Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
commit-guidelines
Provides commit message formatting standards for this project. Claude should use this skill when creating git commits to ensure messages follow project conventions, including proper co-authorship attribution and concise formatting.
majiayu000/claude-skill-registry 163
-
design-prompt-generator-v2
Advanced 7-step hierarchical design prompt generator for AI web development tools (Lovable, Cursor, Bolt). Generates domain-aware, user-journey-based design prompts with emotional design considerations. Triggers on "디자인 프롬프트", "웹 디자인", "Lovable 프롬프트", "랜딩페이지 만들어줘", or any AI web builder prompt requests.
majiayu000/claude-skill-registry 163
-
deliberate
Adversarial deliberation process for making decisions. Spawns advocate agents for each option who argue their cases before a judge (you) who renders a verdict.
majiayu000/claude-skill-registry 163
-
debugging-patterns
Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scoring.
majiayu000/claude-skill-registry 163
-
kiss-dry-yagni
KISS, DRY, YAGNI principles for simple, maintainable code
majiayu000/claude-skill-registry 163
-
doc-hygiene
Documentation hygiene — anti-drift rules, count elimination, and living document maintenance
majiayu000/claude-skill-registry 163
-
testing-strategies
Systematic testing for confidence without over-testing — the right test at the right level
majiayu000/claude-skill-registry 163
-
fix-auto
Auto-fix bugs. Observe symptom, find root cause, apply minimal fix, verify, explain in human terms.
majiayu000/claude-skill-registry 163
-
progressive-estimation
Estimate AI-assisted and hybrid human+agent development work with research-backed PERT statistics and calibration feedback loops
majiayu000/claude-skill-registry 163
-
performing-tls-analysis
majiayu000/claude-skill-registry 163
-
forge-textures-and-samplers
Load images, create GPU textures and samplers, draw textured geometry with index buffers. Use when someone needs to map an image onto geometry, set up texture filtering, or use index buffers in SDL3 GPU.
majiayu000/claude-skill-registry 163
-
okr-framework
Define and achieve ambitious goals using Objectives and Key Results methodology. Use for: goal setting, strategic alignment, measuring progress, quarterly planning, team objectives, company-wide alignment, tracking key results, and performance management.
majiayu000/claude-skill-registry 163
-
device-prober
Probe and test SDR hardware capabilities (RTL-SDR, SDRplay, HackRF, etc.). Use when verifying device detection, discovering supported sample rates and gains, testing antenna ports, or troubleshooting SDR hardware issues.
majiayu000/claude-skill-registry 163
-
etsy-product-description
Product description writing — keyword integration, benefit-focused copy, FAQ, formatting
majiayu000/claude-skill-registry 163
-
sif-to-csv
Convert a SIF (Standard Interchange Format) file to a clean, readable CSV or Google Sheet.
majiayu000/claude-skill-registry 163
-
tiktok-product-strategy
Analyze and select winning products for TikTok Shop affiliate Vietnam. Use when evaluating products with WIN scoring (100-point), competitor analysis, pain point research, hashtag strategy, content angle planning, and go/no-go decisions. Also use when deciding to stop or continue a product based on performance data.
majiayu000/claude-skill-registry 163
-
evaluation
Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.
majiayu000/claude-skill-registry 163
-
bmad-wds-create-design-system
Build a new design system or add components from specifications
majiayu000/claude-skill-registry 163
-
Git Commit Helper
Generate descriptive commit messages by analyzing git diffs. Use when the user asks for help writing commit messages or reviewing staged changes.
majiayu000/claude-skill-registry 163
-
evaluating-candidates
Help users make better hiring decisions. Use when someone is evaluating job candidates, making hiring decisions, conducting reference checks, reviewing work samples or take-homes, calibrating their hiring bar, or deciding between finalists.
majiayu000/claude-skill-registry 163
-
llm-streaming-response-handler
Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI/Anthropic/Claude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on "LLM streaming", "SSE", "token stream", "chat UI", "real-time AI". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.
majiayu000/claude-skill-registry 163
-
ping
Test connectivity with AI provider (gemini/codex/opencode/droid/claude).
majiayu000/claude-skill-registry 163
-
124-java-secure-coding
Use when you need to apply Java secure coding best practices — including validating untrusted inputs, defending against injection attacks with parameterized queries, minimizing attack surface via least privilege, applying strong cryptographic algorithms, handling exceptions securely without exposing sensitive data, managing secrets at runtime, avoiding unsafe deserialization, and encoding output to prevent XSS. Part of the skills-for-java project
majiayu000/claude-skill-registry 163
-
sfx-catalog
Sound effects management for Horus's filmmaking pipeline. Catalogs audio files with acoustic analysis, provides semantic search via memory integration, tracks usage patterns, and generates missing SFX. Makes sound effects discoverable, reusable, and learnable through the Memory First pattern.
majiayu000/claude-skill-registry 163