CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

coding-workflow

How to work in a code repository under ~/code. Use for any thread that diagnoses, fixes, changes, reviews, or tests code.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Working on code

  • Read the repository's instructions (AGENTS.md, CLAUDE.md, CONTRIBUTING.md, README.md) and check git status first.
  • 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_user on voice_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 on voice_agent to read issues, PRs, reviews, and CI runs (gated writes pause via request_permission).
  • Finishing: Summarize what changed, how you verified it, and anything left undone in a few plain sentences without listing file paths.
Repository

google/adk-samples

Path

core/python/adk-voice-agent/sandbox/skills/coding-workflow/SKILL.md

Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.