JuliusBrussee
Grades are signals, not a certification. Always review a skill yourself before use.
Is this you?
These skills are attributed to JuliusBrussee on SkillRepo. If that’s your GitHub account, sign in with GitHub to move them into your account — they’re already here, and it never touches your GitHub repos.
Sign up free to publish unlimited skills, graded and attributed to you.
Get StartedSearching by meaning· free account to run
20 skills found
When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or… more
Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /cavema… more
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
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.
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 LL… more
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where L… more
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 i… more
Quick-reference card for caveman modes, skills and commands. Trigger: /caveman-help or "caveman help".
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 a… more
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman opt… more
Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".
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 obse… more
Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report. Trigger: /ca… more
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hy… more
Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop… more
Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preserv… more
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matte… more
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proo… more