
majiayu000/claude-skill-registry 163
-
agent-check
Validate custom agent file format and structure
majiayu000/claude-skill-registry 163
-
bmad-agent-cis-creative-problem-solver
creative-problem-solver agent
majiayu000/claude-skill-registry 163
-
exa-automation
Automate Exa tasks via Rube MCP (Composio). Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
exa-install-auth
Install and configure Exa SDK/CLI authentication.
Use when setting up a new Exa integration, configuring API keys,
or initializing Exa in your project.
Trigger with phrases like "install exa", "setup exa",
"exa auth", "configure exa API key".
majiayu000/claude-skill-registry 163
-
cost-optimization
Optimize cloud costs through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.
majiayu000/claude-skill-registry 163
-
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
majiayu000/claude-skill-registry 163
-
goal-tracker
Track goal progress, derive state from execution, identify gaps, trigger actions. Use for goal status checks, progress reviews, and operational goal management.
majiayu000/claude-skill-registry 163