skill-improver SKILL.md skillA

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

Install it, pinned
mdr add air-gapped/skills/skill-improver@git:20261019.f156b14

Pins git:20261019.f156b14 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
air-gapped/skills
Path
.claude/skills/skill-improver/SKILL.md
Versions recorded
17
Latest version
git:20261019.f156b14, committed Oct 19, 2026
First version recorded
Sep 15, 2026
Size
16,788 bytes
Repository stars
6
License
MIT

Improve, test and maintain Claude Code skills. Modes: `fix` runs a skill's eval cases and fixes what the failed answers show is missing; `improve` hill-climbs a 10-dimension quality rubric with blind scoring and an A/B comparator; `score` rates a skill without editing it; `freshen` verifies the skill's external references online and applies updates; `trigger` measures and tunes how reliably the description fires; `outcome` runs eval cases with and without the skill; `floor` measures what a…

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

# Skill Improver

`/skill-improver <mode> <target> [--opts]`. `<target>` is a skill name, a
SKILL.md path, `--all`, or a glob (`'vllm-*'`). No mode → **Auto**. No target
(except `ages`, `batch`) → ask.

| Mode | Does | Read first |
|---|---|---|
| Auto | Decides which modes the skill needs, runs them | §Auto |
| `fix` | Runs the skill's eval cases, fixes what the failed answers show is missing | §Fix |
| `improve` | Keep/discard loop on the 10-dimension rubric | `references/improve-loop.md`, `references/quality-rubric.md` |
| `score` | Rubric score, no edits | §Score |
| `freshen` | Verifies every `sources.md` row online, applies verified updates | `references/freshen-patterns.md` |
| `trigger` | Measures and tunes the description's trigger rate | `references/trigger-patterns.md` |
| `outcome` | Runs the skill's eval cases with vs without it (`claude plugin eval`) | §Outcome |
| `floor` | Measures what a bare model already knows about the subject | `references/floor-patterns.md` |
| `ages` | Fleet table of verification age vs last change | §Ages |
| `batch` | Runs `improve`, `freshen` or `trigger` over many skills | §Batch |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add air-gapped/skills/skill-improver@sha256:80731b5c0176594d

The line at the top of this page pins the label git:20261019.f156b14, 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_ewpyd2zw6oxmva2m.svg)](https://markdownregistry.com/a/art_ewpyd2zw6oxmva2m)

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

Versions

The registry has recorded 17 versions of this file, between Sep 15, 2026 and Oct 19, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
git:20261019.f156b14 latest2026-10-19 f156b14 16,788 BA view · diff
git:20261003.22f63012026-10-03 22f6301 15,882 BA view · diff
git:20261003.242c8a92026-10-03 242c8a9 15,856 BA view · diff
git:20261003.0a1338c2026-10-03 0a1338c 15,650 BA view · diff
git:20261003.68f13fc2026-10-03 68f13fc 16,572 BA view · diff
git:20261003.563af9a2026-10-03 563af9a 15,166 BA view · diff
git:20260923.6de680e2026-09-23 6de680e 30,980 BA view · diff
git:20260923.d0700962026-09-23 d070096 30,085 BA view · diff
git:20260923.5ccd91a2026-09-23 5ccd91a 29,882 BA view · diff
git:20260923.92cbfa02026-09-23 92cbfa0 29,832 BA view · diff
git:20260923.a6119d32026-09-23 a6119d3 30,133 BA view · diff
git:20260922.5e8f5092026-09-22 5e8f509 31,402 BA view · diff
git:20260915.2a6f5992026-09-15 2a6f599 31,402 BA view · diff
git:20260915.42df51f2026-09-15 42df51f 30,975 BA view · diff
git:20260915.3c235fb2026-09-15 3c235fb 30,778 BA view · diff
git:20260915.09d57542026-09-15 09d5754 30,779 BA view · diff
git:20260915.d8e1b322026-09-15 d8e1b32 38,696 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 (16788 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

air-gapped/skills · 6 stars · license MIT · pushed 2026-11-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ewpyd2zw6oxmva2m
GET https://markdownregistry.com/api/v1/resolve?ref=air-gapped/skills/skill-improver
GET https://markdownregistry.com/api/v1/blob/80731b5c0176594d113f953392a356cd2bf565357c96d43f9c428fa165fac518

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 air-gapped/skills

aiperf SKILL.md skill
air-gapped/skills · .claude/skills/aiperf/SKILL.md · NVIDIA AIPerf — vendor-neutral generative-AI inference benchmarking (genai-perf successor). `aiperf profile`…
git:20261019.9eca78f · audit A · 6 stars
airgap-vetting SKILL.md skill
air-gapped/skills · .claude/skills/airgap-vetting/SKILL.md · Vet an open-source product for air-gap readiness BEFORE adoption. Answers eight questions — telemetry…
git:20261027.4b5fb58 · audit A · 6 stars
analytical-troubleshooting SKILL.md skill
air-gapped/skills · .claude/skills/analytical-troubleshooting/SKILL.md · Structured live troubleshooting for deviation problems: something worked (or should work) and now doesn't, and the…
git:20261019.819b406 · audit A · 6 stars
ansible-idrac-9-10 SKILL.md skill
air-gapped/skills · .claude/skills/ansible-idrac-9-10/SKILL.md · Run and debug `dellemc.openmanage` Ansible playbooks against Dell PowerEdge **iDRAC 9** (14G–16G) and **iDRAC 10** (17G…
git:20261019.b3bbe99 · audit A · 6 stars
argo-cd-apps SKILL.md skill
air-gapped/skills · .claude/skills/argo-cd-apps/SKILL.md · Author and maintain Argo CD `Application` and `ApplicationSet` manifests as a GitOps consumer (publisher), targeting…
git:20261027.31fbcc7 · audit A · 6 stars
autoresearch SKILL.md skill
air-gapped/skills · .claude/skills/autoresearch/SKILL.md · Autonomous experiment loops that hill-climb a measurable metric — apply one change, measure, keep it only if the number…
git:20261027.75d87c7 · audit A · 6 stars
baml-expert SKILL.md skill
air-gapped/skills · .claude/skills/baml-expert/SKILL.md · BAML (Boundary ML) expert for projects defining LLM calls as typed functions in .baml files with a generated Python…
git:20261027.db2bb25 · audit A · 6 stars
ceph-performance SKILL.md skill
air-gapped/skills · .claude/skills/ceph-performance/SKILL.md · Tune and benchmark a healthy Ceph cluster, with Rook-on-Kubernetes specifics: mClock profiles and the NVMe…
git:20261027.28d2580 · audit A · 6 stars
ceph-s3 SKILL.md skill
air-gapped/skills · .claude/skills/ceph-s3/SKILL.md · Run Ceph RGW as an S3 endpoint under Rook (CephObjectStore, CephObjectStoreUser, ObjectBucketClaim, COSI…
git:20261027.61472c6 · audit A · 6 stars
ceph-troubleshooting SKILL.md skill
air-gapped/skills · .claude/skills/ceph-troubleshooting/SKILL.md · Diagnose and recover an unhealthy Ceph cluster, with Rook-on-Kubernetes specifics: slow or stuck recovery/backfill…
git:20261027.0ad34cc · audit A · 6 stars
chat-completions-api SKILL.md skill
air-gapped/skills · .claude/skills/chat-completions-api/SKILL.md · Reference for the OpenAI Chat Completions API (/v1/chat/completions) and legacy /v1/completions as the lingua-franca…
git:20261027.42f4242 · audit A · 6 stars
claude-code-ci-harness SKILL.md skill
air-gapped/skills · .claude/skills/claude-code-ci-harness/SKILL.md · Run Claude Code headlessly as an isolated CI harness against any Anthropic Messages-compatible endpoint (local engine…
git:20261019.25dcc92 · audit A · 6 stars

Every file in air-gapped/skills

Other files named skill-improver

skill-improver SKILL.md skill
gentleman-programming/gentle-ai · internal/assets/skills/skill-improver/SKILL.md · Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.
v1.0 · audit A · 8,364 stars
skill-improver SKILL.md skill
trailofbits/skills · plugins/code-improver/skills/skill-improver/SKILL.md · Runs an autonomous review-and-fix improvement loop over a Claude Code skill until a review comes back clean, with a…
git:20261027.bf23bfb · audit A · 8,043 stars

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