Context Compressor
SkillFiles & storageCompress long histories and documents into durable decision summaries without losing constraints, TODOs, or file paths. Use before long continuations, handoffs, or when context is getting large.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Context Compressor skill
What this skill tells your AI
The instructions your AI receives, as published by navinspire-ia/navin in navin/skills/context-compressor/SKILL.md and read by ahel’s review.
Overview
Produce a high-signal digest that a future turn (or subagent) can resume from.
What to keep
- Goal and success criteria
- Hard constraints (“do not…”, versions, environments)
- Decisions made + why
- Open questions / blockers
- Key file paths and commands
- Current status of each workstream
What to drop
- Exploratory dead-ends that no longer matter
- Raw tool dumps (keep conclusions only)
- Repeated chit-chat
- Full file contents (link paths instead)
Workflow
- Skim the conversation / docs for decisions and artifacts.
- Write a Resume Brief using the template below.
- Offer to store durable facts in memory only when the user wants persistence (Dream manages long-term memory files - do not silently rewrite them).
- For handoff to
spawn, paste the Resume Brief into the subagenttask.
Resume Brief template
## Goal
...
## Done
- ...
## Decisions
- ...
## Open
- ...
## Key paths
- `path/to/file`
## Next step
...
Rules
- Prefer bullets over prose.
- Never invent completed work.
- If unsure whether a constraint still applies, list it under Open.
Signals
- GitHub stars
- 22
- Forks
- 4
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
context-compressor- Source
- github.com/navinspire-ia/navin