typmem-learn
Capture one durable fact as a recipe card under ~/.typmem/memory/learnings/. A learning is what you now know about the world — useful to anyone, indefinitely, even someone who never saw the painful session that produced it. A learning is valid and usable the moment you capture it — it does not wait for any review. typmem-judge later tidies learnings and may propose that the strongest ones be promoted to precedents/ or rules.md, but that is optional and non-blocking.
Learning vs retro — read this first
- Learning = recipe card. "What I now know about the world." A distilled fact. No story, no timeline, no
I. True regardless of which day or project hit it. → goes here.
- Retro = diary. "What happened to me." Status, decisions-in-flight, dead ends, follow-ups. → goes to
typmem-retro.
The test: "Will this still matter after the work that produced it is finished?"
- Yes → it is a learning. Capture it here.
- No → it is retro material. Do NOT write it here; it belongs in
typmem-retro.
What makes a good learning
- Atomic — one fact per file, so each can be searched, judged, and promoted on its own. If you have three facts, write three files.
- No
I, no timeline, no story. State the fact, not the journey that produced it.
- Self-contained — understandable by someone who never saw the work behind it.
- Specific and actionable — a constraint, a gotcha, a pattern, a how-things-work truth. Not a vague impression.
Example of the move — turn a diary sentence into a recipe card:
Diary (retro): "Spent two hours today fighting the iii-engine install, the binary kept failing on this machine, eventually gave up."
Recipe card (learning): "iii-engine has no prebuilt binary for this arch — anything depending on it needs the Docker fallback."
Two ways to use this
- Direct capture (default). You (or the user) have a fact in mind right now → write one learning file.
- Extract from a retro. Point at a retro file (or the latest one in
~/.typmem/memory/retro/) → read it, pull out each durable fact, and write one learning file per fact. Distil — do not copy the narrative across.
How to write it
- Make sure the directory exists:
mkdir -p ~/.typmem/memory/learnings
- Distil the fact and run the test above. If it fails (it only matters for this session), stop — it belongs in
typmem-retro, not here.
- Build a slug from the fact itself (not the session): lowercase kebab-case, 2–6 words, no spaces (e.g.
iii-engine-no-prebuilt-binary, aca-sidecar-no-host-network).
- Target file:
~/.typmem/memory/learnings/<slug>.md — no date prefix. Learnings are timeless; only retro carries a date in the filename.
- Write this frontmatter, then the body:
---
author: <agent name or person capturing this>
reviewer:
created: YYYY-MM-DD
---
Leave reviewer empty. An empty reviewer just means typmem-judge has not looked at this one yet — it does not mean the learning is unusable. The learning is valid right away. Do not fill reviewer in from this skill.
- Body: state the fact in recipe-card shape — a short, self-contained claim. Free-form prose is fine; no fixed template yet. Keep the discipline: no
I, no timeline.
- If a file with that slug already exists: it is probably the same fact. Either refine the slug to be more specific, or update the existing file rather than creating a near-duplicate. (Automatic dedup comes later with
typmem-judge / index search — for now, use judgement.)
When extracting from a retro, repeat steps 2–7 once per durable fact you find.
File rules
- Location:
~/.typmem/memory/learnings/
- Filename:
<slug>.md — no date prefix (timeless fact)
- Frontmatter (MVP):
author, reviewer (empty — typmem-judge fills it once it has looked), created
- One fact per file
Don't
- Don't write session narrative, status, or what-happened here — that is a retro (
typmem-retro).
- Don't fill in
reviewer yourself — that is typmem-judge's job; an empty field just means the judge hasn't looked at it yet, not that the learning is unusable.
- Don't bundle multiple facts into one file — split them so each can be judged and promoted independently.
- Don't promote a learning to
precedents/ from here — that is a human review step handled by a later skill.
1---2name: typmem-learn3description: Capture a durable fact — a "learning" / recipe card — to ~/.typmem/memory/learnings/. A learning is a distilled, timeless fact about the world (a gotcha, a constraint, a how-things-work truth) that stays useful long after the work that produced it is done. Use this whenever you discover something worth keeping, when the user says "remember this", "note that", "save this", "TIL", or "lesson learned", and use it to extract durable facts out of a retro after a session. This is the primary memory-capture skill — reach for it often, even when the user doesn't say the word "learning". Do NOT use it for session narrative, status, or what-happened-today; that is a retro — use typmem-retro for those.4---56# typmem-learn78Capture one durable fact as a recipe card under `~/.typmem/memory/learnings/`. A learning is *what you now know about the world* — useful to anyone, indefinitely, even someone who never saw the painful session that produced it. A learning is **valid and usable the moment you capture it** — it does not wait for any review. `typmem-judge` later tidies learnings and may propose that the strongest ones be promoted to `precedents/` or `rules.md`, but that is optional and non-blocking.910## Learning vs retro — read this first1112- **Learning = recipe card.** "What I now know about the world." A distilled fact. No story, no timeline, no `I`. True regardless of which day or project hit it. → goes here.13- **Retro = diary.** "What happened to me." Status, decisions-in-flight, dead ends, follow-ups. → goes to `typmem-retro`.1415The test: **"Will this still matter after the work that produced it is finished?"**16- Yes → it is a learning. Capture it here.17- No → it is retro material. Do NOT write it here; it belongs in `typmem-retro`.1819## What makes a good learning2021- **Atomic** — one fact per file, so each can be searched, judged, and promoted on its own. If you have three facts, write three files.22- **No `I`, no timeline, no story.** State the fact, not the journey that produced it.23- **Self-contained** — understandable by someone who never saw the work behind it.24- **Specific and actionable** — a constraint, a gotcha, a pattern, a how-things-work truth. Not a vague impression.2526Example of the move — turn a diary sentence into a recipe card:2728> Diary (retro): "Spent two hours today fighting the iii-engine install, the binary kept failing on this machine, eventually gave up."29>30> Recipe card (learning): "iii-engine has no prebuilt binary for this arch — anything depending on it needs the Docker fallback."3132## Two ways to use this3334- **Direct capture (default).** You (or the user) have a fact in mind right now → write one learning file.35- **Extract from a retro.** Point at a retro file (or the latest one in `~/.typmem/memory/retro/`) → read it, pull out each durable fact, and write one learning file per fact. Distil — do not copy the narrative across.3637## How to write it38391. Make sure the directory exists: `mkdir -p ~/.typmem/memory/learnings`402. Distil the fact and run the test above. If it fails (it only matters for this session), stop — it belongs in `typmem-retro`, not here.413. Build a slug from the **fact itself** (not the session): lowercase kebab-case, 2–6 words, no spaces (e.g. `iii-engine-no-prebuilt-binary`, `aca-sidecar-no-host-network`).424. Target file: `~/.typmem/memory/learnings/<slug>.md` — no date prefix. Learnings are timeless; only retro carries a date in the filename.435. Write this frontmatter, then the body:44 ```45 ---46 author: <agent name or person capturing this>47 reviewer:48 created: YYYY-MM-DD49 ---50 ```51 **Leave `reviewer` empty.** An empty `reviewer` just means `typmem-judge` has not looked at this one yet — it does not mean the learning is unusable. The learning is valid right away. Do not fill `reviewer` in from this skill.526. Body: state the fact in recipe-card shape — a short, self-contained claim. Free-form prose is fine; no fixed template yet. Keep the discipline: no `I`, no timeline.537. If a file with that slug already exists: it is probably the same fact. Either refine the slug to be more specific, or update the existing file rather than creating a near-duplicate. (Automatic dedup comes later with `typmem-judge` / index search — for now, use judgement.)5455When extracting from a retro, repeat steps 2–7 once per durable fact you find.5657## File rules5859- Location: `~/.typmem/memory/learnings/`60- Filename: `<slug>.md` — no date prefix (timeless fact)61- Frontmatter (MVP): `author`, `reviewer` (empty — `typmem-judge` fills it once it has looked), `created`62- One fact per file6364## Don't6566- Don't write session narrative, status, or what-happened here — that is a retro (`typmem-retro`).67- Don't fill in `reviewer` yourself — that is `typmem-judge`'s job; an empty field just means the judge hasn't looked at it yet, not that the learning is unusable.68- Don't bundle multiple facts into one file — split them so each can be judged and promoted independently.69- Don't promote a learning to `precedents/` from here — that is a human review step handled by a later skill.
thaitype