improve-skill SKILL.md skillA

improve-skill from av/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add av/skills/improve-skill@git:20260813.b71baeb

Pins git:20260813.b71baeb in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
av/skills
Path
improve-skill/SKILL.md
Versions recorded
5
Latest version
git:20260813.b71baeb, committed Aug 13, 2026
First version recorded
Aug 13, 2026
Size
16,459 bytes
Repository stars
24
License
MIT

Improve an existing agent SKILL.md through one gated cycle: select the target (default this skill), snapshot the committed baseline, diagnose against skill-design-principles plus four rubric dimensions, apply exactly one focused change, and ship only if a different agent than the author PASSes with quoted evidence. Use when the user says "improve this skill", "improve-skill", "iterate on SKILL.md", or "apply skill-design-principles to a skill". Do not use for code slop over a duration…

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

One cycle, one change, one independent verdict. You do not decide the skill got better.

## Role

You are the **orchestrator**. You:

1. Resolve the target `SKILL.md`.
2. Snapshot the baseline off-tree before any edit.
3. Diagnose against the lens below and pick exactly one hole.
4. Apply that one change, or dispatch an author who does only that.
5. Dispatch a **different** agent as judge. Enforce the verdict.

You do **not**: score your own (or the author's) change; skip the gate; rewrite the skill; hand-edit generated README catalog files; create a skill from scratch.

```
NO INDEPENDENT PASS → NO COMMIT. FAIL → RESTORE BASELINE.
```

If you cannot dispatch a different agent, stop. Leave the tree at baseline. Do not self-score.

## Inputs

| Input | Required | Default |
|---|---|---|
| Target skill | no | The `SKILL.md` next to this file (`improve-skill`) |
| Commit prefix | no | none; the dimension still goes in the subject |

If the user names a path that is not an existing `*/SKILL.md`, stop and say so. Do not ask them what to change.

Out of scope: README, cheatsheet, harness files, new skills, application code, duration-boxed work.

## Working files
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add av/skills/improve-skill@sha256:0cf56396db4bb961

The line at the top of this page pins the label git:20260813.b71baeb, 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 badge

[![mdr](https://markdownregistry.com/badge/art_vyeljeq7otwkhqc4.svg)](https://markdownregistry.com/a/art_vyeljeq7otwkhqc4)

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

Versions

The registry has recorded 5 versions of this file, all committed on Aug 13, 2026.

versioncommittedcommitsizeaudit
git:20260813.b71baeb latest2026-08-13 b71baeb 16,459 BA view · diff
git:20260813.dc0f6b12026-08-13 dc0f6b1 15,272 BA view · diff
git:20260813.2dc022f2026-08-13 2dc022f 14,020 BA view · diff
git:20260813.09d512c2026-08-13 09d512c 13,754 BA view · diff
git:20260813.25f7fa22026-08-13 25f7fa2 13,441 BA 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 (16459 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

av/skills · 24 stars · license MIT · pushed 2026-10-21 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_vyeljeq7otwkhqc4
GET https://markdownregistry.com/api/v1/resolve?ref=av/skills/improve-skill
GET https://markdownregistry.com/api/v1/blob/0cf56396db4bb961af4966d0b1342fedc892694c6ed3d4acdba6441cea839170

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 av/skills

agent-integration-testing SKILL.md skill
av/skills · agent-integration-testing/SKILL.md · Use when the user requests integration testing, feature validation, or test plan execution
git:20260330.d629481 · audit A · 24 stars
anneal SKILL.md skill
av/skills · anneal/SKILL.md · Use when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error…
git:20260601.cc3497a · audit A · 24 stars
article-factory SKILL.md skill
av/skills · article-factory/SKILL.md · Produce a researched long-form article from a topic prompt via an orchestrated pipeline - research agent (first-person…
git:20260730.ada63fd · audit A · 24 stars
autoresearch SKILL.md skill
av/skills · autoresearch/SKILL.md · Runs autonomous keep/discard experiments on a codebase to optimize a single metric for a fixed duration, in the style…
git:20260923.7fb0398 · audit A · 24 stars
boost-modules SKILL.md skill
av/skills · boost-modules/SKILL.md · Create custom modules for [Harbor Boost](https://github.com/av/harbor/tree/main/boost), an optimizing LLM proxy. Use…
git:20260123.eeaa581 · audit B · 24 stars
bugbash SKILL.md skill
av/skills · bugbash/SKILL.md · Systematically explore and test any software project (CLI, API, Backend, Library, etc.) to find bugs, usability issues…
git:20260402.6abcf0b · audit A · 24 stars
bughunt SKILL.md skill
av/skills · bughunt/SKILL.md · Fully autonomous bug hunting pipeline — discover bugs in a scoped area using parallel subagents, independently triage…
git:20260612.7c5d841 · audit A · 24 stars
catalog-deslop SKILL.md skill
av/skills · catalog-deslop/SKILL.md · Catalog-then-fix slop removal on an existing prose draft. Parallel catalog subagents inventory four slop categories…
git:20260730.ada63fd · audit A · 24 stars
discipline SKILL.md skill
av/skills · discipline/SKILL.md · Bulletproof agent operating protocol. 15 failure-prevention rules distilled from 120+ real sessions and 10 agent…
git:20260509.2572fa1 · audit A · 24 stars
factual-communication SKILL.md skill
av/skills · factual-communication/SKILL.md · Restate content as a flat list of atomic facts in the style of av/facts fact sheets. Use when the user says "just…
git:20260825.4dce9e4 · audit A · 24 stars
ideate SKILL.md skill
av/skills · ideate/SKILL.md · Timeboxed ideation on a topic where lens-driven proposers generate structurally different ideas, blind critics cull…
git:20261011.7d38584 · audit A · 24 stars
make-video SKILL.md skill
av/skills · make-video/SKILL.md · Build a HyperFrames video composition from a brief/script autonomously. Uses separated builder and critic subagents —…
git:20260608.856dd1c · audit A · 24 stars

Every file in av/skills

Other files named improve-skill

improve-skill SKILL.md skill
namedtoaster/the-last-mile · skills/improve-skill/SKILL.md · Fix a Last Mile skill that did the wrong thing, from inside the project where it went wrong. Decides whether the lesson…
git:20261012.0a65810 · audit A · 14 stars
improve-skill SKILL.md skill
tomzx/agents · skills/improve-skill/SKILL.md · Inspect a single skill in the library, reason about high-value low-risk improvements, and apply them directly. Used by…
git:20261007.b35fc4b · audit A · 12 stars
improve-skill SKILL.md skill
mgiovani/cc-arsenal · skills/improve-skill/SKILL.md · Improve one or more EXISTING agent skills to the current authoring standard, with measured before/after evidence…
v1.0.0 · audit A · 8 stars
improve-skill SKILL.md skill
devskale/skale-skills · deprecated/improve-skill/SKILL.md · Analyze coding agent session transcripts to improve existing skills or create new ones. Use when asked to improve a…
git:20261006.3723cb2 · audit A · 3 stars

Browse by kind, by grade A, or by owner.