caveman-discover

A skill in JuliusBrussee/caveman · 121,496 stars on GitHub

Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.

Security grade of this SKILL.md: SAFE · how we grade

How to install caveman-discover

npx skills add JuliusBrussee/caveman --skill caveman-discover -a claude-code

The skills CLI copies this one skill into Claude Code (use -a for another agent). Or read its SKILL.md on GitHub.

What the SKILL.md says

You are labeling this repository's LLM workflows for Caveman Cloud. A workflow is a job the code performs — "answer a support ticket", "build the nightly digest", "run the eval suite" — not a technology. Every gateway request can carry a workflow label; unlabeled traffic all lands in one unlabeled-workflow bucket. Your job: find the workflows, name them well, wire the labels, and verify nothing broke. This changes code, so it goes through the user's normal review: propose the table first, apply after the user agrees. Re-running on an already-labeled repo must change nothing (idempotent). This skill is operator-invoked. An unlabeled-traffic Cave Plan observation is review-only and does not create an advisory file, proposal, or Draft PR. Do not infer that telemetry selected a callsite or authorized an edit.

Other skills in JuliusBrussee/caveman

  • cavecrew When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead…
  • caveman Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief"…
  • caveman-commit Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
  • caveman-compress Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Sends the file…
  • caveman-evidence-review Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Cav…
  • caveman-explore Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the e…
  • caveman-help Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".
  • caveman-learn Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes…
  • caveman-manage Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a C…
  • caveman-optimize Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or e…
  • caveman-review Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the dif…
  • caveman-setup Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or…
  • caveman-stats Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage…
  • investigate-first Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needi…
  • lean-build Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope,…
  • megacave Caveman in Classical Chinese: 文言文 register, far fewer characters, technical terms verbatim. Invoke only with /megacave or /caveman wenyan.…
  • migration Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring…
  • safe-refactor Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket…
  • surgical-patch Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task…
  • ultracave Caveman at maximum compression: fragments, one word when one word is enough, each fact once. Invoke only with /ultracave or /caveman ultra.…