Compact Guide

Community

jh941213

compact-guide

Context window management and token optimization guide. Triggers on: context, tokens, compact, memory management. NOT for: code writing, debugging.

Overview

Publisher	jh941213
Repository	`my-cc-harness`
Skill name	`compact-guide`
Stars	125
Forks	35
Bundled files	Instructions only
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by jh941213 on GitHub. Read the source before you install it.

Installation

Install the Compact Guide AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/jh941213/my-cc-harness.git /tmp/my-cc-harness
mkdir -p .claude/skills
cp -r /tmp/my-cc-harness/skills_en/compact-guide .claude/skills/compact-guide

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Compact Guide in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Compact Guide on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Compact Guide is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Context Management Guide

Context is like fresh milk. The problem is freshness, not volume — polluted context deserves a reset.

Core Principles (the 1M-context era)

Don't count remaining tokens — auto-compact manages the threshold — manual /compact only when a work unit ends
Manual intervention is signal-based, not number-based:

Signal	Action
A work unit (milestone/story) just finished	/compact — start the next unit clean
The work topic changes entirely	/handoff → /clear — new session
Repeating the same mistakes, forgetting earlier decisions, illogical replies	Pollution signal — /handoff → /clear (compact doesn't wash pollution out)
Right after long exploration/log output	/compact if a work unit is ending; otherwise leave it to auto-compact

Never shrink or rush work out of worry about remaining context — keep going

Commands

/compact

Summarizes and compresses conversation content
Retains important information, reduces tokens only
Does not interrupt workflow

/clear

Complete reset
Risky without HANDOFF.md!
Use when you want a clean start

Recommended Pattern


Start work
    |
Work unit completed (milestone/story)
    |
/compact (clean up at the boundary)
    |
… repeat …
    |
Topic switch or pollution signal
    |
/handoff (generate HANDOFF.md)
    |
/clear (reset)
    |
Read HANDOFF.md in new session

Context Management from a Cost Perspective

Why /compact is advantageous

Work context (progress, decisions) is preserved as a summary, so nothing needs rebuilding
Retains important information while reducing tokens only, so workflow is not interrupted
Lower restart cost than /clear

Hidden cost of /clear

Conversation-context rebuild cost — progress, decisions, and exploration results must be rebuilt from scratch
Additional tokens generated when loading HANDOFF.md
Implicit context not captured in HANDOFF.md is lost

Decision rule

On cost alone: /compact > /clear
When quality wobbles: /clear is the answer — summarizing polluted context summarizes the pollution too
For long autonomous runs (TTH/autodev), leave it to auto-compact and don't intervene

Frequently asked questions

What does the Compact Guide AI skill do?

Context window management and token optimization guide. Triggers on: context, tokens, compact, memory management. NOT for: code writing, debugging.

Why use Compact Guide on TypingMind?

Because you install it once and use it with any model. Compact Guide is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Compact Guide in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jh941213/my-cc-harness/tree/main/skills_en/compact-guide. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Compact Guide?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Compact Guide?

As many as you like. As long as a model supports skills, you can use Compact Guide with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Compact Guide AI skill free?

It is published on GitHub by jh941213. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Migration

JuliusBrussee

CommunityPopular

Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.

Blog Post

A long-form article / blog post — masthead, hero image placeholder, article body with figures and pull quotes, author byline, related posts. Use when the brief asks for "blog", "article", "post",…

Html Ppt Zhangzara Monochrome

nexu-io

OrganizationPopular

A grant proposal on CRISPR base-editing for sickle-cell disease — the hypothesis, the approach, the milestones, and the risk. Built as a decision-grade academic research deck for grant review…

Html Ppt Zhangzara Scatterbrain

nexu-io

OrganizationPopular

A design-school graduation project: a civic wayfinding system for a transit hub — the brief, the process, and the outcome. Built as a decision-grade coursework defense deck for crit panel, faculty.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Context Management Guide

Core Principles (the 1M-context era)

Commands

/compact

/clear

Recommended Pattern

Context Management from a Cost Perspective

Why /compact is advantageous

Hidden cost of /clear

Decision rule

Frequently asked questions

Related AI Skills

Set up your own AI workspace now