structured-context-compressor
Skill236 starsChanged 8 months agoMITView on GitHub
Compress a long agent conversation into a nine-part continuation summary that preserves request, files, errors, user messages, current work, and the next aligned step.
In this repository5 other files it gives its agents.
- dream-memorySkill
- kairos-liteSkill
- memory-extractorSkill
- swarm-coordinatorSkill
- verification-gateSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill when a free-form summary is too lossy and you need a reliable continuation artifact.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Structured Context Compressor
Use this skill when a free-form summary is too lossy and you need a reliable continuation artifact.
Use It For
- long coding conversations
- session handoff
- agent-to-agent continuation
- preserving user intent under context pressure
Quick Start
Render the standard template:
python3 {baseDir}/scripts/render_template.pyThen apply the prompt in references/prompt-template.md.
Nine Sections
- primary request and intent
- key technical concepts
- files and code sections
- errors and fixes
- problem solving
- all user messages
- pending tasks
- current work
- next aligned step
Highest-Value Rule
Preserve all user messages or an accurate equivalent. Do not compress away the corrections that changed the direction of work.
Supporting Files
- Prompt template: references/prompt-template.md
- Source notes: references/source-notes.md
- Helper script:
python3 {baseDir}/scripts/render_template.py
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
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.