Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
doc-coauthoring
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
majiayu000/claude-skill-registry 163
-
command-naming-conventions
コマンド命名規則（動詞ベース命名/kebab-case/名前空間/発見可能性）を整理し、一貫した命名設計と見直しを支援するスキル。
命名ルール、チェックリスト運用、検証手順を一貫して整理する。
Anchors:
• The Pragmatic Programmer (Andrew Hunt, David Thomas) / 適用: 命名規則の一貫性 / 目的: 実践的な命名の安定化
• Clean Code (Robert C. Martin) / 適用: 意図が伝わる命名 / 目的: 自己説明性の向上
Trigger:
Use when defining command naming conventions, reviewing naming consistency, or designing namespace structures.
command naming, kebab-case, verb-based naming, namespace design, discoverability
majiayu000/claude-skill-registry 163
-
dokkado
Five-phase reasoning protocol based on Musashi's Book of Five Rings. Ground (morphemic extraction), Water (pattern matching), Fire (unified derivation), Wind (predictions), Void (meta-closure). Use for cross-disciplinary insight discovery.
majiayu000/claude-skill-registry 163
-
abaqus-interaction
Define contact and interactions - contact pairs, tie constraints, connectors. Use when user mentions contact, friction, tie, parts touching, or bonded surfaces.
majiayu000/claude-skill-registry 163
-
AgentDB Advanced Features
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.
majiayu000/claude-skill-registry 163
-
remotion-best-practices
Best practices for Remotion - Video creation in React
majiayu000/claude-skill-registry 163
-
novel-truncator
Intelligently truncate text while preserving content integrity. Suitable for novel text preprocessing, ensuring text does not exceed specified length limits
majiayu000/claude-skill-registry 163
-
prodcheck
Release Wolf - Pre-deployment QA gatekeeper. Run before any production deploy. Checks for exposed secrets, broken links, Lighthouse performance scores, and visual regressions. Invoke with /prodcheck or when user mentions 'release check', 'deploy check', 'pre-launch', 'go/no-go', or 'production ready'.
majiayu000/claude-skill-registry 163
-
error-message-explainer
Explain compiler/runtime errors in plain language. Use when a junior developer needs help understanding an error message.
majiayu000/claude-skill-registry 163
-
python-testing
Write and run Python tests using pytest with fixtures, mocking, coverage, and the AAA pattern. Use when writing Python tests, creating test files, or setting up pytest configuration.
majiayu000/claude-skill-registry 163
-
research-agent
Research agent for external documentation, best practices, and library APIs via MCP tools
majiayu000/claude-skill-registry 163
-
dignified-python
Python coding standards with automatic version detection. Use when writing, reviewing, or refactoring Python to ensure adherence to LBYL exception handling patterns, modern type syntax (list[str], str | None), pathlib operations, ABC-based interfaces, absolute imports, and explicit error boundaries at CLI level. Also provides production-tested code smell patterns from Dagster Labs for API design, parameter complexity, and code organization. Essential for maintaining erk's dignified Python standards.
majiayu000/claude-skill-registry 163
-
e2e-test
Run E2E test scenarios against running services. Use for happy path testing, unhappy flows, debugging, or when user says "otestuj", "proved test", "zkus flow".
majiayu000/claude-skill-registry 163
-
nuxt-content
Author Markdown content files for Nuxt Content using MDC syntax. Use when creating or editing .md files in content/ directories, writing documentation, blog posts, or any content that uses Vue components in Markdown. Triggers on content authoring, MDC syntax, Nuxt Content files.
majiayu000/claude-skill-registry 163
-
dotnet-testing-autofixture-basics
使用 AutoFixture 自動產生測試資料的基礎技能。
當需要快速產生測試物件、減少樣板程式碼、實現匿名測試時使用。
涵蓋 Fixture.Create、CreateMany、循環參考處理、與 xUnit 整合等。
majiayu000/claude-skill-registry 163
-
systems-thinking
Apply systems thinking to leadership decisions and produce a Systems Thinking Pack (system boundary, actors & incentives map, feedback loops, second-order effects ledger, leverage points, intervention plan). Use for complex ecosystems, trade-offs, org/process redesign, and preventing unintended consequences.
majiayu000/claude-skill-registry 163
-
karen-repo-reviewer
Use when the user requests a repository review, code assessment, or honest evaluation of their codebase. Provides brutally honest AI-powered reviews with market-aware Karen Scores (0-100) analyzing over-engineering, completion honesty, and practical value. Available as GitHub Action or IDE tool.
majiayu000/claude-skill-registry 163
-
cost-optimization-review
Review system costs and propose reductions. Use when a senior developer needs cost-saving recommendations.
majiayu000/claude-skill-registry 163
-
prescriptive-analytics
When the user wants decision support systems, recommendation engines, or prescriptive analytics. Also use when the user mentions "decision optimization," "recommendation system," "what should we do," "action recommendations," "decision support," "intelligent recommendations," "automated decisions," or "prescriptive models." For pure optimization, see optimization-modeling. For forecasting, see demand-forecasting.
majiayu000/claude-skill-registry 163
-
repo-defining-workflows-wahidyankf-open-sharia-enterpri
Workflow pattern standards for creating multi-agent orchestrations including YAML frontmatter (name, description, tags, status, agents, parameters), execution phases (sequential/parallel/conditional), agent coordination patterns, and Gherkin success criteria. Essential for defining reusable, validated workflow processes.
majiayu000/claude-skill-registry 163
-
boliga-api
Query Danish real estate data from Boliga.dk as pandas DataFrames. Use when the user asks about Danish property prices, real estate searches, market statistics, or housing analysis in Denmark.
majiayu000/claude-skill-registry 163
-
kratos-tests
Generates comprehensive table-driven tests for go-kratos microservices using testify/mock and testify/assert. Creates repository tests with in-memory SQLite, business layer tests with mocks, and service layer tests with proper context propagation. Use when writing unit tests for any kratos layer, adding test coverage, creating mock implementations, or validating CRUD operations.
majiayu000/claude-skill-registry 163
-
ha-api
Integrate with Home Assistant REST and WebSocket APIs. Use when making API calls, managing entity states, calling services, subscribing to events, or setting up authentication. Activates on keywords REST API, WebSocket, API endpoint, service call, access token, Bearer token, subscribe_events.
majiayu000/claude-skill-registry 163
-
patent-search
Search 76M+ patents using BigQuery (fast, zero setup) or PatentsView API (US patents with rich metadata).
majiayu000/claude-skill-registry 163