context-recovery
Skill2 starsChanged 12 months agoMITView on GitHub
Recover lost context after session compaction or when information from previous sessions is needed. Use when: user mentions "what were we working on", "I lost context", "before the compact", "previous session", or asks about decisions/implementations/discussions that aren't in current context. Also use proactively when you notice references to prior work you lack context for.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- neomjs/neo-agent-skillstheir own version, first seen Nov 15, 2026
- MarchRory/liushi_agent_settingstheir own version, first seen Jun 1, 2026
- SakuraByteCore/codexmatetheir own version, first seen Mar 7, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- SakuraByteCore/codexmate★ 356same name
- neomjs/neo-agent-skills★ 11same name
- MarchRory/liushi_agent_settings★ 0same 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.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
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 19
If the user's request is vague, ask: "What topic should I search for?"
- Distinctive: line 41
Default limit of 10 results is usually sufficient
“Common” is measured: kept by at least 6 in 10 of the 3 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.
Files
Context Recovery
You've been activated to recover context that was lost to compaction or exists in a previous session.
Quick Start
- Identify the topic - What specific context is needed?
- If the user's request is vague, ask: "What topic should I search for?"
- Use aspy_recall (primary tool):
This combines semantic search (if embeddings enabled) with keyword matching. Searches thinking blocks, user prompts, AND assistant responses simultaneously. Handles both exact queries and fuzzy queries like "that golf thing?"aspy_recall(query="<keywords>", limit=10) - Synthesize, don't dump - Summarize findings:
- What was decided or implemented
- Key file paths and line numbers mentioned
- Any unfinished work or next steps discussed
- Offer continuity - "Would you like me to continue where we left off?"
Search Strategy
Start with aspy_recall (Primary)
- Combines semantic + keyword search automatically
- Finds conceptually related content even with different wording
- Default limit of 10 results is usually sufficient
Targeted Searches (If Combined Is Noisy)
aspy_recall_thinking- Claude's reasoning and analysis (WHY decisions were made)aspy_recall_prompts- What the user askedaspy_recall_responses- Claude's answers and code
What Makes Good Context Recovery
Good synthesis:
"On Dec 2nd, we implemented mouse scroll support for the detail modal. The fix was in
src/tui/mod.rs:299-322- checking if modal is open before dispatching scroll events. You mentioned wanting to test it before merging."
Bad synthesis:
"Found 5 results mentioning 'scroll'. Here they are: [dumps raw results]"
Common Patterns
| User Says | Search For |
| "that bug we fixed" | error keywords, "fix", file names |
| "the refactor" | "refactor", component names |
| "what we decided" | "decided", "approach", "pattern" |
| "before compact" | recent topics from today |
| "something about golf?" | just search it - semantic will handle fuzzy |
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.

