JuliusBrussee@Caveman

JuliusBrussee@Caveman from gabrielmoreira/agent-skills-mirror.

by @gabrielmoreira 18 skills 2 authors

Skills in this plugin

18
  1. Cavecrew · gabrielmoreira bundle
    When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.
    17 repo stars
  2. Migration · juliusbrussee bundle
    Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.
    3 installs
  3. Lean Build · juliusbrussee bundle
    Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.
    1 install
  4. Caveman Help · gabrielmoreira bundle
    Quick-reference card for caveman modes, skills and commands. Trigger: /caveman-help or "caveman help".
    17 repo stars
  5. Caveman Learn · juliusbrussee bundle
    Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.
    3 installs
  6. Caveman Setup · juliusbrussee
    Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.
    2 installs
  7. Safe Refactor · juliusbrussee bundle
    Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
    3 installs
  8. Caveman Commit · gabrielmoreira bundle
    Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
    17 repo stars
  9. Caveman Manage · juliusbrussee
    Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.
    2 installs
  10. Caveman Review · gabrielmoreira bundle
    Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".
    17 repo stars
  11. Surgical Patch · juliusbrussee bundle
    Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.
    1 install
  12. Caveman Explore · juliusbrussee bundle
    Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.
    3 installs
  13. Verify And Stop · juliusbrussee bundle
    Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
    3 installs
  14. Caveman Compress · gabrielmoreira bundle
    Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.
    17 repo stars
  15. Caveman Discover · juliusbrussee
    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.
    2 installs
  16. Caveman Optimize · juliusbrussee
    Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs explicit approval.
    2 installs
  17. Investigate First · juliusbrussee bundle
    Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
    5 installs
  18. Caveman Evidence Review · juliusbrussee
    Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.
    2 installs