GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills，按职业与使用场景整理，复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoft
openclaw
@openclaw
OpenAI
@openai
The Apache Software Foundation
@apache
GitHub
@github
Anthropic
@anthropics
AutoGPT
@Significant-Gravitas
Garry Tan
@garrytan全部 Skills 196628
create-story
Creates a new Momentum story (from an epic) or enriches an existing slug-stub in place — change-type classification, injected EDD/TDD guidance, AVFL validation. Use when creating or fleshing out a Momentum story.
gitnexus-debugging
Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?", "Where does this error come from?", "Trace this bug"
gitnexus-cli
Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki"
constitution-builder
Builds Tier 1 domain-knowledge constitution for KB-backed agents. Accepts write_mode: in_place_skill | composed_agent_file | standalone_constitution.
conductor
In-session sprint build orchestrator — per-story pipelines, AVFL-on-merge, E2E, single end-gate. No story-count cap.
code-reviewer
Non-interactive bmad-code-review adapter for conduct. Accepts a single story diff, drives adversarial bug-hunt in report-only mode, normalizes surviving findings to the canonical schema with stakes_class populated, and returns the finding stream to the Conductor. Invoked by the Conductor — do not invoke directly.
canvas
Launch the Momentum Cycle live dashboard (Hono+Bun, port 3456). Checks if running, starts if not; opens http://localhost:3456 in the viewer pane.
build-guidelines
Builds gen-2 composed specialist agent files (base body + manifesto) and Tier 1 constitution. Run before sprint to bake guidelines in.
validator-enum
AVFL Enumerator validator. Systematic, section-by-section quality validation.
validator-adv
AVFL Adversary validator. Intuitive, holistic, pattern-aware quality validation.
avfl-merge-review
AVFL merge-review sub-skill — invoked by the avfl-merge-review Workflow. Do not invoke directly.
fixer
AVFL fixer. Applies validated findings as corrections and produces a complete fixed artifact.
consolidator
AVFL consolidator. Merges, cross-checks, deduplicates, and scores validator findings.
avfl
Adversarial Validate-Fix Loop — multi-agent validation catching errors, hallucinations, and quality issues via parallel lenses and iterative fix.
assessment
Guided product state evaluation. Spawns parallel discovery agents, validates findings with the developer, and produces a structured ASR document.
architecture-guard
Detects pattern drift against architecture decisions. Read-only enforcer. Invoked by Impetus — do not invoke directly.
test-config-scanner
Detects testing frameworks, configuration, and test patterns in the project.
source-pattern-scanner
Analyzes source code patterns to identify languages, frameworks, and conventions.