浏览 Git-Fg 维护的已发布 AI 技能，比较用途与说明，并通过来源仓库了解安装方式。
已收录技能
76收录技能的仓库 Stars 合计
71仓库 Forks
0平均每个技能的仓库 Stars
1同一仓库中的多个技能可能共享 Stars，合计包含重复仓库数据。
Project-scoped skills router for .claude/skills/ with progressive disclosure. Use when creating, auditing, or refining skills in current project. Routes to skills-knowledge for implementation details. Do not us...
Orchestrate resource contention test
Unified CLI testing workflow - execute skills/plugins/subagents tests with stream-json output, automated analysis, and comprehensive reporting
Forked skill testing context isolation
Test skill that simulates timeout behavior analysis
Tests context isolation in forked skills
Orchestrates comprehensive audit workflow
Project-scoped .mcp.json router with multi-workflow orchestration. Automatically detects DISCOVER/INTEGRATE/VALIDATE/OPTIMIZE workflows. Routes to mcp-knowledge for configuration details.
Create event-driven automation and validation hooks in your local project. Use for file validation, security guardrails, pre-tool checks, and project automation. Templates for PreToolUse, PostToolUse, and compo...
Validate .claude/ configuration quality and compliance with 2026 best practices. Use when auditing project setup, checking skills/mcp/hooks compliance, or validating local-first configuration. Do not use for st...
Creates, audits, and refines subagent files with multi-workflow orchestration. Automatically detects DETECT/CREATE/VALIDATE/OPTIMIZE workflows. Context-aware routing for projects and plugins. Routes to subagent...
Proactively capture and archive project discoveries during work. Maintains CLAUDE.md by capturing working commands, architectural decisions, gotchas, and insights as they emerge during development. Use during a...
Creates, audits, and refines subagent files with multi-workflow orchestration. Automatically detects DETECT/CREATE/VALIDATE/OPTIMIZE workflows. Context-aware routing for projects and plugins.
Configure and audit project guardrails in .claude/ configuration with multi-workflow orchestration. Automatically detects INIT/SECURE/AUDIT/REMEDIATE workflows. Creates component-scoped hooks (skills/commands/a...
Configure and audit project guardrails in .claude/ configuration with multi-workflow orchestration. Automatically detects INIT/SECURE/AUDIT/REMEDIATE workflows. Creates component-scoped hooks with PreToolUse/Po...
Orchestrates parallel forked workers
Checks if variables are blocked
Analyze tool usage patterns from stream-json log files and verify test suites
Long-running skill to test timeout behavior
Reference knowledge for hooks: events (PreToolUse/PostToolUse/Stop), security patterns, exit codes, configuration types. Use when understanding hooks. No execution logic.
Improving and debugging skills through metacognitive analysis. Use when needing to analyzes skill execution patterns, identifies flaws in instructions, and refines skill content to improve performance.
Inspects what context is available
Audits code quality and patterns
Creates, refines, ingests, and evaluates agent skills using archetype-driven design. Use when building skills from scratch, extracting knowledge from documentation, or auditing skill quality. Do not use for non...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。