improve-skill SKILL.md skillA
improve-skill from mgiovani/cc-arsenal is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add mgiovani/cc-arsenal/improve-skill@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- mgiovani/cc-arsenal
- Path
skills/improve-skill/SKILL.md- Versions recorded
- 5
- Latest version
- v1.0.0, committed Oct 5, 2026
- First version recorded
- Jul 19, 2026
- Size
- 11,638 bytes
- Repository stars
- 8
- License
- MIT
Improve one or more EXISTING agent skills to the current authoring standard, with measured before/after evidence instead of a trust-me rewrite. Snapshots the current version to an immutable baseline, rewrites description/body/references against the rubric, authors or upgrades evals/evals.json and trigger-eval.json in the same pass, then benchmarks the rewrite against the frozen baseline with deterministic grading before calling it done. Use when the user wants to improve, audit, refresh…
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
# Improve Skill Take a skill that already exists and bring it up to the current authoring standard: with a frozen baseline and a measured comparison, not just a confident rewrite. Every claim of "better" in your final report must trace to a validator run or a grading result you actually produced this session. ## Ground rules The snapshot is write-once. Once `skill-snapshot/` exists for a skill, it is read-only for the rest of the run: every later step (rewrite, iteration, feedback pass) reads it for comparison and never writes to it. If a later step wants to "fix" the baseline to make a comparison look better, that is overfitting to the eval, not improving the skill, so refuse and explain why. Eval prompts and assertions are frozen the same way, so never edit one just to make a failing run pass. If a rewritten skill fails an assertion, fix the skill (SKILL.md, references, description). If the assertion itself was wrong when it was written, say so explicitly and get the user's sign-off before changing it: silently loosening an assertion after seeing it fail is the one move that makes every later benchmark meaningless. …
Read the whole file at its exact version.
How to install
mdr add mgiovani/cc-arsenal/improve-skill@sha256:7aa0e3f0bc2506efThe line at the top of this page pins the label v1.0.0, 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.
[](https://markdownregistry.com/a/art_wozoxzr67jpdrnji)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 19, 2026 and Oct 5, 2026, about one every 19 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-10-05 | b620662 | 11,638 B | A | view · diff |
| v1.0.0 | 2026-09-25 | ca015cc | 10,448 B | A | view · diff |
| v1.0.0 | 2026-09-16 | 0d6e629 | 10,252 B | A | view · diff |
| v1.0.0 | 2026-07-27 | fa2e9cf | 10,151 B | A | view · diff |
| v1.0.0 | 2026-07-19 | 4ee8666 | 10,241 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 (11638 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
mgiovani/cc-arsenal · 8 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_wozoxzr67jpdrnji GET https://markdownregistry.com/api/v1/resolve?ref=mgiovani/cc-arsenal/improve-skill GET https://markdownregistry.com/api/v1/blob/7aa0e3f0bc2506ef6ef206bef91dd53f4ccc2f032a1f16b3ac1b66698e7a6848
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 mgiovani/cc-arsenal
Every file in mgiovani/cc-arsenal