AgentStack
SKILL verified CC0-1.0 Self-run

Audit Tests

skill-jhostalek-dotclaude-audit-tests · by JHostalek

Use when the user wants a thorough audit of the existing test suite — aggressively cutting tests that exist just to exist, rewriting weak ones to actually catch the bugs they should, identifying production code that is uncovered or thinly covered, and adding tests where coverage would catch real defects. Trigger on "audit tests", "find test bloat", "tests don't catch anything", or similar request…

No reviews yet
0 installs
19 views
0.0% view→install

Install

$ agentstack add skill-jhostalek-dotclaude-audit-tests

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Audit Tests? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

!cat ~/.claude/skills/audit-workflow.md

Run as the tests dimension. Lens:

Bias hard toward cutting. A test earns its keep only if it catches context loss between changes or encodes domain knowledge the code can't express. Delete bloat: restated-behavior, getter/setter coverage, mock-the-world ceremonies, framework smoke checks, "returns what I told it to return", assertions mirroring implementation line-for-line. Doubt → delete; deletion is auto-fix.

Rewrite weak tests to catch the bug they nominally guard: tests passing against a broken implementation, asserting incidental output over contract, or so heavily mocked the unit under test never runs. Rewrite preserving intended behavior = auto-fix; rewrite changing which behavior is correct = sign-off.

Add tests where coverage would catch real defects in uncovered or thinly covered production code — critical paths (auth, money, data integrity), non-obvious edges, business rules, integration seams. Skip framework behavior and passthroughs. Prefer integration over mocked unit, behavior over implementation. Coverage for existing behavior = auto-fix.

No flag: absent tests for trivial passthroughs, missing unit test where integration test already exercises the path, coverage gaps in throwaway/generated code. Green baseline before cutting = engine's concern, not a finding.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.