Menu
SkillsMP a collecté 24 skills depuis JuliusBrussee/caveman. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 24 skills collectés sur 24.
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Quick-reference card for caveman modes, skills and commands. Trigger: /caveman-help or "caveman help".
Langue du texte source : anglais
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…
Langue du texte source : anglais
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".
Langue du texte source : anglais
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.
Langue du texte source : anglais
Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".
Langue du texte source : anglais
Show real token usage and estimated savings for the current session, read from the session log. Trigger: /caveman-stats.
Langue du texte source : anglais
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.
Langue du texte source : anglais
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
Langue du texte source : anglais
Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.
Langue du texte source : anglais
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
Langue du texte source : anglais
Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.
Langue du texte source : anglais