Skip to content
Get packs

Test Value Auditor

Audits and chooses tests by the risk they protect, cutting slow, flaky or redundant checks

Source Download skill
Repository
tt-a1i/archify
Stars
92,587
Licence
Apache-2.0
Files
4 files

What it does

When installed, the agent reviews existing tests or picks which tests to add, change, merge or remove for code it is working on. It asks what real failure each test would catch and what a user would lose if that failure happened, then recommends the cheapest check that still protects that risk. It also helps diagnose a failing test by separating a real product bug from an outdated assertion, an environment problem or an unstable test.

Great for

  • Developers with slow or flaky test suites who want to cut feedback time without losing real protection
  • Teams reviewing AI-written tests to check whether implementation and tests share the same wrong assumption
  • Engineers preparing a commit or pull request who want only the tests affected by their change run

Skip it if

  • Projects that need a full repository-wide test audit on every small edit: the skill says ordinary implementation and pre-commit work should stay scoped to affected behavior
  • Users who want the agent to commit or push automatically: the skill says reviewing before a commit does not authorize committing or pushing

Try asking

  • “Audit the slow and flaky tests in the payments module and tell me which ones protect real risks”
  • “I changed the date parser. Which tests should I add, adapt or remove before I open a PR?”
  • “This test failed after my refactor. Is it a real regression, an obsolete assertion, or a flaky test?”
  • “Review the test changes in my current branch and explain why each new test matters”
Step-by-step guide: how to use Test Value AuditorInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 4 original files, the Apache-2.0 licence and an attribution note.

    test-value.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

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

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip test-value.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

  • Name the scope explicitly (a module, file or behavior) so the agent does not drift into a repository-wide audit
  • Say whether you want a read-only audit or permission to make scoped changes, since the skill treats these differently
  • Ask the agent to report which tests actually ran, because a green result with no relevant tests proves nothing

What's inside

  • agents/openai.yaml
  • references/audit.md
  • references/decision-examples.md
  • SKILL.md

Redistributed unmodified from tt-a1i/archify under the Apache-2.0 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.