Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
frontend-excellence
Create distinctive, production-grade frontend interfaces that avoid generic AI aesthetics. Use when building web UIs, React components, landing pages, dashboards, or styling any web interface. Provides design thinking process, color palettes, typography treatments, and anti-patterns to avoid.
majiayu000/claude-skill-registry 163
-
aico-pm-acceptance-criteria
Define clear, testable acceptance criteria using Given/When/Then (Gherkin) format that can be directly used for testing.
Use this skill when:
- User asks for "acceptance criteria", "AC", "test criteria", "done criteria"
- User asks "how do we know it's done?", "what counts as complete?"
- User story needs testable success conditions
- QA needs test scenarios or test cases
- Running /pm.plan and need to add AC to stories
- Reviewing story and AC is missing or vague
Format: Always use Given [context], When [action], Then [expected result] structure.
majiayu000/claude-skill-registry 163
-
signal-state-management
Preact Signals for reactive state management, signal vs computed signal usage, batch updates for performance, action creator patterns, signal integration with React components, state management by domain (boards posts members), reactive patterns, and signal best practices for ree-board project
majiayu000/claude-skill-registry 163
-
programmatic-seo
Design and evaluate programmatic SEO strategies for creating SEO-driven pages at scale using templates and structured data. Use when the user mentions programmatic SEO, pages at scale, template pages, directory pages, location pages, comparison pages, integration pages, or keyword-pattern page generation. This skill focuses on feasibility, strategy, and page system design—not execution unless explicitly requested.
majiayu000/claude-skill-registry 163
-
mission-solo
HOUSTON executes feature tasks directly. No agents. Best for small features (1-3 tasks).
majiayu000/claude-skill-registry 163
-
comment-analyzer
Use when asked to review code comments for accuracy/quality or explicitly asked to run the comment-analyzer subagent.
majiayu000/claude-skill-registry 163
-
cloudflare-agents
Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Provides WebSockets, state persistence, scheduling, and multi-agent coordination. Prevents 23 documented errors.
Use when: building WebSocket agents, RAG with Vectorize, MCP servers, or troubleshooting "Agent class must extend", "new_sqlite_classes", binding errors, WebSocket payload limits.
majiayu000/claude-skill-registry 163
-
mcp-spec-checker
Predicate-level semantic diff for MCP protocol specs. Compares 0618 vs 1125 specs via Narya types, GF(3) evaluators, and Unison-style effects. Use for protocol verification, spec migration, or detecting breaking changes.
majiayu000/claude-skill-registry 163
-
convex-scheduling
Advanced scheduling - runtime crons, batch processing, timeouts, retry patterns
majiayu000/claude-skill-registry 163
-
fly-deploy
Quick MVP deployment to fly.io for JavaScript (Next.js, RedwoodSDK, Express), Rust (Axum, Rocket), Python (FastAPI), and generic Dockerfiles. Use when deploying applications to fly.io, setting up databases (Postgres, volumes, Tigris object storage), managing secrets, configuring custom domains, setting up GitHub Actions workflows, creating review apps for pull requests, or troubleshooting fly.io deployments. Covers complete deployment workflows from initial setup through production.
majiayu000/claude-skill-registry 163
-
tenant-credit-analyst
Expert in tenant creditworthiness assessment and financial statement analysis. Use when evaluating tenant credit quality, analyzing financial ratios, assessing default risk, or structuring security requirements. Key terms include DSCR, current ratio, debt-to-equity, working capital, liquidity analysis, credit scoring, personal guarantee, security deposit, financial covenants
majiayu000/claude-skill-registry 163
-
form-system
Enforces project form system conventions when creating or modifying forms using the custom TanStack Form integration. This skill covers useAppForm hook usage, field components, focus management, validation patterns, and accessibility requirements.
majiayu000/claude-skill-registry 163
-
documentation-production
Use when generating, updating, or organizing documentation (component/API docs, project indexes, diagrams, tutorials, learning paths) - provides structured workflows and references for docs generation, indexing, diagrams, and teaching.
majiayu000/claude-skill-registry 163
-
AgentDB Memory Patterns
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
majiayu000/claude-skill-registry 163
-
docs-generate-readme
Generate Level 1 (README.md) user documentation from design docs. Use when creating or updating package README files for npm/GitHub.
majiayu000/claude-skill-registry 163
-
present
Convert a deliverable document to an HTML presentation
majiayu000/claude-skill-registry 163
-
youtube-transcribe
This skill should be used when the user asks to "download YouTube transcript", "get YouTube captions", "extract YouTube subtitles", or needs to retrieve transcript from a YouTube video.
majiayu000/claude-skill-registry 163
-
query-dependencies
majiayu000/claude-skill-registry 163
-
junit-integration
Maven integration testing with Failsafe plugin, IT naming conventions, and profile configuration
majiayu000/claude-skill-registry 163
-
performance-analyzer
Analyze code performance, detect bottlenecks, suggest optimizations for algorithms, queries, and resource usage. Use when improving application performance or investigating slow code.
majiayu000/claude-skill-registry 163
-
troubleshooting-execute
Use when execute command encounters errors - diagnostic guide for phase failures, parallel agent failures, merge conflicts, worktree issues, and recovery strategies
majiayu000/claude-skill-registry 163
-
juggle
Task management via CLI for agent loops. Balls are tasks with acceptance criteria; sessions group related balls. Use when working on a project with a .juggle/ directory, when user mentions juggle/balls/sessions, when planning tasks before agent loops, or when updating task state and logging progress during execution.
majiayu000/claude-skill-registry 163
-
novel-evaluator
Rigorously and meticulously evaluate and score story text, analyzing quality from market potential, innovation attributes, and content highlights dimensions. Suitable for novel initial screening, multi-dimensional evaluation scoring
majiayu000/claude-skill-registry 163
-
open-construction-estimate
Access and utilize open construction pricing databases. Match BIM elements to standardized work items, calculate costs using public unit price databases with 55,000+ work items.
majiayu000/claude-skill-registry 163