prompt-tuning skillA
prompt-tuning is agent-read markdown (skill) from hiroro-work/claude-plugins: Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) by having a bias-free executor run them and evaluating two-sidedly (executor self-report + instruction-side metrics) until improvements plateau. Use after creating or revising a prompt or skill..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Empirical Prompt Tuning The author of a prompt cannot judge its quality. The clearer the writer thinks something is, the more likely another agent will stumble on it. The core of this skill is to **have a bias-free executor actually run the instruction, evaluate it two-sidedly, and iterate**. Do not stop until improvements plateau. ## When to use - Right after creating or substantially revising a skill / slash command / task prompt - When an agent does not behave as expected and you want to attribute the cause to ambiguity on the instruction side - When hardening high-importance instructions (frequently used skills, automation-core prompts) When not to use: - One-off throwaway prompts (evaluation cost does not pay off) - When the goal is not to improve success rate but merely to reflect the writer's subjective preferences ## Workflow 0. **Iteration 0 — description / body consistency check** (static, no dispatch needed) …
Read the whole file at its exact version.
How to install
mdr add hiroro-work/claude-plugins/prompt-tuning@git:20260818.9421b02mdr add hiroro-work/claude-plugins/prompt-tuning@sha256:60035a42092b9556Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_ftrjny64mwylxbnl)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260818.9421b02 latest | 2026-08-18 | 9421b02 | 40,716 B | A | view · diff |
| git:20260522.cdbbe7c | 2026-05-22 | cdbbe7c | 45,220 B | A | view · diff |
| git:20260515.666e188 | 2026-05-15 | 666e188 | 42,271 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (40716 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
hiroro-work/claude-plugins · 48 stars · license none · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ftrjny64mwylxbnl GET https://markdownregistry.com/api/v1/resolve?ref=hiroro-work/claude-plugins/prompt-tuning GET https://markdownregistry.com/api/v1/blob/60035a42092b9556ac27e072820bc0e6b0c7e8e220b8bc6b5fb74928a8c321ae
Your agent 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.