refine-specialization SKILL.md skillA

refine-specialization from wellwelwel/lagune is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add wellwelwel/lagune/refine-specialization@git:20261116.785865e

Pins git:20261116.785865e in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
wellwelwel/lagune
Path
.claude/skills/refine-specialization/SKILL.md
Versions recorded
1
Latest version
git:20261116.785865e, committed Nov 16, 2026
Size
6,924 bytes
Repository stars
221
License
Apache-2.0

Refines one built-in specialization to name every attack, bypass, weak guard, and decoy, and to cut what the model already knows, then proves the new text against the old one in blind simulations of detect and verify.

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

# Refining a built-in specialization

A model already knows how to write secure code. Asked to make something secure, it reaches for the center of generic security advice and returns code that looks safe while leaving old, well-known holes open. Named one by one, each attack, bypass, and weak guard pulls the model to the exact defense instead. A specialization exists to name, not to teach: each named vector is an anchor, and each sentence that explains what the model already knows dilutes the anchors around it.

This skill brings one built-in specialization to that standard and proves the result: the refined text must reach everything the old one reached, in blind runs of the phases that read it. A tie is the goal and a win is a bonus. The secrets specialization is the reference, refined and proven this way.

## User Input

```text
$ARGUMENTS
```

The User Input names one built-in specialization. When it is empty or names none the catalog holds, list the built-ins and ask which. Reply in the language the user writes in, and write the specialization in English.

## Ground rules

- **One specialization per run.** Its tags, categories, and index row stay as they are.
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_dnnrlhnfqwcmujqx/5b9e6c6dcb79c3c450eaa94918da63f2f871026b614d4a12ebed6842e2efbcd3.json

Then /plugin install refine-specialization@markdownregistry-dnnrlhnfqwcmujqx in Claude Code. It installs git:20261116.785865e, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add wellwelwel/lagune/refine-specialization@sha256:5b9e6c6dcb79c3c4

The line at the top of this page pins the label git:20261116.785865e, 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_dnnrlhnfqwcmujqx.svg)](https://markdownregistry.com/a/art_dnnrlhnfqwcmujqx)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in wellwelwel/lagune/refine-specialization since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of refine-specialization from somewhere else? Ask it: where did my refine-specialization come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Nov 16, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261116.785865e latest2026-11-16 785865e 6,924 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

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 (6924 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

wellwelwel/lagune · 221 stars · license Apache-2.0 · pushed 2026-11-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_dnnrlhnfqwcmujqx
GET https://markdownregistry.com/api/v1/resolve?ref=wellwelwel/lagune/refine-specialization
GET https://markdownregistry.com/api/v1/blob/5b9e6c6dcb79c3c450eaa94918da63f2f871026b614d4a12ebed6842e2efbcd3

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 wellwelwel/lagune

architecture SKILL.md skill
wellwelwel/lagune · .claude/skills/architecture/SKILL.md · Authoritative record of Lagune's architecture decisions, covering the three owners, what ships, the engine, the skills…
git:20261116.3d8916d · audit A · 221 stars
blind-review SKILL.md skill
wellwelwel/lagune · .claude/skills/blind-review/SKILL.md · Maps what a branch or the work in progress changes in behavior, before and after, from the code diff alone. Commit…
v1.0.0 · audit A · 221 stars
calibrate SKILL.md skill
wellwelwel/lagune · .claude/skills/calibrate/SKILL.md · Confronts every block, warning, and piece of noise a change raises with the false positives real projects trigger…
git:20261114.380681d · audit A · 221 stars
cdp SKILL.md skill
wellwelwel/lagune · .claude/skills/cdp/SKILL.md · Visual verification of a running page through Chrome's DevTools Protocol, capturing screenshots and measuring the…
v1.0.0 · audit A · 221 stars
dashboard SKILL.md skill
wellwelwel/lagune · .claude/skills/dashboard/SKILL.md · Authoritative reference for the Lagune dashboard, a live view of a project's .lagune/ chain with a locked-down local…
git:20261105.299dc21 · audit A · 221 stars
engineering SKILL.md skill
wellwelwel/lagune · .claude/skills/engineering/SKILL.md · Authoritative engineering reference covering code conventions, performance, comments, TypeScript type rules, testing…
v1.4.0 · audit A · 221 stars
ingest SKILL.md skill
wellwelwel/lagune · .claude/skills/ingest/SKILL.md · Use before reading any .txt file, whatever its name, and whenever a task builds on GitIngest digests. Checks whether a…
v1.0.0 · audit A · 221 stars
mcp-catalog SKILL.md skill
wellwelwel/lagune · .claude/skills/mcp-catalog/SKILL.md · Find, review, and add MCP servers to the reviewed catalog that lagune.ai serves to Lagune Code. Use when asked to look…
git:20261102.0ad572c · audit A · 221 stars
playground SKILL.md skill
wellwelwel/lagune · .claude/skills/playground/SKILL.md · Mounts an agent against this tree's build in an isolated home and a fresh fixture, then measures it, probes it, or adds…
git:20261116.6edc3b1 · audit B · 221 stars
refine SKILL.md skill
wellwelwel/lagune · .claude/skills/refine/SKILL.md · Confronts a scope with the engineering, testing, and writer skills, each where it applies, and with the architecture a…
v1.0.0 · audit A · 221 stars
simulate SKILL.md skill
wellwelwel/lagune · .claude/skills/simulate/SKILL.md · How to simulate a Lagune command end to end so the user sees both the process and the results in chat. Use when the…
git:20261102.0ad572c · audit A · 221 stars
specialize SKILL.md skill
wellwelwel/lagune · .claude/skills/specialize/SKILL.md · Author a new built-in Lagune specialization inside the Lagune source, not a project's own catalog. Use when adding or…
git:20261112.c2e63ba · audit A · 221 stars

Every file in wellwelwel/lagune

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