eugenelim/agent-ready-repo · packs/agent-skill-engineering/.apm/skills/review-or-optimize-agent-skill/SKILL.md

review-or-optimize-agent-skill skillA

review-or-optimize-agent-skill is agent-read markdown (skill) from eugenelim/agent-ready-repo: Use when the user asks to review, audit, tune, or optimize an agent skill or SKILL.md for trigger precision, progressive disclosure, portability, deterministic mechanics, authority, or security. Select it first and resolve the target inside the workflow, including when the request points at "this skill" with nothing attached or names no file; it stays read-only until you authorize a change. Optimization requires an observed failure or measured baseline. Do not use to frame, create, or update a s.

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.

How to install

Latest version
mdr add eugenelim/agent-ready-repo/review-or-optimize-agent-skill@git:20260831.597011c
Exact content
mdr add eugenelim/agent-ready-repo/review-or-optimize-agent-skill@sha256:e2f08f07faa619f5

Pin 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_4pgim2qfyietmven.svg)](https://markdownregistry.com/a/art_4pgim2qfyietmven)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260831.597011c latest2026-08-31 597011c 4,143 BA view · diff
git:20260830.924b03a2026-08-30 924b03a 4,050 BA view · diff
git:20260829.1edfadd2026-08-29 1edfadd 3,974 BA view · diff
git:20260829.c7ed3f92026-08-29 c7ed3f9 6,550 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (4143 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

eugenelim/agent-ready-repo · 22 stars · license Apache-2.0 · pushed 2026-09-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4pgim2qfyietmven
GET https://markdownregistry.com/api/v1/resolve?ref=eugenelim/agent-ready-repo/review-or-optimize-agent-skill
GET https://markdownregistry.com/api/v1/blob/e2f08f07faa619f528662c8a7d40530ea49b9053b2b98d58c177c54356393818

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.