skill-distillation SKILL.md skillA

skill-distillation from naimkatiman/continuous-improvement is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add naimkatiman/continuous-improvement/skill-distillation@git:20260602.aeb6415

Pins git:20260602.aeb6415 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
naimkatiman/continuous-improvement
Path
plugins/continuous-improvement/skills/skill-distillation/SKILL.md
Versions recorded
1
Latest version
git:20260602.aeb6415, committed Jun 2, 2026
Size
3,701 bytes
Repository stars
9
License
MIT

Enforces Law 7 (Learn From Every Session) of the 7 Laws of AI Agent Discipline. Distills repeated successful tool sequences into reusable draft instincts, so a pattern that worked three times becomes a captured recipe instead of being re-derived from scratch every session.

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 Distillation — Turn Repeated Wins Into Reusable Instincts

Law 7 says learn from every session. The friction harvester already learns from failures. This skill learns from the other side: when the same tool sequence keeps ending in a passing verification, that is a recipe worth keeping — not a coincidence to forget.

## When to Activate

- At end of session, after a successful multi-step task — check whether the pattern is worth keeping.
- When you notice you have solved a similar problem the same way more than once.
- During a retrospective, to mine the observation log for patterns that have proven themselves.

## Core Concept

Distillation walks the observation log, groups it into contiguous trajectories (split on session change or a long time gap), and keeps only the trajectories that ended in success:

```
verify-exit-0   — a Bash test/build/verify command with a non-failing output
reflection-pass — an observation containing "verified" / "phase 4" / "verify:all green"
```
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add naimkatiman/continuous-improvement/skill-distillation@sha256:859bc8cc49567dc8

The line at the top of this page pins the label git:20260602.aeb6415, 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_3acjvcosmn2bkaex.svg)](https://markdownregistry.com/a/art_3acjvcosmn2bkaex)

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

Versions

The registry has recorded 1 version of this file, committed on Jun 2, 2026.

versioncommittedcommitsizeaudit
git:20260602.aeb6415 latest2026-06-02 aeb6415 3,701 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 (3701 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

naimkatiman/continuous-improvement · 9 stars · license MIT · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_3acjvcosmn2bkaex
GET https://markdownregistry.com/api/v1/resolve?ref=naimkatiman/continuous-improvement/skill-distillation
GET https://markdownregistry.com/api/v1/blob/859bc8cc49567dc857e16b8591d3e0b56b3cc6540e1b53f1dba3d9482e45666d

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 naimkatiman/continuous-improvement

AGENTS.md AGENTS.md file
naimkatiman/continuous-improvement · AGENTS.md
git:20260906.e54b2e4 · audit A · 9 stars
CLAUDE.md CLAUDE.md file
naimkatiman/continuous-improvement · CLAUDE.md
git:20260906.e54b2e4 · audit A · 9 stars
continuous-improvement SKILL.md skill
naimkatiman/continuous-improvement · SKILL.md · Install structured self-improvement loops with instinct-based learning into Claude Code — research, plan, execute…
git:20260906.3e80e82 · audit A · 9 stars
llms.txt llms.txt file
naimkatiman/continuous-improvement · llms.txt
git:20260906.fca30a4 · audit A · 9 stars
audit SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/audit/SKILL.md · Enforces Law 4 (Verify Before Reporting) of the 7 Laws of AI Agent Discipline. Audits a window of recent commits for…
git:20260602.e0e1217 · audit A · 9 stars
continuous-improvement SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/continuous-improvement/SKILL.md · Install structured self-improvement loops with instinct-based learning into Claude Code — research, plan, execute…
git:20260906.3e80e82 · audit A · 9 stars
deploy-receipt SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/deploy-receipt/SKILL.md · Enforces Law 4 (Verify Before Reporting) of the 7 Laws of AI Agent Discipline at the deploy seam. A merge into a branch…
git:20260906.fca30a4 · audit A · 9 stars
gateguard SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/gateguard/SKILL.md · Enforces Law 1 (Research Before Executing) of the 7 Laws of AI Agent Discipline. Fact-forcing gate that blocks…
git:20261101.d6fb48b · audit A · 9 stars
goal-monitor SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/goal-monitor/SKILL.md · Enforces Law 2 (Plan Is Sacred) of the 7 Laws of AI Agent Discipline. Detects when a session has drifted away from its…
git:20260610.57b1c8e · audit A · 9 stars
grill-me SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/grill-me/SKILL.md · Enforces Law 1 (Research Before Executing) of the 7 Laws of AI Agent Discipline. Interview the user relentlessly about…
git:20260511.2223960 · audit A · 9 stars
grill-with-docs SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/grill-with-docs/SKILL.md · Enforces Law 1 (Research Before Executing) and Law 7 (Learn From Every Session) of the 7 Laws of AI Agent Discipline…
git:20260527.d97abe8 · audit A · 9 stars
handoff SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/handoff/SKILL.md · Enforces Law 5 (Reflect After Every Session) of the 7 Laws of AI Agent Discipline. Compact the current conversation…
git:20260610.57b1c8e · audit A · 9 stars

Every file in naimkatiman/continuous-improvement

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