tl-regression-test

tl-regression-test is a Test-driven development skill for AI agents, published by ITSalt in the NaCl repository on GitHub. Skillspace rates tl-regression-test F (53/100) and it passed the safety scan; the rating is based on static analysis only.

Writes a test authored by a separate sub-agent (test-author isolation seam). Two modes: bug-fix — writes a test that FAILS on broken (un-fixed) code. feature-dev — writes a test that FAILS because the feature does not exist yet. In both modes the test MUST be RED on the current codebase before this skill returns. A green test here means the test does not capture what it should, and will be rejected. Writes ONLY the test file. Never modifies production code. Refuses if the affected workspace has no test runner. Use when: invoked by /nacl:tl-fix Step 6d (bug-fix mode), or by /nacl:tl-dev-be, /nacl:tl-dev-fe, /nacl:tl-dev Steps 3.2–3.3 / A.2–A.3 (feature-dev mode), or directly by the user.

Grade
F
Quality
53 / 100
Safety
Passed
GitHub stars
22

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubITSalt/NaCl

Our review

Architecture
80 / 100
Maturity
Basic: a single SKILL.md
Security scan
Low-risk patterns
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Test-driven development

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.