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
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
按钮
分析代码库结构,查看依赖,变更,引入与创建按钮控件与元素
应用通讯
变更,分析应用通讯
依赖包
分析依赖结构,分析代码库,执行命令
不要重复造轮子
分析代码库结构,分析依赖,变更
elysia后端
分析数据库
plan-format
暂无简介
test-fixer
This skill fixes broken tests.
ticket-breakdown
Decompose one capability area's requirements for one change into implementable tickets with Priority, Value, acceptance criteria, Prior Art, Output contracts, Known Hazards, dependency ordering and relative sizing: one TICKET-NNN.md per ticket plus backlog.md, in the change's tickets directory. Use when a specification is approved and the team needs work items, such as 'break this spec into tickets' or 'create the backlog for search'. Not for implementing a ticket (delivery) or ordering whole capability areas (dependencies).
technical-design
Translate specifications, constraints and dependencies into architecture decisions (AD-XXX), component boundaries, data model and interface contracts under .gener8v/technical-design/. Use when technology or architecture choices must be settled before tickets are written, such as 'which datastore should we use' or 'design the components for search'. Skip it when the approach is obvious and uncontested. Not for judging an architecture that has already shipped (architecture-review).
specification
Expand one capability area from .gener8v/prd.md into a functional specification with atomic, testable [PREFIX]-REQ-XXX requirements, behaviors, edge cases and open questions under .gener8v/specifications/. Use when a PRD capability area needs elaboration before constraints, technical design or tickets, or a change brief still marks an area as pending specification, such as 'spec out the search area' or 'write the requirements for billing'. Not for the whole product (planning) or work items (ticket-breakdown).
setup
Bootstrap the gener8v pipeline in a project: create .gener8v/, copy the conventions, generate pipeline-state.yaml, and add the pipeline directives to CLAUDE.md. Use when the user says 'set up gener8v' or 'initialize the pipeline', when a project has no .gener8v/prd.md, or after a plugin upgrade to refresh the conventions. Not for deciding what to do next on a project already on the pipeline (orchestrate).
security-review
OWASP-informed, code-level security review of delivered code: injection, authentication and authorization, data exposure, configuration, dependencies, cryptography and logging, with attack scenarios for Medium+ findings and compliance constraints (CC-XXX) treated as Critical. Use after a delivery, especially one touching input handling, auth, sensitive data or external integrations, such as 'security review TICKET-007' or 'check what this delivery shipped for injection or auth bypass before we merge'. Not for a whole-codebase OWASP posture assessment (owasp-top10-review) or prompt-injection risk in LLM features (owasp-llm-top10-review).
rot-watch
Detect decay in code that is being actively written: measure six signals (packaging drift, dependency direction, comment language, growth slopes, tests, the detectable subset of SOLID) against a recorded baseline and report only what moved, at .gener8v/rot/. Use once code has been delivered and again every few deliveries, before a release, or when asked 'is the codebase getting worse' or 'has this module drifted'. The first run records the baseline and reports nothing. Not for one delivery's quality (quality-review), defects (defect-sweep) or whether the architecture was right (architecture-review).
quality-review
Review delivered code for engineering quality (organization, readability, error handling, tests, consistency with the codebase's patterns) independent of the specification. Use after a delivery in parallel with code-review and security-review, or on any files the user points at, such as 'is this module maintainable' or 'review this file for readability and tests'. Not for checking a delivery against its ticket (code-review), vulnerabilities (security-review) or decay across many deliveries (rot-watch).
planning
Turn a description of a feature, product or system into a PRD at .gener8v/prd.md (3-7 capability areas, user scenarios, scope boundaries, open questions) and open a change brief under .gener8v/changes/ with its priority cut. Use when the user describes something new they want built, such as 'I want to build a support portal' or 'add a feature that lets agents export results': a greenfield product, new scope on a project already on the pipeline (Planning opens a new change for it rather than folding it into a change in delivery), or the first feature after brownfield onboarding. Not for onboarding an existing codebase with no PRD (brownfield) or detailing an area the current change already covers (specification).
owasp-top10-review
Category-by-category OWASP Top 10:2025 coverage assessment of a codebase: maps existing SEC-XXX findings onto the taxonomy, probes the categories bottom-up reviews miss (supply chain, exceptional conditions, logging, SSRF) and re-ranks priorities. Use when asked 'are we OWASP-compliant' or 'how do we score against the Top 10', before an audit or a security questionnaire, or after security reviews accumulate. Not for one delivered ticket (security-review) or the model surface of an LLM application (owasp-llm-top10-review).
owasp-llm-top10-review
OWASP Top 10 for LLM Applications 2025 assessment of anything that calls a model: direct and indirect prompt injection, sensitive disclosure, output handling, excessive agency, system-prompt leakage, vector and embedding weaknesses, unbounded consumption. Use for chat, RAG, agentic or LLM-orchestration code, alongside the web OWASP review, such as 'can someone smuggle instructions in through retrieved documents' or 'is our chatbot safe to launch'. Not for systems that make no model calls (owasp-top10-review) or one delivered ticket (security-review).
orchestrate
Report where the gener8v pipeline stands (coverage matrix per capability area, ticket-level delivery and review status with verdicts, current stage), regenerate .gener8v/pipeline-state.yaml, and recommend the exact next skills and targets. Use at session start, after any pipeline skill, after a break or a compaction, or when asked 'what's next', 'where are we' or 'what should I work on'. Reports and recommends only: it writes nothing but the state file.