coding-workflow
How to work in a code repository under ~/code. Use for any thread that diagnoses, fixes, changes, reviews, or tests code.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.1w
- Forks
- 3.0k
01 前言 Front Matter
- name
- coding-workflow
- description
- How to work in a code repository under ~/code. Use for any thread that diagnoses, fixes, changes, reviews, or tests code.
03 SKILL.md 正文
Working on code
- Read the repository's instructions (
AGENTS.md,CLAUDE.md,CONTRIBUTING.md,README.md) and checkgit statusfirst. - Diagnose without changing: "Why is this failing", "figure out", "look into", "review", and "explain" ask for analysis, not edits. Reproduce the issue, identify the file, line, and introducing change, and propose the fix in your response without modifying files.
- Fixing:
- Reproduce first with a failing test or command, then fix the root cause. Never skip, delete, or weaken a test to pass.
- Make the minimal change matching surrounding style; add or update tests for changed behavior.
- Report meaningful findings during the run with
update_useronvoice_agent. - For large, underspecified changes, write a brief proposed plan or clarifying question in your response and end your turn.
- Verifying: Run existing tests, linters, and type checkers, and report only checks you actually ran.
- Git & GitHub:
- The server commits your working directory on the thread's branch when the turn ends. Do not commit, rebase, or switch branches unless asked.
- Never push, open a pull request, or merge on your own; tell the user the branch is ready to publish.
- Use
github__*tools onvoice_agentto read issues, PRs, reviews, and CI runs (gated writes pause viarequest_permission).
- Finishing: Summarize what changed, how you verified it, and anything left undone in a few plain sentences without listing file paths.
04 同仓库更多 Skills
retail-virtual-tryon
Creates virtual try-on agents supporting image and video (catwalk animation) try-ons on Google Cloud (Gemini image models and Veo on Gemini Enterprise Agent Platform). Handles resource setup, user photo uploading, image/video generation pipelines, local testing, and evaluation.
retail-product-search
Creates product search agents with semantic search and RAG on Google Cloud (Vector Search on Gemini Enterprise Agent Platform, BigQuery, embeddings). Use when the user wants to "build a product search agent", "create an e-commerce search", "make a shopping assistant", "set up semantic catalog discovery", "ingest products into Vector Search", or "deploy a retail RAG agent". Handles the full pipeline: catalog data ingestion to BigQuery, Gemini Enterprise Agent Platform Vector Search collection setup, ADK agent scaffolding, evaluation, and Cloud Run deployment.
routines
Use for a recurring unattended task (cron; pull data, open a PR, post a digest), or to test/dry-run a routine first. Explains authoring and testing via the routine tool.
policy
Inspect the per-workspace tool-policy overlay (.lha/policies.jsonl) that gates destructive or sensitive tool calls, and tell the user what to change if they want a rule added or removed.
google-workspace
Read/write Google Drive, Docs, Sheets, Gmail, Calendar, Chat, Tasks, Slides via the `gws` CLI. Needs an OAuth client or service account configured first. Use for any Google Workspace task.
find-skills
Discover/install NEW agent skills from external sources (skills.sh). Use for capabilities you lack, e.g. "find a skill for X". Do NOT use to list skills you already have; see `<available_skills>`.