Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
setup
Run initial MatClaw setup. Use when user wants to install dependencies, authenticate messaging channels, register their main channel, or start the background services. Triggers on "setup", "install", "configure matclaw", or first-time setup requests.
majiayu000/claude-skill-registry 163
-
deep-analysis
Deep exploration and synthesis workflow using Agent Teams with dynamic planning and hub-and-spoke coordination. Use when asked for "deep analysis", "deep understanding", "analyze codebase", "explore and analyze", or "investigate codebase".
majiayu000/claude-skill-registry 163
-
aget-create-project
Create research projects with context-aware scaffolding. Reads AGET identity, searches prior work, pre-populates Due Diligence. Use when starting any formal AGET project.
majiayu000/claude-skill-registry 163
-
algorithmic-art-jp
Japanese algorithmic and generative art skill covering traditional pattern generation (wagara), calligraphy simulation, zen garden generators, and mathematical patterns from Japanese art. Triggers on requests for 和柄生成, ジェネラティブアート, アルゴリズミックアート, 伝統紋様パターン, Japanese generative art.
majiayu000/claude-skill-registry 163
-
brand-asset-management
Brand hierarchy, visual identity, asset deployment, platform-specific branding guidelines
majiayu000/claude-skill-registry 163
-
ai-pr
Use when creating pull requests: governed PR workflow with commit pipeline, pre-push gates, auto-generated summary, and auto-complete squash merge.
majiayu000/claude-skill-registry 163
-
seo-review
SEO review workflow — technical SEO audit, meta tags, structured data validation, Core Web Vitals, crawlability, indexability, AI search readiness. Applies SEO Engineer role. Use standalone or as part of feature/docs workflows.
majiayu000/claude-skill-registry 163
-
data-quality-frameworks
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
majiayu000/claude-skill-registry 163
-
qlora
Memory-efficient fine-tuning with 4-bit quantization and LoRA adapters. Use when fine-tuning large models (7B+) on consumer GPUs, when VRAM is limited, or when standard LoRA still exceeds memory. Builds on the lora skill.
majiayu000/claude-skill-registry 163
-
campaign-review
Post-mortem on recent campaign
majiayu000/claude-skill-registry 163
-
programmatic-seo
When the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pages," "[keyword] + [city] pages," "comparison pages," "integration pages," or "building many pages for SEO." For auditing existing SEO issues, see seo-audit.
majiayu000/claude-skill-registry 163
-
social-media-automation
Multi-platform social media automation patterns for Facebook, Instagram, and Twitter (X) with MCP server templates, API integration examples, platform-specific constraints, and coordinated posting workflows. Includes draft generation with character limits, image requirements, rate limit handling, and human approval gates. Use when: (1) building multi-platform social media automation, (2) implementing Facebook/Instagram/Twitter API integrations, (3) creating coordinated cross-platform posting, (4) handling platform-specific constraints (character limits, media requirements), (5) extending Gold tier with Phase 2B social media features.
majiayu000/claude-skill-registry 163
-
bmad-cis-problem-solving
Apply systematic problem-solving methodologies to complex challenges. Use when the user says "guide me through structured problem solving" or "I want to crack this challenge with guided problem solving techniques"
majiayu000/claude-skill-registry 163
-
moai-cc-skills
Claude Code Skills management, skill creation patterns, and knowledge capsule architecture. Use when creating custom Skills, managing skill libraries, or designing knowledge systems.
majiayu000/claude-skill-registry 163
-
version-updates
Bump versions, update changelogs, and coordinate version changes across files for releases
majiayu000/claude-skill-registry 163
-
veto-mechanism
封驳机制，门下审议草案时触发审查、中书收到封驳时触发修订的双向制衡流程
majiayu000/claude-skill-registry 163
-
n8n-mcp-tools-expert
Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.
majiayu000/claude-skill-registry 163
-
design-systems
Help users build and scale design systems. Use when someone is creating a component library, establishing design tokens, scaling brand consistency, or deciding when to invest in a design system.
majiayu000/claude-skill-registry 163
-
farm-inspect
Run full code inspection with all audit agents in parallel. Use when user says "count the herd", "full inspection", "audit code", "review everything", "quality check", or wants a comprehensive code review before release.
majiayu000/claude-skill-registry 163
-
gsd:verify-work
Verify completed work against requirements
majiayu000/claude-skill-registry 163
-
release-notes
Generate release notes between two git tags with categorized PR summaries and author attribution
majiayu000/claude-skill-registry 163
-
no-eval-skill
A skill with no eval.yaml for testing discovery behavior.
majiayu000/claude-skill-registry 163
-
lp-do-assessment-01-problem-statement
Problem framing for new startups (ASSESSMENT-01). Produces a falsifiable problem statement artifact before entering ASSESSMENT intake. Upstream of lp-do-assessment-02-solution-profiling.
majiayu000/claude-skill-registry 163
-
pql-framework
Methodology for defining product-qualified lead (PQL) signals, scoring, and routing.
majiayu000/claude-skill-registry 163