compacting-skills SKILL.md skillA

compacting-skills from toongri/oh-my-toong-playground is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add toongri/oh-my-toong-playground/compacting-skills@git:20261022.0d15fd3

Pins git:20261022.0d15fd3 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
toongri/oh-my-toong-playground
Path
skills/compacting-skills/SKILL.md
Versions recorded
4
Latest version
git:20261022.0d15fd3, committed Oct 22, 2026
First version recorded
Oct 22, 2026
Size
7,409 bytes
Repository stars
25
License
MIT

Use when a skill, agent prompt, or rules document has grown long, repetitive, or self-contradicting and must get shorter without changing the behavior it produces, or when an already-compressed doc must be checked for lost rules before merge.

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

# Compacting Skills

## Overview

The current doc is the specification. Compression may remove only what you can show the agent will still do without it. Size is the outcome, never the goal: the deliverable is the same behavior from fewer words, with evidence.

Three kinds of evidence are required, because each misses what the others catch:

| Evidence | Catches | Misses |
|---|---|---|
| Rule inventory + trace table | a rule that vanished | a rule that changed scope; behavior |
| Scenario measurement (before/after, 5 reps) | behavior drift on asked questions | gaps between sentences; unasked cases |
| Compression regression audit | widened/narrowed rules, deleted premises, doc/code mismatch | nothing alone proves behavior |

A pilot compression scored 0.997 on its scenarios (baseline 0.960) and still carried 10 regressions that only the audit found, plus one more an external reviewer found. Never stop at the score.

**REQUIRED BACKGROUND:** writing-skills (scenario testing with subagents).

## What stays, what goes

Keep a rule (MUST) when at least one holds, and record which:
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add toongri/oh-my-toong-playground/compacting-skills@sha256:49d8e4fdfc4ce5aa

The line at the top of this page pins the label git:20261022.0d15fd3, 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_h2k6xegc2gr6ljci.svg)](https://markdownregistry.com/a/art_h2k6xegc2gr6ljci)

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

Versions

The registry has recorded 4 versions of this file, all committed on Oct 22, 2026.

versioncommittedcommitsizeaudit
git:20261022.0d15fd3 latest2026-10-22 0d15fd3 7,409 BA view · diff
git:20261022.17208282026-10-22 1720828 7,350 BA view · diff
git:20261022.13c7db12026-10-22 13c7db1 7,289 BA view · diff
git:20261022.21ea5d12026-10-22 21ea5d1 7,200 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 (7409 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

toongri/oh-my-toong-playground · 25 stars · license MIT · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_h2k6xegc2gr6ljci
GET https://markdownregistry.com/api/v1/resolve?ref=toongri/oh-my-toong-playground/compacting-skills
GET https://markdownregistry.com/api/v1/blob/49d8e4fdfc4ce5aaebe056c5cd0745d360d4f410ad26c5a7ca34c6f6e961b8f8

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 toongri/oh-my-toong-playground

AGENTS.md AGENTS.md file
toongri/oh-my-toong-playground · AGENTS.md
git:20260715.747bbce · audit B · 25 stars
CLAUDE.md CLAUDE.md file
toongri/oh-my-toong-playground · CLAUDE.md
git:20261021.f2e95a0 · audit A · 25 stars
DESIGN.md@evals/ultraresearch/baselines/control/rep5 DESIGN.md file
toongri/oh-my-toong-playground · evals/ultraresearch/baselines/control/rep5/DESIGN.md
git:20260811.1c876fe · audit A · 25 stars
fc-feedback SKILL.md skill
toongri/oh-my-toong-playground · projects/fc-feedback/skills/fc-feedback/SKILL.md · Use when an EA FC (EA Sports FC)/football or futsal coaching-feedback YouTube video — narrated, or with feedback left…
git:20261011.4c42650 · audit A · 25 stars
DESIGN.md@projects/fc-feedback/skills/fc-feedback/scripts DESIGN.md file
toongri/oh-my-toong-playground · projects/fc-feedback/skills/fc-feedback/scripts/DESIGN.md
git:20261006.6ed684a · audit A · 25 stars
implementation SKILL.md skill
toongri/oh-my-toong-playground · projects/toong-java-spring-template/skills/implementation/SKILL.md · Use when implementing any feature, adding code, or modifying existing code in this Java/Spring project. Triggers on…
git:20260401.829a4a9 · audit A · 25 stars
testing SKILL.md skill
toongri/oh-my-toong-playground · projects/toong-java-spring-template/skills/testing/SKILL.md · Use when writing tests in this Java/Spring project, generating test skeletons, deciding mock strategies, learning test…
git:20260401.829a4a9 · audit A · 25 stars
agent-browser SKILL.md skill
toongri/oh-my-toong-playground · skills/agent-browser/SKILL.md · Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages…
git:20260918.d25484f · audit A · 25 stars
agent-council SKILL.md skill
toongri/oh-my-toong-playground · skills/agent-council/SKILL.md · Use when facing trade-offs, subjective judgments, uncertain decisions, or when diverse viewpoints would improve…
git:20260908.2ec781d · audit A · 25 stars
agent-device SKILL.md skill
toongri/oh-my-toong-playground · skills/agent-device/SKILL.md · Automates Apple-platform apps (iOS, tvOS, macOS), Android devices, and Amazon Vega OS TV apps in Vega Virtual Devices…
git:20260918.d25484f · audit A · 25 stars
clarify SKILL.md skill
toongri/oh-my-toong-playground · skills/clarify/SKILL.md · MANDATORY before any implementation when request is vague or has multiple interpretations. Triggers on "clarify"…
git:20260918.dba3f1f · audit A · 25 stars
code-review SKILL.md skill
toongri/oh-my-toong-playground · skills/code-review/SKILL.md · Use when reviewing code changes for quality, correctness, and production readiness before merge
git:20261022.4d3da64 · audit A · 25 stars

Every file in toongri/oh-my-toong-playground

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