agentleFS
Sign inStart free
MaDxCRaZYMaDxCRaZY/antigravity-skills/skills/compaction/SKILL.md

compaction

Skill4 starsChanged 26 days agoMITView on GitHub

Triggers on-demand context compaction: persists critical state into durable artifacts, flushes obsolete transient turn history, and signals the runtime to compact context.

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. StarRocks/starrocks-debug-skills★ 77same name
    2. frnkgns/Overgeared-Skills★ 7same name
    3. VECTORG99/acf★ 2same name
    4. CorvusWing/CorvusWing★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When the user invokes /compaction:

    line 16
  2. Distinctive:

    Before pruning the conversation history, identify all critical ongoing context:

    line 19
  3. Very specific:

    Write or update this state into a persistent summary artifact in <artifactDir>/session_state.md.

    line 23
  4. Very specific:

    When conversation volume is high, the runtime periodically summarizes earlier steps into conversation_summaries.db.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

On-Demand Context Compaction Protocol

The /compaction command provides an explicit trigger to compact the active conversation context, preventing context exhaustion during long-running sessions.

Compaction Routine

When the user invokes /compaction:

  1. State Preservation (Pre-Compaction Audit):
    • Before pruning the conversation history, identify all critical ongoing context:
      • Current objective and tasks completed.
      • Active file paths, line numbers, and key symbols under investigation.
      • Ground-truth telemetry, architectural findings, or pending bugs.
    • Write or update this state into a persistent summary artifact in <artifactDir>/session_state.md.
  2. Trigger Runtime Compaction:
    • Invoke internal /compact mechanics or on-demand context checkpointing.
    • Format the compaction checkpoint with:
      • Accomplished So Far: Summary of completed changes.
      • Current State: Active files, ongoing tests, or current build statuses.
      • Immediate Next Actions: Clear bullet points for the next prompt turns.
  3. Background Auto-Compaction Configuration:
    • Antigravity automatically monitors conversation token thresholds in the background.
    • When conversation volume is high, the runtime periodically summarizes earlier steps into conversation_summaries.db.
    • Invoking /compaction forces this summarization immediately rather than waiting for automatic token limit triggers.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free