Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
rfc-compliance-workflow
RFC/OIDC仕様書の準拠ワークフロー。要件抽出→Gap分析→実装設計→E2Eテスト生成までの一連の流れを管理。
majiayu000/claude-skill-registry 163
-
agent-prompt-behavior
Design agent system prompts with explicit behavior rules and cognitive control.
This skill should be used when users need to define agent instructions,
create intent-to-tool mappings, establish confirmation policies, or prevent
hallucinated actions in AI agents.
majiayu000/claude-skill-registry 163
-
database-design-vuralserhat86-antigravity-agentic--2
majiayu000/claude-skill-registry 163
-
confirm-plan
Plan confirmation workflow - extract plan from conversation, create file, auto-review with Interactive Recovery. Use for confirming plans after /00_plan.
majiayu000/claude-skill-registry 163
-
koerner-office
Talk to Koerner Office King Of Hustle about their expertise. Koerner Office King Of Hustle provides authentic advice using their mental models, core beliefs, and real-world examples.
majiayu000/claude-skill-registry 163
-
solublempnn
Solubility-optimized protein sequence design using SolubleMPNN. Use this skill when: (1) Designing for E. coli expression, (2) Optimizing solubility of designed proteins, (3) Reducing aggregation propensity, (4) Need high-yield expression, (5) Avoiding inclusion body formation.
For standard design, use proteinmpnn. For ligand-aware design, use ligandmpnn.
majiayu000/claude-skill-registry 163
-
direct-response-copy
Write persuasive sales copy that converts using proven direct response principles. Use when writing landing pages, sales emails, ads, or any copy designed to drive action.
majiayu000/claude-skill-registry 163
-
art-direction-prompt-refiner
Transform rough image generation prompts into consistent, effective art direction. Use when getting inconsistent results from AI image generators, need variations matching existing style, or translating vague ideas into precise prompts. Outputs structured prompts, negative prompts, and composition variants.
majiayu000/claude-skill-registry 163
-
migration-management-skill
majiayu000/claude-skill-registry 163
-
create-hooks
Expert guidance for creating, configuring, and using Claude Code hooks. Use when working with hooks, setting up event listeners, validating commands, automating workflows, adding notifications, or understanding hook types (PreToolUse, PostToolUse, Stop, SessionStart, UserPromptSubmit, etc).
majiayu000/claude-skill-registry 163
-
skill-repo
Agent Skill: Guide for structuring Netresearch skill repositories. Use when creating skills, standardizing repos, or setting up composer/release workflows. By Netresearch.
majiayu000/claude-skill-registry 163
-
prettier
Code formatting with Prettier for TypeScript/NestJS projects. Trigger: After editing/creating files, before committing code, ensuring code style consistency.
majiayu000/claude-skill-registry 163
-
personal-crypto-secrets-management
Diagnose and resolve AES-256-GCM crypto key mismatches in the Orient secrets service
majiayu000/claude-skill-registry 163
-
skill-quality-standards
When creating or validating skills. Reference for SKILL-CREATOR and SKILL-VALIDATOR.
majiayu000/claude-skill-registry 163
-
experiment-workflow
Run thesis experiments from ideation through publication. Use when brainstorming research questions, writing specs, executing experiments, or polishing for thesis.
majiayu000/claude-skill-registry 163
-
meteor-sync-specialist
Sync data from Meteor MongoDB to Supabase; use when running syncs, debugging sync failures, investigating entity mapping issues, or implementing new mappers
majiayu000/claude-skill-registry 163
-
cross-linking
Guidance for finding and adding bidirectional wikilinks when creating or updating content in the knowledge base. Use when user creates new content or wants to improve discoverability by adding links to related pages. Helps maintain the interconnected graph structure.
majiayu000/claude-skill-registry 163
-
rich-text-editor-engineering
Integrate or build a contenteditable-based editor with custom data models.
majiayu000/claude-skill-registry 163
-
test-guardian
Specialized in testing and quality assurance for Gravito. Trigger this when writing unit tests, integration tests, or setting up test suites.
majiayu000/claude-skill-registry 163
-
69-evaluation-quality-gates
Create a reusable skill for evaluating fine-tuned models, benchmarking performance, and detecting quality regressions
majiayu000/claude-skill-registry 163
-
Enterprise AI Patterns
Production-grade AI architecture patterns for enterprise - security, governance, scalability, and operational excellence
majiayu000/claude-skill-registry 163
-
remote-code-agents
Delegate tasks to remote Claude Code agent containers for parallel execution, long-running analysis, or resource-intensive operations.
majiayu000/claude-skill-registry 163
-
agentica-prompts
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
majiayu000/claude-skill-registry 163
-
update-project
Update project to latest Clorch standards (agents, hooks, settings)
majiayu000/claude-skill-registry 163