skill-improve SKILL.md skillA

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

Install it, pinned

mdr add summerengine/summer/skill-improve@git:20261010.4ade947

Pins git:20261010.4ade947 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: summerengine/summer
Path: library/skills/skill-improve/SKILL.md
Versions recorded: 4
Latest version: git:20261010.4ade947, committed Oct 10, 2026
First version recorded: Sep 1, 2026
Size: 2,952 bytes
Repository stars: 86
License: MIT

Upgrade an underperforming Summer skill — run it against a behavioral spec with and without changes via a parallel-eval harness; ship the winner.

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-improve — Iterate on a Skill With Eval Harness

Adapted from the `skill-creator` skill in `anthropics/skills`. Use when a skill's behavioral spec fails assertions or the skill produces low-quality output.

## When to use this vs. `/skill-test`

- `/skill-test spec` reasons over text. Cheap and fast, but lossy.
- `/skill-improve` runs the skill in parallel subagents, with and without the proposed changes. Slower and more expensive, but accurate.

Run this when `/skill-test spec` flags issues you can't fix by reading the skill alone.

## Steps

### 1. Pick the skill + the spec

Ask the user:
- **Skill slug.** Resolves to `library/skills/<slug>/SKILL.md`.
- **Test cases to focus on.** Default: all `## Case` blocks in `evals/skills/specs/<slug>.md`.

### 2. Establish a baseline

For each Case:

1. Spawn a subagent (`Task` tool, `general-purpose`) with the **current** skill body in context.
2. Give it the Case's Input + Fixture.
3. Capture the tool calls it makes and the diff it produces.
4. Score against the Case's Assertions.

Save outputs to `tests/runs/<skill-name>/baseline/case-<N>/`.

### 3. Propose changes
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add summerengine/summer/skill-improve@sha256:fab36fb2421a3af5

The line at the top of this page pins the label git:20261010.4ade947, 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](https://markdownregistry.com/badge/art_uto3uf7vvj27r56m.svg)](https://markdownregistry.com/a/art_uto3uf7vvj27r56m)

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

Versions

The registry has recorded 4 versions of this file, between Sep 1, 2026 and Oct 10, 2026, about one every 13 days.

version	committed	commit	size	audit
git:20261010.4ade947 latest	2026-10-10	4ade947	2,952 B	A	view · diff
git:20260911.b4df358	2026-09-11	b4df358	2,883 B	A	view · diff
git:20260902.548800b	2026-09-02	548800b	3,047 B	A	view · diff
git:20260901.7eb75a2	2026-09-01	7eb75a2	3,047 B	A	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 (2952 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

summerengine/summer · 86 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_uto3uf7vvj27r56m
GET https://markdownregistry.com/api/v1/resolve?ref=summerengine/summer/skill-improve
GET https://markdownregistry.com/api/v1/blob/fab36fb2421a3af5e89788bb17f026b87e2db7d5a1b9b431c42e167b5d961a56

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 summerengine/summer

AGENTS.md AGENTS.md file

summerengine/summer · AGENTS.md

git:20261010.8edeb3f · audit A · 86 stars

3d-lighting SKILL.md skill

summerengine/summer · library/skills/3d-lighting/SKILL.md · Set up 3D scene lighting — DirectionalLight3D vs Omni vs Spot, WorldEnvironment, sky, shadow tuning, ambient — per…