Skip to content
Get packs

Test Collaboration Governance

Track a project's tests, required coverage, and bug-regression evidence in one registry

Source Download skill
Repository
affaan-m/ECC
Stars
295,127
Licence
MIT
Files
3 files

What it does

When installed, the agent treats a project's tests as governed assets. It inventories existing tests, links requirements, business rules, risks and bugs to stable TEST-IDs, and records whether each has sufficient evidence in the repository's test registry (usually TESTS.md). It also flags coverage gaps, duplicate or stale tests, and bugs fixed without regression protection. The skill itself is written as instructions and a template; it does not add a dedicated tool.

Great for

  • Teams with growing test suites who need to know which requirements and past bugs are actually protected
  • Projects where frontend and backend or several services must test against one shared machine-readable contract
  • Reviewers doing pre-delivery checks of test evidence before merging or releasing

Skip it if

  • Small projects with a handful of tests, where the registry overhead outweighs the benefit
  • Teams that need automated test generation, since the skill governs and reviews tests rather than writing them at scale
  • Environments where the agent should not read repository files broadly, because the skill asks it to inspect test directories, CI configuration and contracts

Try asking

  • “Inventory the existing test assets in this repository and identify test gaps for the order module”
  • “Turn the bug we fixed in the payment retry flow into a TEST-ID with a regression test”
  • “Review whether our pre-delivery test evidence is sufficient for the new checkout feature”
  • “Classify our tests as unit, integration, contract, E2E or smoke and update TESTS.md”
Step-by-step guide: how to use Test Collaboration GovernanceInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 3 original files, the MIT licence and an attribution note.

    test-collaboration.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip test-collaboration.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip test-collaboration.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Point the agent at the real test registry first so it preserves existing naming and layout instead of creating a new TESTS.md
  • Ask for a full inventory once on first adoption, then request incremental rescans after changes to tests or CI
  • Review the TEST-ID entries it proposes against your actual specs, since the skill says to link criteria rather than guess them

What's inside

  • agents/openai.yaml
  • SKILL.md
  • templates/TESTS.example.md

Redistributed unmodified from affaan-m/ECC under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.