investigate-first
investigate-first is a Root-cause investigation skill for AI agents, published by JuliusBrussee in the caveman repository on GitHub. Skillspace rates investigate-first D (68/100) and it passed the safety scan; a judge model has also reviewed it.
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
- Grade
- D
- Quality
- 68 / 100
- Safety
- Passed
- GitHub stars
- 105,328
Placed #6 of 6 in the judged category final for Root-cause investigation.
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
- Not declared. Check the repository before reusing it.
Judge review
Placed #6 of 6 in the judged category final for Root-cause investigation.
- Trigger
82 82 - Instructions
45 45 - Specificity
25 25 - Safety
85 85 - Disclosure
50 50 - Maintenance
35 35
A crisp evidence-before-editing philosophy in six bullet points, with no concrete steps, commands, or examples to actually operationalize it.
Not checked yet
- 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.