Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
composable-svelte-maps
Interactive maps and geospatial visualizations for Composable Svelte. Use when implementing maps, geolocation, markers, overlays, or geospatial data visualization. Covers Map component, markers, popups, GeoJSON layers, heatmaps, tile providers, viewport controls from @composable-svelte/maps package built with Maplibre GL.
majiayu000/claude-skill-registry 163
-
Docx
Word document processing. USE WHEN docx, Word document. SkillSearch('docx') for docs.
majiayu000/claude-skill-registry 163
-
configuring
Universal environment variable loader for AI agent environments. Loads secrets and config from Claude.ai, Claude Code, OpenAI Codex, Jules, and standard .env files.
majiayu000/claude-skill-registry 163
-
lyra
Transform vague inputs into precision-optimized AI prompts for Claude, ChatGPT, Gemini, or other LLMs. Use when user mentions "optimize prompt", "improve prompt", "lyra", "prompt engineering", or needs help crafting effective AI prompts.
majiayu000/claude-skill-registry 163
-
granola-common-errors
Troubleshoot common Granola errors and issues.
Use when experiencing recording problems, sync issues,
transcription errors, or integration failures.
Trigger with phrases like "granola error", "granola not working",
"granola problem", "fix granola", "granola troubleshoot".
majiayu000/claude-skill-registry 163
-
kubecon-llm-k8s
Slidev presentation about taming dependency chaos for LLM in Kubernetes.
majiayu000/claude-skill-registry 163
-
git-stats
分析Git仓库统计信息，包括提交、贡献者和代码变更。
majiayu000/claude-skill-registry 163
-
quality-detect-orphaned-code
Detects orphaned code (files/functions that exist but are never imported or called in production),
preventing "created but not integrated" failures. Use before marking features complete, before moving
ADRs to completed, during code reviews, or as part of quality gates. Triggers on "detect orphaned code",
"find dead code", "check for unused modules", "verify integration", or proactively before completion.
Works with Python modules, functions, classes, and LangGraph nodes. Catches the ADR-013 failure pattern
where code exists and tests pass but is never integrated.
majiayu000/claude-skill-registry 163
-
manage-plan-documents
Manage request documents within plan directories with schema validation and template-based creation
majiayu000/claude-skill-registry 163
-
computer-scientist-analyst
Analyzes events through computer science lens using computational complexity, algorithms, data structures,
systems architecture, information theory, and software engineering principles to evaluate feasibility, scalability, security.
Provides insights on algorithmic efficiency, system design, computational limits, data management, and technical trade-offs.
Use when: Technology evaluation, system architecture, algorithm design, scalability analysis, security assessment.
Evaluates: Computational complexity, algorithmic efficiency, system architecture, scalability, data integrity, security.
majiayu000/claude-skill-registry 163
-
form-components-vassovass-scl-v3-5857ca21
majiayu000/claude-skill-registry 163
-
final-qa-launcher
Start dev server, generate QA checklist, guide manual verification. Use before creating PR.
majiayu000/claude-skill-registry 163
-
kaizen
Guide for continuous improvement, error proofing, and standardization. Use this skill when the user wants to improve code quality, refactor, or discuss process improvements.
majiayu000/claude-skill-registry 163
-
agentuity-cli-cloud-db-create
Create a new database resource. Requires authentication. Use for Agentuity cloud platform operations
majiayu000/claude-skill-registry 163
-
dcode:find-component
Find UI components from screenshots, route paths, or component names. Use when a designer asks "where does this live?", shares a screenshot and wants to find the code, needs to locate a component by its visual appearance, or wants to understand how a UI element is built. Works with React, Vue, Angular, and other component-based frameworks.
majiayu000/claude-skill-registry 163
-
fluentd-config-generator
Generate fluentd config generator operations. Auto-activating skill for DevOps Advanced.
Triggers on: fluentd config generator, fluentd config generator
Part of the DevOps Advanced skill category. Use when configuring systems or services. Trigger with phrases like "fluentd config generator", "fluentd generator", "fluentd".
majiayu000/claude-skill-registry 163
-
capacitor-deep-linking
Complete guide to implementing deep links and universal links in Capacitor apps. Covers iOS Universal Links, Android App Links, custom URL schemes, and navigation handling. Use this skill when users need to open their app from links.
majiayu000/claude-skill-registry 163
-
arcanea-skill-mastery
The meta-skill of using skills effectively. Learn when to invoke which skill, how to chain them together, and how to develop your own. Master the Arcanea skill system itself.
majiayu000/claude-skill-registry 163
-
document-in-case
Add a comment to a case to document findings, actions, or recommendations. Use to maintain audit trail during investigations. Requires CASE_ID and comment text.
majiayu000/claude-skill-registry 163
-
compare-keywords
Compare keyword sets between resume and job description. Returns match statistics including score, missing keywords, and intersection.
majiayu000/claude-skill-registry 163
-
Rails Context Verification
Systematic verification of codebase context before code generation to prevent assumption bugs
majiayu000/claude-skill-registry 163
-
unity-headless
Install Unity Hub/Editor, activate licenses, run headless builds and tests
majiayu000/claude-skill-registry 163
-
sfdipot-product-factors
James Bach's HTSM Product Factors (SFDIPOT) analysis for comprehensive test strategy generation. Use when analyzing requirements, epics, or user stories to generate prioritized test ideas across Structure, Function, Data, Interfaces, Platform, Operations, and Time dimensions.
majiayu000/claude-skill-registry 163
-
workflow-analyze
Analyze issue and generate analysis.md with solution approaches. Use when starting a new task or feature to thoroughly analyze the problem and compare solution options.
majiayu000/claude-skill-registry 163