Caveman Discover skill: what it does and how to install it
Labels LLM call sites by human-named workflow for Caveman Cloud, proposes the mapping for approval, applies minimal changes, and verifies a path.
Summary generated from the skill's documentation.
Install
$ npx skills add JuliusBrussee/caveman --skill caveman-discoverRun it in a terminal. If your agent is already running, start a new session so it picks the skill up.
About this skill
What it does. Inventories HTTP handlers, jobs, CLI scripts and evals from entry points, then proposes a workflow table before adding labels at callers using SDK options, headers or wrapper flags. It verifies a labelled path and reports wired, unlabelled and review cases.
When to use it. Use for breaking Caveman Cloud LLM spend down by workflow. It does not edit traffic that bypasses the Caveman gateway, and telemetry observations remain review-only.
History
Repo stars
109kAbout +8k since 9 Jul 2026
Before 1 Oct 2026 the curve is estimated from public event data.
Stars are counted for the whole repository, which holds 20 skills.
Show as a table
| Date | Repo stars |
|---|---|
| 1 Oct 2026 | 108,672 |
| 24 Sept 2026 (estimated) | 108,359 |
| 17 Sept 2026 (estimated) | 107,939 |
| 10 Sept 2026 (estimated) | 105,130 |
| 3 Sept 2026 (estimated) | 101,650 |
| 27 Aug 2026 (estimated) | 101,470 |
| 20 Aug 2026 (estimated) | 101,320 |
| 13 Aug 2026 (estimated) | 101,310 |
| 6 Aug 2026 (estimated) | 101,120 |
| 30 Jul 2026 (estimated) | 101,070 |
| 23 Jul 2026 (estimated) | 100,990 |
| 16 Jul 2026 (estimated) | 100,920 |
| 9 Jul 2026 (estimated) | 100,711 |
Installs
77.5k
Tracking since . A chart appears once there are 7 days of data.
Installs via skills.sh
Similar skills
- Caveman ExploreExplores a repository read-only to locate code across files and returns path and line citations.
- SuperpowersA full software development workflow for coding agents, built from composable skills for brainstorming, planning, TDD, debugging and review.
- Systematic DebuggingMakes the agent find the root cause of a bug, test failure or unexpected behaviour before it proposes a fix.