agent-trust-hub
Reviewed
Analyzed Aug 11, 2026
juliusbrussee/caveman
investigate-first
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
8-week activity · all time api
Installation
$
npx skills add juliusbrussee/caveman --skill investigate-first
Similar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
investigate-without-getting-made
Similar name
useosint/skills
>- Investigator OPSEC — threat-model who might notice you, control your attribution surface acr…
58.1K installs
investigate-anything
Similar name
useosint/skills
>- Start-here router and tradecraft baseline for any investigation into a person, company, doma…
1.6K installs
investigate
Similar name
ghaida/intent
Guide and conduct user research — from planning through synthesis. Interview scripts, survey de…
1.6K installs
k6-cloud-investigate-test
Similar name
grafana/skills
Investigate a Grafana Cloud k6 test — describe the script, list run history, identify pass/fail…
1.3K installs
investigate
Similar name
cyrusagents/cyrus
Research the codebase to answer questions. Search for relevant files, gather context, and provi…
36 installs
investigate
Similar name
launchdarkly/ai-tooling
Analyzes observability data — logs, traces, errors, sessions, and metrics — to find root cause …
584 installsSecurity audits
Partner security reviews for this skill.
snyk
Reviewed
Analyzed Aug 11, 2026
socket
Score 0.9000 · 0 alerts
Analyzed Aug 11, 2026
0 alerts
Also in this package
Other skills from juliusbrussee/caveman · top by installs.
npx skills add juliusbrussee/caveman
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Claude Code
Not declared
Cursor
Not declared
Codex
Not declared
GitHub Copilot
Not declared
Windsurf
Not declared
Gemini CLI
Not declared
Cline
Not declared
OpenCode
Not declared
Repository health
Stars
104.3K
License
LICENSE
Default branch
main
Open issues
62
Status
Active
Package contents
Files included with this skill beyond the listing page.
-
skill md
SKILL.md688 B -
docs
SUMMARY.md194 B
History
- First seen on skills.sh
- First recorded snapshot · 39,900 installs
SKILL.md
Investigate first
Gather evidence before changing product code.
- Separate observed symptom from inferred cause.
- Trace inputs, state transitions, ownership boundaries, and failure output.
- Rank hypotheses by evidence and cheap falsification value.
- Do not edit until one credible mechanism explains evidence.
- Stop exploration when evidence is sufficient to name cause or exact blocker.
Report cause and proof. Make no fix unless task authorizes implementation.