ronronner02/codepilot-agent

多 Agent 代码分析助手:输入 GitHub 仓库地址,产出可追溯到文件与行号的架构报告、代码评审与可追问的索引。LangGraph + RAG + MCP + React。

0Stars on the repository
85Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

spec-doc-review

25

ronronner02/codepilot-agent

Skill Claude CodeCodex

A review method for requirements, plans, task packs, or specifications using several assigned reviewer perspectives. A specification is a document describing what software should do or how it should be built.

not rated 0 3d ago A 48 tokens original MIT

spec-dogfood

26

ronronner02/codepilot-agent

Skill Claude CodeCodex

Hands-off, diff-scoped browser QA of the active branch or PR. Use when a branch needs autonomous user-flow dogfooding before review or shipping: map changed flows, drive agent-browser, fix small breakages with regression tests, record human-decision blockers, and write a durable report. Do not use for collaborative UI…

not rated 0 3d ago C 89 tokens original MIT

spec-ideate

27

ronronner02/codepilot-agent

Skill Claude CodeCodex

Generate and evaluate grounded ideas. Use when the user asks for ideas, improvements, surprising options, or AI-generated directions before choosing one to develop; use spec-brainstorm to refine the user's own idea.

not rated 0 3d ago B 46 tokens original MIT

spec-optimize

28

ronronner02/codepilot-agent

Skill Claude CodeCodex

Run metric-driven iterative optimization loops. Define a measurable goal, build measurement scaffolding, then run parallel experiments that try many approaches, measure each against hard gates and/or LLM-as-judge quality scores, keep improvements, and converge toward the best solution. Use when optimizing clustering…

not rated 0 3d ago A 100 tokens original MIT

spec-plan

29

ronronner02/codepilot-agent

Skill Claude CodeCodex

Create or deepen evidence-grounded plans for multi-step software and non-software work, including plans derived from requirements and answer-seeking research plans. Use when the outcome is clear enough to plan but HOW is unsettled. Prefer spec-brainstorm for unresolved WHAT, spec-debug for active failures, spec-work…

not rated 0 3d ago A 86 tokens original MIT

spec-polish

30

ronronner02/codepilot-agent

Skill Claude CodeCodex

Start the dev server, inspect the feature in browser, and iterate on polish.

not rated 0 3d ago A 20 tokens original MIT

spec-prd

31

ronronner02/codepilot-agent

Skill Claude CodeCodex

Public workflow entrypoint (spec-prd): create, write, refine, or validate planning-readiness of brownfield PRD-grade requirements for existing systems before implementation planning. Do not use for 0-1 product exploration, unresolved product shape, HOW planning/task compilation, implementation/debug/review…

not rated 0 3d ago A 111 tokens original MIT

spec-runtime-setup

32

ronronner02/codepilot-agent

Skill Claude CodeCodex

Install, configure, verify, and refresh required harness runtime readiness facts for spec-first workflows on Claude Code, Codex, Cursor, Kiro, Qoder, or OpenCode.

not rated 0 3d ago C 41 tokens original MIT

spec-work

33

ronronner02/codepilot-agent

Skill Claude CodeCodex

Execute a settled plan, validated task pack, spec path, or concrete implementation request end-to-end. Use spec-debug for open-ended bugs; stop when target repo, scope, source ownership, or required authorization is unresolved.

not rated 0 3d ago A 47 tokens original MIT

spec-write-skill

34

ronronner02/codepilot-agent

Skill Claude CodeCodex

A workflow for creating, updating, or migrating reusable packages that teach coding agents how to perform tasks. It can also check a package without changing it and report whether it is ready.

not rated 0 3d ago A 102 tokens original MIT

spec-write-tasks

35

ronronner02/codepilot-agent

Skill Claude CodeCodex

Public workflow entrypoint (spec-write-tasks): compile a settled local spec-plan into an optional derived task pack for spec-work, or validate an existing local task pack before execution. Use for explicit plan-splitting/task-doc requests or high-complexity work suitability; do not use for plan authoring…

not rated 0 3d ago A 110 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: