prompt-tuner SKILL.md skillA

prompt-tuner from wildcard/caro is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add wildcard/caro/prompt-tuner@git:20260112.4276d01

Pins git:20260112.4276d01 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: wildcard/caro
Path: .claude/skills/prompt-tuner/SKILL.md
Versions recorded: 1
Latest version: git:20260112.4276d01, committed Jan 12, 2026
Size: 3,022 bytes
Repository stars: 40
License: AGPL-3.0

Improve embedded LLM system prompt based on evaluation test failures.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Prompt Tuner

Iteratively improve the embedded backend's system prompt to increase command generation accuracy.

## When to Use

- "tune the prompt"
- "improve embedded accuracy"
- "fix LLM command generation"
- "run prompt tuning cycle"
- After evaluation tests show low accuracy

## Workflow

### Phase 1: Baseline Measurement

Run evaluation tests with embedded backend:

```bash
./target/release/caro test --backend embedded
```

Record:
- Overall accuracy percentage
- Category breakdown (Website Claim, Natural Variant, Edge Case)
- List of failed test cases with expected vs actual commands

### Phase 2: Failure Analysis

For each failed test case, identify the pattern:

| Pattern | Example | Fix |
|---------|---------|-----|
| Wrong path | `find /` instead of `find .` | Add rule: "ALWAYS use current directory '.'" |
| GNU flags | `--max-depth` on macOS | Add rule: "Use BSD-compatible flags" |
| Missing filters | No `-name "*.py"` | Add rule: "Include ALL relevant filters" |
| Time semantics | `-mtime -1` vs `-mtime 1` | Add clear mtime documentation |
| Quote style | Single vs double quotes | Usually equivalent, low priority |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add wildcard/caro/prompt-tuner@sha256:07435d92bed3f13c

The line at the top of this page pins the label git:20260112.4276d01, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_h3kpbdyfu33onxzh.svg)](https://markdownregistry.com/a/art_h3kpbdyfu33onxzh)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jan 12, 2026.

version	committed	commit	size	audit
git:20260112.4276d01 latest	2026-01-12	4276d01	3,022 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (3022 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

wildcard/caro · 40 stars · license AGPL-3.0 · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_h3kpbdyfu33onxzh
GET https://markdownregistry.com/api/v1/resolve?ref=wildcard/caro/prompt-tuner
GET https://markdownregistry.com/api/v1/blob/07435d92bed3f13c1654ba251f176a659069a021a521f770a78556a9f8c9c83b

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from wildcard/caro

spec-kitty-git-workflow SKILL.md skill

wildcard/caro · .agents/skills/spec-kitty-git-workflow/SKILL.md · Understand how Spec Kitty manages git: what git operations Python handles automatically, what agents must do manually…