cavecrew
When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff…
@juliusbrusseeInstall SkillDevelopment
Skill
/investigate-first
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
Claude Code
$ npx -y skills add JuliusBrussee/caveman --skill investigate-first --agent claude-code
Codex
$ npx skills add JuliusBrussee/caveman --skill investigate-first -a codex -y
Cursor
$ npx skills add JuliusBrussee/caveman --skill investigate-first -a cursor -y
Gemini CLI
$ npx skills add JuliusBrussee/caveman --skill investigate-first -a gemini-cli -y
GitHub Copilot
$ npx skills add JuliusBrussee/caveman --skill investigate-first -a github-copilot -y
OpenCode
$ npx skills add JuliusBrussee/caveman --skill investigate-first -a opencode -y
Windsurf
$ npx skills add JuliusBrussee/caveman --skill investigate-first -a windsurf -y
SKILL.md
investigate-first.SKILL.mdname: investigate-first description: Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
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.
Stats
119,771
Stars
6,981
Forks
Active
Maintenance
Go
Language
Apache-2.0
License
Last commit
Created
Ships withcaveman
Caveman make your AI agent say less and read less. Code stay exact. Brain still big.
119k22 skills3 agents
Stars on GitHub
Momentum
- stars in total
- 118.7k
Other skills on caveman.
@juliusbrusseeInstall Skillcaveman-compress
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup.…
@juliusbrusseeInstall Skillcaveman-stats
Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's…
@juliusbrusseeInstall Skillcaveman
Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman",…
@juliusbrusseeInstall Skillmegacave
Caveman in Classical Chinese: 文言文 register, far fewer characters, technical terms verbatim. Invoke only with /megacave or…
@juliusbrusseeInstall Skillultracave
Caveman at maximum compression: fragments, one word when one word is enough, each fact once. Invoke only with /ultracave or…
@juliusbrusseeInstall SkillMore skills from other plugins.
Auto-invoked
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
@obraInstall Skillask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
@mattpocockInstall SkillAuto-invoked
Questions about investigate-first.
- Which coding agents can use investigate-first?
- investigate-first installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.