agentleFS
SkinnnyJaySkinnnyJay/wiki-llm/skills/wiki-learn/SKILL.md

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.

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
  1. Very specific:

    Ensure llm-wiki/ exists. If .agent-memory.md is missing, create it from the template below (or append sections to an existing file).

    line 15

≈ “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.

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

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

  1. Ensure llm-wiki/ exists. If .agent-memory.md is 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 Steps

Operations (from $ARGUMENTS or user message)

ModeAction
learnAppend a dated bullet under the right section: YYYY-MM-DD — <note> (context: …)
recallRead the file and surface entries relevant to the current task or query
reviewShow 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.md if 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

ReadsWrites
llm-wiki/.agent-memory.mdllm-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.md when useful.

Smoke check

  • CLI: llm-wiki validate from the vault root (vault must exist).
  • Prompt: Invoke this skill; confirm learn/recall targets llm-wiki/.agent-memory.md when relevant.

Optional: persona.name in config (default Gennie).

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.