eval-harness
eval-harness is an LLM evaluation & observability skill for AI agents, published by allenhutchison in the obsidian-gemini repository on GitHub. Skillspace rates eval-harness D (68/100) and it passed the safety scan; the rating is based on static analysis only.
Run the eval harness against a real Obsidian instance, monitor for the harness's known reliability gotchas (concurrent runs, CLI-bridge hangs, stale child processes), and bless a result as a baseline only when the run is clean. Use when the user asks to "run the evals", "bless a baseline", "measure the impact of <change> on solve rate", "run a model sweep", or similar. Has Obsidian-CLI side effects (drives the agent view, creates eval-scratch fixtures, may set chatModelName for the duration of the run); does NOT modify plugin source code or commit unless explicitly asked.
- Grade
- D
- Quality
- 68 / 100
- Safety
- Passed
- GitHub stars
- 506
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.
Our review
- Architecture
- 100 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
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.