Caveman optimization: operator-chosen candidates with paired evals
Turn Caveman's report-only optimization observations into operator-approved candidates, validated by paired baseline/candidate evaluations
- What
- Turn Caveman's report-only optimization observations into operator-approved candidates, validated by paired baseline/candidate evaluations
- Cost
- Free
- Needs
- review the source repository first — it declares no license, so reuse terms are unconfirmed; a logged-in Caveman CLI session is required (commercial service — check terms)
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
💳 Paid service — Caveman is a commercial optimization service; this skill requires a logged-in Caveman CLI session (check their terms). Curated by Skill Harbor — the Caveman optimization-evaluation workflow: read report-only observations verbatim (never from stale local files), present them unranked for an explicit operator choice, design one minimal candidate change with a paired baseline/candidate evaluation on identical inputs, apply only the approved candidate, and report observations — never dollar savings. Its hard rules are the best part: never invent cost figures, never turn aggregates into callsite claims, treat retired profile ids as history only, and revert anything quality-regressing. By @juliusbrussee, listed here with credit to its creator. Honest caveats: NOASSERTION — the source repo declares no license, so reuse terms are unconfirmed: short fiche, link only; deliberately conservative — it stops instead of acting whenever a fixture, quality check, or measurement method is missing; meaningless without a Caveman account and live observations. Discovered via skills.sh. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Caveman optimization is a free Muse skill that turns Caveman's report-only optimization observations into operator-approved candidates, validated by paired baseline and candidate evaluations. Note that Caveman is a paid commercial service, and this skill requires a logged-in Caveman CLI session, so check their terms before use.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 2e08b91Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: review the source repository first — it declares no license, so reuse terms are unconfirmed; a logged-in Caveman CLI session is required (commercial service — check terms) Open the source of "Caveman optimization: operator-chosen candidates with paired evals" for me: Repository: https://raw.githubusercontent.com/juliusbrussee/caveman/2e08b9177c07bb7249a8a2d1a6758e5db281d002/skills/caveman-optimize/SKILL.md Pinned version: install the code at commit 2e08b9177c07bb7249a8a2d1a6758e5db281d002 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file from the repository into a temporary folder 2. Read it as a guide only — it carries no declared license, so don't copy its text into other files. 3. Report what it covers and how to use it. GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it. Rules: don't touch anything outside the temp folder. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 2e08b91 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.