Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
doc-writer
Create or update numbered task docs using repo context, DOC_TEMPLATE.md, and naming conventions.
majiayu000/claude-skill-registry 163
-
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
majiayu000/claude-skill-registry 163
-
deployment-procedures
Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts.
majiayu000/claude-skill-registry 163
-
docs-7474-vimeoopenapi
majiayu000/claude-skill-registry 163
-
manifest-automation
Create and update manifest files using advanced web automation with Playwright, intelligent retry logic, and smart merge capabilities
majiayu000/claude-skill-registry 163
-
postgresql
Manages PostgreSQL database schema, migrations, and queries for Bookkeep.
Use when: configuring database connections, writing migrations, optimizing queries, handling connection pooling, or troubleshooting database issues.
majiayu000/claude-skill-registry 163
-
mail-work
Show work emails only, filtered to Exchange/EWS accounts and corporate email domains. Digest with priorities. Use when user asks about work email, work inbox, or wants to separate work from personal mail. Arguments: optional date range or "today", "yesterday", "this week".
majiayu000/claude-skill-registry 163
-
AgentDB Vector Search
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
majiayu000/claude-skill-registry 163
-
marketing-specialist
提供内容营销、增长策略、社交媒体管理和应用商店优化能力。当需要创建营销内容、制定增长策略或管理社交媒体时使用。
majiayu000/claude-skill-registry 163
-
context-engineering-advisor
Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.
majiayu000/claude-skill-registry 163
-
math-review
Verify math-heavy code for algorithm correctness, numerical stability, and standards alignment
majiayu000/claude-skill-registry 163
-
typescript
TypeScript strict patterns and best practices. Trigger: When writing TypeScript code - types, interfaces, generics.
majiayu000/claude-skill-registry 163
-
db-dump-xml
Выгрузка конфигурации 1С в XML-файлы. Используй когда пользователь просит выгрузить конфигурацию в файлы, XML, исходники, DumpConfigToFiles
majiayu000/claude-skill-registry 163
-
bmad-distillator
Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.
majiayu000/claude-skill-registry 163
-
m04-zero-cost
CRITICAL: Use for generics, traits, zero-cost abstraction. Triggers: E0277, E0308, E0599, generic, trait, impl, dyn, where, monomorphization, static dispatch, dynamic dispatch, impl Trait, trait bound not satisfied, 泛型, 特征, 零成本抽象, 单态化
majiayu000/claude-skill-registry 163
-
abstraction-quality
Evaluates whether abstractions genuinely provide a fundamentally different way of thinking or are structurally shallow. Use when adjacent layers feel redundant, when decorator/wrapper patterns add boilerplate without depth or when an abstraction feels leaky. Not for measuring a single module's interface-to-implementation ratio (use deep-modules) or checking for information leakage across boundaries (use information-hiding).
majiayu000/claude-skill-registry 163
-
claude-review
Review code changes using Hyperlane monorepo coding standards. Use when reviewing PRs, checking your own changes, or doing self-review before committing.
majiayu000/claude-skill-registry 163
-
py-audit-bot
Execute BioETL py-audit-bot profile for role-specific workflow and constraints.
majiayu000/claude-skill-registry 163
-
Agent Reliability & Safety
Design reliable, safe, and trustworthy agent systems that fail gracefully and operate within bounds. Use when building guardrails, handling edge cases, preventing harmful outputs, monitoring for failures, implementing safety constraints, or designing error recovery. Covers failure modes, constraint systems, oversight mechanisms, and safety validation.
majiayu000/claude-skill-registry 163
-
bmad-wds-bugfixing
Fix bugs in existing code through structured investigation and verification
majiayu000/claude-skill-registry 163
-
plan-brainstorm
Explore creative approaches and ideas with external source validation.
majiayu000/claude-skill-registry 163
-
write-skill-readme
当用户明确要求"生成技能 README"、"编写用户指南"或"更新技能文档"时使用。为 Agent Skills 编写符合最佳实践的 README.md 用户使用指南。自动分析技能结构（SKILL.md、config.yaml、scripts/），按模板生成小白友好的文档。
majiayu000/claude-skill-registry 163
-
flutter-init
Use when user wants to create a new Flutter project (Todo/Habit/Note/Expense/Custom domain) with Clean Architecture, Riverpod 3.0, Drift, and modern Flutter stack
majiayu000/claude-skill-registry 163
-
model-escalation
Automatic model switching based on task complexity for OpenClaw agents. Dynamically escalates between Haiku (simple), Sonnet (medium), and Opus (complex) models. Tracks prefix consistency ([H], [S], [O]) and logs discrepancies. USE WHEN configuring multi-model agents, optimizing API costs, or implementing complexity-based model routing.
majiayu000/claude-skill-registry 163