wiki-learn
Skill0 starsChanged 4 months agoMITView on GitHub
Cross-session memory for the vault — learn, recall, and review patterns, preferences, pitfalls, and next steps in llm-wiki/.agent-memory.md.
In this repository36 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- wiki-extract-annasSkill
- wiki-extract-crunchbaseSkill
- wiki-extract-ebookSkill
- wiki-extract-ecommerceSkill
- wiki-extract-githubSkill
- wiki-extract-linkedinSkill
- wiki-extract-newsletterSkill
- wiki-extract-patentsSkill
- wiki-extract-paywallSkill
- wiki-extract-podcastSkill
- wiki-extractSkill
- wiki-extract-wikipediaSkill
- wiki-extract-youtubeSkill
- wiki-fetchSkill
- wiki-ingestSkill
- wiki-lintSkill
- wiki-maintainerSkill
- wiki-onboardSkill
- wiki-pipelineSkill
- wiki-querySkill
- wiki-raw-prepareSkill
- wiki-research-academicSkill
- wiki-research-deepSkill
- wiki-research-feedsSkill
- wiki-research-loopSkill
- wiki-research-newsSkill
- wiki-researchSkill
- wiki-research-socialSkill
- wiki-research-webSkill
- wiki-retroSkill
- wiki-session-memorySkill
- wiki-setupSkill
- wiki-statusSkill
- wiki-upgradeSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Ensure llm-wiki/ exists. If .agent-memory.md is missing, create it from the template below (or append sections to an existing file).
≈ “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
Wiki learn — Memory
Persist patterns, preferences, pitfalls, and next steps across sessions in a single human-reviewable file: llm-wiki/.agent-memory.md. Plain Markdown (no DB). Optional: integrate with wiki-retro (recommendations → Next Steps).
Privacy: This file is assistant-facing notes, not canonical wiki/ evidence — but if the vault is in git, treat it like any tracked doc: do not record secrets, API keys, or confidential tokens here; use env or gitignored settings instead.
Pre-flight
- Ensure
llm-wiki/exists. If.agent-memory.mdis missing, create it from the template below (or append sections to an existing file).
Initial file template
# Agent memory (llm-wiki)
Optional cross-session notes. Edit freely. This file is **not** evidence for claims in `wiki/` — use `raw/` + `wiki/` for that.
## Research Patterns
## Preferences
## Pitfalls
## Next StepsOperations (from $ARGUMENTS or user message)
| Mode | Action |
| learn | Append a dated bullet under the right section: YYYY-MM-DD — <note> (context: …) |
| recall | Read the file and surface entries relevant to the current task or query |
| review | Show all sections; offer to prune, merge, or move items to wiki/log.md if they become project decisions |
Steps
Step 1 — Classify the note
- Research Patterns — what source combos work, domains to avoid, query tricks
- Preferences — tone, page structure, PDF adapter choice, automation level
- Pitfalls — repeated failures (rate limits, paywalls, bad extractions)
- Next Steps — follow-up topics (often fed by wiki-retro)
Step 2 — Read or write
- learn: append; do not duplicate identical bullets unless reinforcing
- recall: quote 3–7 most relevant lines for the user’s question
- review: full file, then ask what to delete or rewrite
Step 3 — Integration
- wiki-research pre-flight: optionally recall Pitfalls + Preferences before classifying the request (see wiki-research — add one line “Read
.agent-memory.mdif present”). - wiki-retro: may append Recommendations to Next Steps here.
Done looks like
- learn: new bullet(s) visible under the correct section with date.
- recall: user sees relevant memory without dumping the whole file unless review.
- review: user confirms edits or leaves file as-is.
Artifacts
| Reads | Writes |
llm-wiki/.agent-memory.md | llm-wiki/.agent-memory.md |
Related skills
- wiki-research — consumes recall at session start (optional)
- wiki-retro — feeds Next Steps
- wiki-pipeline — may read memory before long runs
- wiki-session-memory — per-chat
raw/memory/<session-id>.md; promote recurring patterns from session files into.agent-memory.mdwhen useful.
Smoke check
- CLI:
llm-wiki validatefrom the vault root (vault must exist). - Prompt: Invoke this skill; confirm learn/recall targets
llm-wiki/.agent-memory.mdwhen relevant.
Optional: persona.name in config (default Gennie).
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.

