Repository
JuliusBrussee/caveman agent skills
- skills
- 18
- GitHub stars
- 111k
GitHub description: “🪨 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.”
- Stars
- 110,632 (6,405 forks)
- Licence
- Apache-2.0
- Last push
- Oct 2026
- Created
- Apr 2026
- Homepage
- docs.caveman.so/docs/quickstart
- ai
- anthropic
- caveman
- claude
- claude-code
- llm
- meme
- prompt-engineering
- skill
- tokens
Install all skills
npx skills add JuliusBrussee/cavemanAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in JuliusBrussee/caveman, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Finds every LLM workflow in a repository, proposes a labeling table and, once you agree, wires labels so Caveman Cloud groups spend per workflow. | JuliusBrussee/ | 111k | 1 repo | ~1.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 2 | Read-only review of Caveman Cloud data to explain where LLM spend goes: cost, score, workflows, traces, latency, errors, routing and verified savings. | JuliusBrussee/ | 111k | 1 repo | ~927 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 3 | Reads the state and results of Caveman Cloud experiments and reports one recommendation or a block, without changing an experiment's lifecycle itself. | JuliusBrussee/ | 111k | 1 repo | ~975 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 4 | Turns a Caveman report-only optimization observation into one minimal code change and a paired baseline evaluation, after the operator picks which to pursue. | JuliusBrussee/ | 111k | 1 repo | ~1.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 5 | Routes every LLM call in a repository through the Caveman Cloud gateway in record mode, so requests and costs are measured without changing behavior. | JuliusBrussee/ | 111k | 1 repo | ~2.6k | Automated safety check: Warn | Apache-2.0 | yesterday |
| 6 | Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help". | JuliusBrussee/ | 111k | — | ~690 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 7 | Switches the agent to a terse reply style that gives the answer first, drops filler, and keeps every technical fact, command and number exact. | JuliusBrussee/ | 111k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 8 | Acts on a Caveman learn report: reviews ranked token sinks, applies cost-lowering edits one at a time with your consent, and reports what each fix returned. | JuliusBrussee/ | 111k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 9 | Switches the agent's replies to terse Classical Chinese (wenyan) for the whole session, keeping code, commands, paths and numbers in their original form. | JuliusBrussee/ | 111k | 1 repo | ~612 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 10 | 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. | JuliusBrussee/ | 111k | — | ~491 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 11 | Cuts the agent's replies down to bare fragments for the whole session, one word where one will do and no repeated facts, while code and error strings stay exact. | JuliusBrussee/ | 111k | 1 repo | ~629 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 12 | 12.Lean Build Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an… | JuliusBrussee/ | 111k | 1 repo | ~273 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 13 | A read-only explorer for cold-start orientation or failed searches that replies with nothing but file path and line range citations, keeping its reads out of main context. | JuliusBrussee/ | 111k | 1 repo | ~492 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 14 | Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing… | JuliusBrussee/ | 111k | 1 repo | ~172 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 15 | Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback… | JuliusBrussee/ | 111k | 1 repo | ~196 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 16 | Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket… | JuliusBrussee/ | 111k | 1 repo | ~177 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 17 | Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant… | JuliusBrussee/ | 111k | 1 repo | ~166 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 18 | Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and… | JuliusBrussee/ | 111k | 1 repo | ~176 | Automated safety check: Pass | Apache-2.0 | yesterday |
Questions, answered from the data.
What is the best skill in JuliusBrussee/caveman?
Caveman Workflow Labeler from JuliusBrussee/caveman ranks first of the 18 skills in JuliusBrussee/caveman listed here, with the highest score: its repository has 111k GitHub stars, 1 other GitHub owner carry a copy, its SKILL.md loads about 1.3k tokens and it passes the automated safety check with no findings. Next come Caveman Evidence Review and Caveman Experiment Manager.
Are the skills in JuliusBrussee/caveman official?
None yet. All 18 skills in JuliusBrussee/caveman listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from JuliusBrussee/caveman?
Run npx skills add JuliusBrussee/caveman in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.