skill-evolution SKILL.md skillA
skill-evolution from labs21-dev/agents-stack is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add labs21-dev/agents-stack/skill-evolution@git:20260912.9d47cf0Pins git:20260912.9d47cf0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- labs21-dev/agents-stack
- Path
skill-evolution/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260912.9d47cf0, committed Sep 12, 2026
- Size
- 6,308 bytes
- Repository stars
- 27
- License
- none declared
Evolve skills from real usage. Use when a skill has been used enough to accumulate evidence and the user wants to decide whether a piece of it should graduate into the standard set, be deprecated, or be revised — collects passive usage cases, flags candidates that cross a frequency-plus-verification threshold, drafts concrete upgrade patches, and routes them through a human gate. Also use when the user asks "should this lens/rule/trigger become permanent?…
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 Evolution (L2 + L3) The companion to **skill-creator**. Where skill-creator owns short-cycle, human-driven iteration within a session (L0 generation, L1 evaluation), this skill owns the **long-cycle, case-driven evolution across sessions**: - **L2 Evolution** — collect real usage cases → flag candidates → draft upgrade/deprecate patches → human gate → merge (with rollback). - **L3 Accumulation** — accumulate what "a good skill" means across skills, as cases. **Accumulate only, never legislate** — folding a pattern into a standard is a human action (the reflexivity defense). ## Reflexivity defense (structural, not preference) This skill is a meta-skill operating on skills. A meta-skill that grades its own output with its own standard drifts into **self-validating mediocrity** — everything passes its own bar, quality monotonically decays, no external signal interrupts it. Therefore: - **L3 legislation is human-only.** This skill accumulates cases and flags candidate patterns; it never folds a pattern into a standard itself. …
Read the whole file at its exact version.
How to install
mdr add labs21-dev/agents-stack/skill-evolution@sha256:c061e7ee30de163aThe line at the top of this page pins the label git:20260912.9d47cf0, 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_bhxu4hmlgrnl4p7u)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 12, 2026.
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 (6308 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
labs21-dev/agents-stack · 27 stars · license none declared · pushed 2026-09-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_bhxu4hmlgrnl4p7u GET https://markdownregistry.com/api/v1/resolve?ref=labs21-dev/agents-stack/skill-evolution GET https://markdownregistry.com/api/v1/blob/c061e7ee30de163ab54f393547fc4d8f8519de8488e575ff75f6d53d82a2c8e0
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 labs21-dev/agents-stack
Every file in labs21-dev/agents-stack