live-test-authoring
live-test-authoring is an Integration & environment testing skill for AI agents, published by hanamorix in the companion-emergence repository on GitHub. Skillspace rates live-test-authoring D (64/100) and it passed the safety scan; the rating is based on static analysis only.
Guides authoring a live/behavioral test with the tests/harness/ framework — the ordered flow that drives the REAL companion-emergence engine (seed a Canary persona, author a detector, validate it on anchors before trusting it, drive it with a Bob user-sim, run inside the sandbox, adjudicate trips). Use this whenever writing a live test or behavioral test, building a symptom Detector, standing up a Canary fixture, wiring a DumbBob or Agent-Bob user-simulator, driving the real bridge from a test, or setting up a multi-arm A/B run — even if the request just says "test that the companion does X" rather than naming the harness. It is a PROCEDURE, not a reference; the framework's own tests/harness/README.md is the reference for every knob.
- Grade
- D
- Quality
- 64 / 100
- Safety
- Passed
- GitHub stars
- 29
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 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
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.