SkillAgentSearch skills...
Home

JuliusBrussee

21 skills across 20 repos2.2M repo starsGitHub

JuliusBrussee / caveman-setup

107.7k

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.

📄 SKILL.mduniversal
skill
99
Updated 1d ago

JuliusBrussee / caveman-evidence-review

107.7k

Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings

📄 SKILL.mduniversal
skillreview
93
Updated 1d ago

JuliusBrussee / cavecrew

107.7k

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.

📄 SKILL.mduniversal
skillreview
92
Updated 1d ago

JuliusBrussee / caveman-discover

107.7k

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.

📄 SKILL.mduniversal
skill
92
Updated 1d ago

JuliusBrussee / caveman

107.8k

🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.

🤖 CLAUDE.mdclaude code
claude
91
Updated 14h ago

JuliusBrussee / caveman-manage

107.7k

Inspect Caveman Cloud's experiment lifecycle and block unsafe execution

📄 SKILL.mduniversal
skillapimcp+1
91
Updated 1d ago

JuliusBrussee / caveman

107.7k

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".

📄 SKILL.mduniversal
skill
90
Updated 1d ago

JuliusBrussee / caveman-compress

107.7k

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.

📄 SKILL.mdclaude code
skill
89
Updated 1d ago

JuliusBrussee / caveman-optimize

107.7k

Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation

📄 SKILL.mduniversal
skill
89
Updated 1d ago

JuliusBrussee / caveman-review

107.7k

Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".

📄 SKILL.mduniversal
skillreview
84
Updated 1d ago

JuliusBrussee / caveman-help

107.7k

Quick-reference card for caveman modes, skills and commands. Trigger: /caveman-help or "caveman help".

📄 SKILL.mduniversal
skill
83
Updated 1d ago

JuliusBrussee / caveman-learn

107.7k

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

📄 SKILL.mdclaude code
skillreview
79
Updated 1d ago

JuliusBrussee / caveman-commit

107.7k

Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.

📄 SKILL.mduniversal
skill
78
Updated 1d ago

JuliusBrussee / caveman-explore

107.7k

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.

📄 SKILL.mduniversal
skill
70
Updated 1d ago

JuliusBrussee / caveman-stats

107.7k

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: /caveman-stats.

📄 SKILL.mdclaude code
skill
70
Updated 1d ago

JuliusBrussee / investigate-first

107.7k

Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.

📄 SKILL.mduniversal
skill
68
Updated 1d ago

JuliusBrussee / lean-build

107.7k

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.

📄 SKILL.mduniversal
skill
68
Updated 1d ago

JuliusBrussee / migration

107.7k

Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.

📄 SKILL.mdzed
skillapi
68
Updated 1d ago

JuliusBrussee / safe-refactor

107.7k

Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.

📄 SKILL.mduniversal
skillrest
68
Updated 1d ago

JuliusBrussee / verify-and-stop

107.7k

Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.

📄 SKILL.mduniversal
skill
68
Updated 1d ago

JuliusBrussee / surgical-patch

107.7k

Fix bugs and small behavior changes at the narrowest responsible layer

📄 SKILL.mduniversal
skillrest
65
Updated 1d ago