Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
code-refactoring-context-restore
Use when working with code refactoring context restore
majiayu000/claude-skill-registry 163
-
disciplined-design
Phase 2 of disciplined development. Creates implementation plans based on
approved research. Specifies file changes, function signatures, test strategy,
and step sequence. Requires human approval before implementation.
majiayu000/claude-skill-registry 163
-
high-growth-goal-alignment
A framework for creating radical clarity and focus during rapid scaling. Use this when teams are overwhelmed by complex spreadsheets, when priorities frequently clash, or when accountability is diffused across multiple owners.
majiayu000/claude-skill-registry 163
-
backtest-analyzer-agent
Backtest results interpreter and strategy evaluator. Analyzes historical backtest performance, identifies strengths/weaknesses, and provides actionable recommendations for strategy improvement.
majiayu000/claude-skill-registry 163
-
hypothesis_generation
Bilimsel hipotez oluşturma, deney tasarımı ve test metodolojisi rehberi.
majiayu000/claude-skill-registry 163
-
using-llm-specialist
LLM specialist router to prompt engineering, fine-tuning, RAG, evaluation, and safety skills.
majiayu000/claude-skill-registry 163
-
leann-search
Semantic search across codebase using LEANN vector index
majiayu000/claude-skill-registry 163
-
accessing-google-workspace
gcloud CLI経由でGoogle SheetsとDocsにアクセスする。 Google Sheets/DocsのURLを共有した時、または スプレッドシート, Sheets, Docs, Google ドキュメント に言及した時に使用。
majiayu000/claude-skill-registry 163
-
rad
Response-Aware Development (RAD) - Systematic verification of code assumptions using multi-model AI analysis. Auto-activates on keywords assumption, verify assumptions, list assumptions, RAD, response-aware, assumption tags, critical assumptions, assumption verification. Routes to verification, listing, and testing workflows.
majiayu000/claude-skill-registry 163
-
task-dispatch
Subagent-driven task execution with TDD workflow. Dispatches tester subagent (writes failing tests) then implementer subagent (makes tests pass), with batch review.
majiayu000/claude-skill-registry 163
-
java-optimize-quarkus-native
Systematic Quarkus native image optimization with reflection registration and performance improvements
majiayu000/claude-skill-registry 163
-
phase-plan-generate
Generate comprehensive plan documentation following Template 1 format. Use when creating plan.md files for new components or subsections.
majiayu000/claude-skill-registry 163
-
refactor-elegant-teaching
Refactor code to be cleaner, more modular, and self-documenting when making code more teachable and maintainable. Not for quick fixes, non-educational changes, or style-only changes.
majiayu000/claude-skill-registry 163
-
godot-extract-resources
Use when Godot code has hardcoded game data in const arrays, dictionaries, or embedded values. Detects inline data like enemy stats, item definitions, level configurations. Automatically extracts to .tres resource files, making data visible in editor, easily modifiable, and supports data-driven design.
majiayu000/claude-skill-registry 163
-
bio-read-qc-quality-reports
Generate and interpret quality reports from FASTQ files using FastQC and MultiQC. Assess per-base quality, adapter content, GC bias, duplication levels, and overrepresented sequences. Use when performing initial QC on raw sequencing data or validating preprocessing results.
majiayu000/claude-skill-registry 163
-
FastAPI Kubernetes Deployment
This skill should be used when the user asks to "deploy FastAPI to Kubernetes", "create Dockerfile", "build Docker image", "write Helm chart", "configure K8s deployment", "add health checks", "scale FastAPI", or mentions Docker, Kubernetes, K8s, containers, Helm, or deployment. Provides containerization and orchestration patterns.
majiayu000/claude-skill-registry 163
-
blogwatcher
Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
majiayu000/claude-skill-registry 163
-
skill-name
[REQUIRED] Comprehensive description of what this skill does and when to use it. Include: (1) Primary functionality, (2) Specific use cases, (3) Security operations context. Must include specific "Use when:" clause for skill discovery. Example: "SAST vulnerability analysis and remediation guidance using Semgrep and industry security standards. Use when: (1) Analyzing static code for security vulnerabilities, (2) Prioritizing security findings by severity, (3) Providing secure coding remediation, (4) Integrating security checks into CI/CD pipelines." Maximum 1024 characters.
majiayu000/claude-skill-registry 163
-
project-aeo-monitoring-tools
Build custom AI search monitoring tools for competitive AEO analysis. Covers API access, scraping architecture, legal compliance, and cost estimation.
majiayu000/claude-skill-registry 163
-
audit-performance
Run a single-session performance audit on the codebase
majiayu000/claude-skill-registry 163
-
pr-comment-limit-enforcement
Use when posting PR comments. Enforces 50-comment limit to prevent infinite review cycles.
majiayu000/claude-skill-registry 163
-
openai-image-gen
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
majiayu000/claude-skill-registry 163
-
sync-core-vuralserhat86-antigravity-agentic-
majiayu000/claude-skill-registry 163
-
web-shells
majiayu000/claude-skill-registry 163