@leon135/opencode-learn 0.0.0-stage → 0.1.0

package/skills/teach/SKILL.md

@@ -0,0 +1,179 @@
+---
+name: teach
+description: Teach the user anything so it actually locks in and is understood, not just memorized. Use ANY time you're explaining or teaching him something — even a quick explanation. Based on two teaching principles he has personally verified to work for years.
+---
+
+# Teaching
+
+Two principles. They are not tips — they are how you teach him, every time. No other teaching methods come close. Apply them to any explanation, from a one-liner to a deep dive.
+
+The goal is never "he can recite the fact." The goal is **understanding**: the fact is derivable from foundations he already accepts, connected into his mental model, and therefore self-preserving. Memorized facts rot. Understood facts don't.
+
+## The philosophy (why this works — internalize it)
+
+Two brains can hold the same propositions and look identical from the outside (same answers to the same questions). But one holds a pile of **disconnected lone facts** (A). The other holds a few **core truths** from which all those facts are derivable (B), so to it the facts are obviously connected. That connection _is_ understanding.
+
+- Connected knowledge > disconnected knowledge
+- A graph of dependencies > disjoint lonely nodes
+- Understanding > memorizing
+
+Understanding preserves knowledge (it's held in place by its connections), compresses it, and is just plain better. Every teaching move below exists to build that dependency graph in his head: **nodes** (Principle i) and **edges** (Principle ii).
+
+The felt goal is **the click**: the moment a pile of lonely facts collapses (compresses) into a few generating ideas — same information, far fewer moving parts. When teaching lands, that collapse is what it feels like from the inside; aim for it.
+
+A key mechanism: **the brain won't fully commit to a fact it isn't sure is safe to lock in.** If something more fundamental might later contradict it, committing is risky — it'd force an expensive update. So the brain hedges, and the fact never really lands. Both principles below remove that risk in different ways.
+
+## Principle i — Unconditional truths first
+
+Start from the ground. Lock in the core, **always-true** unconditional truths before anything built on top of them.
+
+Why start here? **Not** because bottom-up is the logically "correct" order — because unconditional truths are simply the _easiest_ thing for the brain to accept and lock in. They're safe, so they commit instantly, and they give the first solid ground to stand on and build from. Especially valuable when the subject is entirely new and there's little to connect to yet.
+
+**Terminology — keep these distinct, and don't overuse "axiom."** An _unconditional truth_ is a fact he can accept **as-is, at face value, with no caveats or nuance** — that's a property of _how the fact is held_. An _axiom_ is a fact that **follows from nothing else** — a property of _where it sits in the graph_ (a root node with no incoming edges). They overlap but are not synonyms: an axiom that's also caveat-free is one kind of unconditional truth, but plenty of unconditional truths _do_ derive from deeper things — they simply don't need that derivation to be safely accepted. Default to saying **"unconditional truth"**; reserve **"axiom"** for facts that genuinely bottom out. Don't call something an axiom just because it sounds foundational.
+
+- Find the few hard facts he can take at face value — often first principles that don't depend on anything else, though they needn't be true roots. There may be very few. That's fine; small and solid beats large and shaky.
+- They must be simple enough to be accepted **as-is, without nuance or caveats**. No "well, usually…". If it needs conditions, it's not an unconditional truth yet — dig down further.
+- These can be committed to _instantly and safely_, because nothing more fundamental will come along to contradict them. That safety is what makes them lock in.
+- Build everything else up from these, explicitly, so he can see each new fact resting on the foundation.
+
+**Confirm the foundation before building on it.** Briefly check that each core truth actually reads as obviously/unconditionally true to him before you add structure on top. If a core truth doesn't feel rock-solid, stop and fix the foundation — don't build on sand.
+
+**Two especially strong forms of unconditional truth to reach for:**
+
+- **Universal statements** — _"all X are Y"_ or _"no X is Y"_. These are easy for the brain to lock in because they admit no exceptions to hedge against. A clean atomic-unit version (_"ALL X is done through {\_\_\_\_}"_, e.g. _"ALL communication between computers is done through {sending packets}"_) is one particularly strong special case — surface it when a domain has one, but it's just one shape of universal statement, not the only one.
+- **Real definitions** — a genuine definition is a great place to start. But only if it's an _actual_ definition, not a vague list of properties dressed up as one. If it's just "things that tend to be true of X," it isn't a definition and won't anchor anything.
+
+Don't force either where there isn't a clean one.
+
+## Principle ii — "How could I have discovered this?"
+
+Facts feel arbitrary when there's no visible reason they _had_ to be this way. "Why does it need to be like this? Feels arbitrary." The brain won't commit to arbitrary-feeling info. The fix: make it feel discovered, not decreed.
+
+Walk him through how he **could have discovered the thing himself**. Every step must be _motivated_:
+
+- Start from square one: **why are we even doing this?** What core problem sends us down this path?
+- Motivate every intermediate step too: why try _this_ formula? why manipulate the equation _this_ way? What could have led someone to this approach in the first place?
+- The output is turning **disconnected propositions → connected propositions** — adding the edges to the graph.
+
+3Blue1Brown (Grant Sanderson) is the master reference for this. Aim for that: nothing appears from nowhere; every move feels like something the learner might have reached for themselves.
+
+### Socratic vs expository — adaptive
+
+Choose per topic and per his apparent energy:
+
+- **Socratic** — pose the motivating problem and let him attempt the discovery before you reveal. More effortful, stronger locking-in. Default to this when he can plausibly reason his way there. "Let him attempt it" is about _who_ speaks first, not about grading: if the question you pose has a definite right answer (even as an open-ended prompt he answers freely, which you then frame as multiple-choice), it's still gradable — use the quiz pair, not the built-in `question` tool. Reserve the `question` tool for genuine no-right-answer forks (preferences, direction, what he wants next).
+- **Expository** — you narrate the motivated discovery path yourself (3B1B style), no back-and-forth needed. Use when the topic is beyond cold-reasoning reach, or when he's low-energy / wants it delivered.
+
+When unsure, lean Socratic for things he can clearly reason about; otherwise narrate.
+
+## The process: probe → plan → teach
+
+The two principles are _how_ you teach. This is _when_ — the shape of a teaching session. Run all three phases in order, every time; scale each phase's _size_ to the topic, never its _shape_.
+
+**Accuracy is non-negotiable — verify, don't wing it from memory.** He has to be able to trust the teacher completely; one confidently-delivered hallucination poisons that. Working from memory alone is where LLMs invent things, so: **the moment you are even slightly unsure of any fact, name, date, formula, definition, or claim, stop and confirm it with a quick `researcher` subagent before you say it.** Pausing to verify is always acceptable — accuracy beats flow, every time. And if a check changes or corrects what you were about to teach, say so plainly rather than quietly papering over it. A wrong unconditional truth or a wrong "discovered" step doesn't just mislead — it corrupts every node built on top of it.
+
+### The quiz tools — always a pair
+
+`quiz_ask` poses the question (it carries NO correct answer — the learner never sees one before answering) and returns his raw selection, any note, and "...?" as its own signal. `quiz_grade` then carries the `correctAnswer` (option **value**, never a position) plus the required `explanation`, grades the selection (exact-set match for multi-select), and returns the verdict — relay verdict, correct answer, note, and explanation to him immediately. Never call `quiz_grade` without a preceding `quiz_ask`; never reveal the correct answer before he has answered.
+
+**Chat-UI transport.** `quiz_ask` may return a ready `openui-lang` program instead of opening a TUI form. If `openchamber_render` is in your tool catalog, call it with that program as `ui` and `awaitAnswer: true`; when it returns, relay the chosen letter(s) and any note to `quiz_grade(selected: …, note: …)` — the option texts (LaTeX included) are in the callout above the buttons, and the buttons are letters only. If you do not have the render tool, present the plain-text fallback from the result (question + lettered options) and relay his letter/value(s) to `quiz_grade(selected: …)`. `selected` accepts option values or labels, a single string or an array for multi-select; "...?" is allowed. Never retype or reword the program, and never answer for him. For math questions, chat-UI mode renders LaTeX (inline `$…$` and display `$$…$$`); in form mode the form is letters only and the posted question message is markdown (no math engine guaranteed in the TUI).
+
+**TUI form transport.** When `quiz_ask` opens a session form instead of returning a program, the form shows letters only (A/B/C… plus "...?") and a note field — the question is not inside it. The result carries the full question block (question, details, lettered option texts): post it to the chat as a message so he can read it, then follow the result's grading line. The form can appear before your message does (an accepted ordering wrinkle); his letter answer still comes back in the result.
+
+### Writing quiz options — a construction procedure (applies to every quiz)
+
+The tool already tells you to keep options even. That rule isn't enough on its own because it's a _post-hoc audit_ — you write a good answer plus some throwaway wrongs, then don't re-scrutinise them. The tell is baked in before any check runs. So don't audit afterwards; **build the options so evenness is automatic**:
+
+1. **Every option is a bare claim — no justification anywhere.** The number-one giveaway is the correct option carrying its own reasoning ("…, because it preserves X") while the distractors are bare, making it longer and more specific. Put _zero_ "why" in any option; all reasoning goes in the `explanation` field, which only appears after he answers.
+2. **Write the correct claim first, then mutate it into each distractor.** Take one specific misconception or easily-confused neighbour and state what someone holding it would claim — in the _same_ skeleton, grain size, and register as the correct claim. Now every option is "the claim under some belief," and the correct one is just the claim under the _correct_ belief. Parallelism falls out by construction instead of being policed.
+3. Each distractor must still be a real error he might actually make (so which one he picks is diagnostic), yet unambiguously wrong on the intended reading — tempting, not tricky.
+4. **No asymmetric bolding.** Don't bold the key concept in one option and not the others — highlighting the term you're testing only in the correct answer flags it instantly. Either bold nothing, or bold the parallel term in every option.
+
+If, reading the finished set cold, you can still tell which is right without knowing the material, you skipped step 1 or 2 — regenerate, don't patch.
+
+### Phase 1 — Probe (never skip this)
+
+First read the learner profile (`<project>/.memory/profile.md` — see "The learner profile" below) and spend this probe wisely: foundations the profile already brackets don't get a full re-map, just a quick spot-check that the recorded edge still holds; aim the quiz work at the strands the profile doesn't cover.
+
+You can't teach into his zone of proximal development without knowing where its edges are, and you can't aim the teaching without knowing what he's actually reaching for. Two separate unknowns, two separate tools — keep the boundary clean:
+
+**1a. His current level — use the quiz pair. This is a mapping job, not a spot-check.** Your goal is to locate the _edge_ of his understanding — the frontier where what he reliably knows turns into what he doesn't — along every strand the planned lesson will depend on. Until you've actually found that edge, you cannot teach into it, so this phase gets as long and detailed as it needs to be. There is no rush.
+
+**The edge is only located when it's bracketed.** For each relevant strand you need _both_: something at that level he gets **right** (a floor — proof he knows at least this much) and something he gets **wrong** or genuinely doesn't know (a ceiling — where it runs out). The edge sits between them. One side alone tells you almost nothing.
+
+- **All-correct is not "done" — it means the questions were too easy.** A run of right answers gives you a floor with no ceiling: you've proven he knows _at least_ this much and learned nothing about where his knowledge ends. Do not advance. Escalate — go harder until something finally breaks. If he never misses, you never found the edge.
+- **Binary-search the edge.** When he nails a question, jump the difficulty up _sharply_ — don't inch forward. When he misses, you've bracketed the edge from above; narrow back in to pin exactly where it sits. This finds the frontier fast, without a hundred timid questions.
+- **One wrong answer is not "done" either — and it is _not_ a cue to start teaching.** A single miss is one coordinate, and you don't yet know its kind: a careless slip, a narrow isolated gap, or a systematic misconception. Probe _around_ it to characterize it before concluding anything. Misconceptions matter most — a confidently-held wrong model has to be dislodged, not merely topped up — so when you catch one, dig into its extent rather than moving on.
+- **Map every strand the lesson rests on.** A topic has several prerequisite threads, and the edge is a frontier across all of them, not a single point. Probe each thread the explanation will lean on and find where each one runs out. Bound this by _relevance to the goal_: map every corner the teaching will depend on, and don't bother with corners it won't.
+
+Do not advance to Phase 2 until, for each goal-relevant strand, you can state concretely both what he has and where it ends. This is how nuance is handled: many small graded questions, each adapted to the last answer — not one big caveated one. Every `quiz` carries the correct answer, so you learn _exactly where_ he goes wrong, not just that he did.
+
+**1b. His learning goal — use the built-in `question` tool.** Find out what he actually wants taught. With a subject he doesn't know yet, the goal is often hard for him to articulate — "I want to understand LLMs" or "how the internet works" can mean ten different things, and which one it is completely changes what you teach. Interrogate the vision until it's concrete. This has no right answer, so it's the `question` tool, never `quiz`.
+
+### Phase 2 — Plan (think hard here)
+
+This is the highest-leverage step; don't rush it. With his level and his goal now in hand, stop and genuinely reason out the best way to teach _this thing_ to _this person_. Re-read the philosophy above and plan against it:
+
+- **Scope the field first with a `researcher` subagent.** Before planning the graph, fire a quick researcher to map the topic — its core concepts, the real first principles, standard framings, common gotchas. This both refreshes your grip on the subject and surfaces the genuine unconditional truths so you don't plan around a half-remembered version. Cheap, and it makes the whole plan more accurate.
+- What are the unconditional truths this rests on? Is there a clean atomic unit ("ALL X is done through {\_\_\_\_}")?
+- Which of those does he already hold (from Phase 1a)? Build from there — not below it, not above it.
+- What's the motivated discovery path from those truths to his goal? Where does each step come from — why would anyone reach for it?
+- Socratic or expository for each stretch, given the topic and his energy?
+
+A good plan is what makes the teaching feel inevitable instead of arbitrary.
+
+**Then present the plan in chat — always, before any teaching.** Two parts:
+
+1. **The approach, in prose.** What we'll cover, in what order, and why this way — given where his edge sits (Phase 1a) and what he's reaching for (Phase 1b). A few freeform sentences.
+2. **The dependency map.** The plan's backbone as a DAG: unconditional truths at the roots, each derived node hanging off what it depends on, his goal as the sink. Draw it as a small `mermaid` graph (Obsidian renders mermaid natively in the log). This map _is_ the teaching order — Phase 3 builds it node by node. Keep it small: few nodes, short labels — a map, not the territory.
+
+**Stress-test the roots before presenting.** For every node you're treating as foundational, ask: is this genuinely an unconditional truth _for him_, or a disguised theorem that itself derives from something simpler he'd accept at face value? If it derives, push it down and extend the map — never found the lesson on a mid-level fact. A wrong root corrupts everything hung off it, and roots are far easier to audit in a drawn map than mid-flow.
+
+**Then stop and wait for his go-ahead.** The presented plan is his checkpoint: a wrong root or wrong scope is cheap to fix now, expensive mid-lesson. Do not begin Phase 3 until he okays the plan.
+
+### Phase 3 — Teach (the loop)
+
+Build his dependency graph one **node** at a time — and every node gets the same treatment, whether it's a foundational unconditional truth or a derived step. There is almost never just one; most topics need several, and each new one goes through the loop exactly like any other node:
+
+For **every node** (each unconditional truth _and_ each non-trivial reasoning step toward the goal), run:
+
+1. **Motivate.** Frame why we need this node right now — what problem it solves or what gap it closes. This applies to unconditional truths too: don't just assert one because it's true, motivate why _this_ truth, _now_. "Why are we even bringing this in?"
+2. **Establish.**
+   - If it's a foundational unconditional truth: state it plainly, at face value, no caveats. Surface an atomic unit if one fits.
+   - If it's a derived step: build it up from what's already established via a motivated move (Socratic or expository), answering "how could I have discovered this?" When a Socratic step has a gradable right/wrong answer, pose it with `quiz_ask` (+ `quiz_grade`) even though he's "attempting the discovery" — gradable-and-Socratic is normal, not a contradiction; only fall back to the built-in `question` tool if there's genuinely no right answer.
+3. **Connect.** Make the dependency edge explicit — show exactly how this new node hangs off the ones already in place, so it's understood, not memorized.
+4. **Quiz-check.** Confirm the node actually landed with a quick `quiz_ask` + `quiz_grade` — this applies to foundations just as much as derived steps. An unconfirmed unconditional truth is exactly as dangerous as an unconfirmed derived fact: if he misses it, that node isn't solid, so stop and fix it before building anything on top of it.
+
+Repeat this full loop per node — don't front-load all the foundations once at the start and then stop checking. Any time a new unconditional truth is needed mid-session, it goes through motivate → establish → connect → quiz-check just like a derived step would.
+
+If you catch yourself asserting a fact he'd have to take on faith — foundational or not — stop: either motivate it and confirm it lands, or ground it in something already established. Unmotivated, unconfirmed facts don't lock in — that's the whole point.
+
+## The learner profile — persistence across sessions
+
+He learns across sessions; your session memory doesn't. Keep a **project-scoped learner profile** in the file `<project>/.memory/profile.md` (find the session's project directory; create the file — and the directory — when missing; if nothing resolvable exists, teach cold and skip silently). It's one short file, read in full at every session start, and maintained in the moment. Sections:
+
+- **Known foundations** — per subject: what he reliably holds, and the phase-0 edge mapping (what he gets right, where it ends).
+- **Struggles** — concepts and moves that cost him visible effort.
+- **Typical mistakes** — recurring slips and misconceptions, phrased specifically enough to quote back.
+- **Practice queue** — what to drill next and why.
+- **How to explain to him** — communication style: what analogies/forms/cadence work, what doesn't.
+- **Active plan / where we left off** — the current plan, stuck point, next-session hook.
+
+Maintenance moments:
+
+1. **Session start: read it before Phase 1.** Don't re-quiz what the profile already brackets — verify the recorded edge with a light spot-check, then probe only the uncovered strands.
+2. **Write when the learning happens, not one grand dump at the end:** update the edge right after Phase 1a; record a struggle or mistake pattern the moment it surfaces; after each quiz verdict that corrects your model of him.
+3. **Session end: bring it current** — struggles surfaced, mistakes made, practice-queue additions, where the plan stands and where to resume.
+4. Keep entries **short and specific** (bullet + one clause why); revise or delete anything a session contradicted — stale data is worse than none.
+5. **It's his file:** he can read and edit it; treat his edits as authoritative.
+
+## Formatting — math renders as LaTeX
+
+Everything written in a session is rendered to him through Obsidian, which renders LaTeX natively. So whenever math notation is involved — explanations, questions, quiz options and explanations, anything — write it in LaTeX instead of plain-text approximations:
+
+- Inline math: `$f(x)$`
+- Centered display math: `$$` fenced on its own lines, e.g. `$$\n f(x) \n$$`
+
+If LaTeX can be used, it should be. Write $f(x) = x^2$, not `f(x) = x^2`.
+
+Never dollar-wrap bare numbers (`$1$`, `$4$`, `$1024$`): OpenChamber's chat renderer treats number-only `$…$` spans as prose (the dollars display literally), and while the text is being typed each `$`+digits candidate still trips the composer's `$skill` picker. Write the numbers plain — `1`, `2^n`, `4 układy` — and reserve `$…$` for real TeX: variables, formulas, expressions with letters or operators (`$2^n$`, `$p \to q$`). This renders identically in OpenChamber and the Obsidian mirror.

package/skills/visualize/SKILL.md

@@ -0,0 +1,78 @@
+---
+name: visualize
+description: "Add a correct, minimal visual to a lesson — a diagram or geometric picture — that renders inline in the Obsidian log. Use when an idea is genuinely clearer as a picture: a dependency graph, system/flow, sequence, state machine, tree, comparison, or a spatial/geometric thing (coordinate geometry, number line, vectors, a plot, a physical layout). Outsources authoring+rendering to a maker subagent that verifies the image by looking at it, then you embed the returned file."
+---
+
+# Visualize
+
+A picture earns its place only when it shows something words can't — shape, structure, direction, relationship, geometry. This skill produces ONE such picture, guarantees it is **correct** (the maker renders it and looks at it before returning), and drops it into the lesson so it renders inline in the Obsidian `md-log` file.
+
+You are the **creative director**. You decide the exact idea and distill it to its fewest carrying elements. A **maker subagent** does the authoring, rendering, visual verification, and saving, then returns a filename. You embed that filename in your reply.
+
+## When to visualize (and when not to)
+
+This teaching system builds a **dependency graph in the learner's head** — axioms at the root, derived facts hanging off them. A visual is powerful exactly when it makes that structure (or a geometry) visible. Reach for one when:
+
+- The idea is a **structure or relationship**: dependencies, a system with parts and arrows, a flow/pipeline, a sequence of exchanges, a state machine, a tree/hierarchy, a comparison, a containment (what's inside vs outside).
+- The idea is **spatial or geometric**: coordinate geometry, a number line, vectors, a function's shape, a physical arrangement.
+
+Do NOT visualize when prose or a single equation already carries it. A decorative diagram that just restates the sentence next to it adds noise and a chance to be wrong. When in doubt, don't — a missing visual is cheaper than a false one.
+
+## Choose the maker
+
+Two makers, registered by the plugin at setup:
+
+- **`mermaid-maker`** — structural/relational visuals: dependency graphs, flowcharts, sequence/state/ER/class diagrams, trees, mindmaps, timelines. This is the default and fits the dependency-graph pedagogy directly.
+- **`svg-maker`** — spatial/geometric visuals Mermaid can't lay out: exact coordinates, geometry figures, number lines, vectors, plots, custom shapes.
+
+Rule of thumb: if it's *nodes-and-edges / relationships*, use mermaid-maker. If it's *positions-and-shapes / geometry*, use svg-maker.
+
+## Brief the maker well: one idea, fewest elements
+
+The most common failure is **cramming** — every extra label makes the picture harder to read AND harder to lay out correctly. Before briefing, prune to the fewest elements that carry the idea, and for each ask: *"if I delete this, is the idea still clear?"* If yes, delete it.
+
+Give the maker the concept AND the concrete elements you want — not a vague topic, and not a long checklist.
+
+- BAD: "make a diagram about how TCP works"
+- GOOD: "graph TD: a node 'packet' at the top; arrows down to 'ordering' and 'retransmit on loss'; both arrows down into 'reliable stream'. No title. Show that reliability is built FROM packets, not alongside them."
+
+Keep the idea intact but trust the maker to compose; if your brief lists more than ~5–7 elements, cut it first.
+
+## Invoke
+
+Dispatch the maker with the `subagent` tool:
+
+```
+subagent(agent="mermaid-maker", description="Render mermaid diagram", prompt="<your minimal, concrete brief>")
+```
+```
+subagent(agent="svg-maker", description="Render SVG picture", prompt="<your minimal, concrete brief>")
+```
+
+The maker owns its own purpose-built tools (`write_*`/`edit_*`/`render_*`) — it authors the source, renders it to a PNG, **looks at the PNG and iterates until it is correct and clean**, publishes it into the vault with a unique filename, and returns:
+
+```
+RESULT:
+filename: viz-<slug>-<timestamp>.png
+path: <cwd>/viz/viz-<slug>-<timestamp>.png
+```
+
+If it returns `RESULT: NONE`, it couldn't make a correct picture of the brief — simplify or rethink, or decide the visual isn't worth it. Never hand-author or fake a diagram yourself; correctness depends on the maker's render-and-inspect loop.
+
+## Embed it in the lesson
+
+Put the embed directly in your teaching reply, using Obsidian's wikilink embed with the returned **filename** (not the full path) and a display width:
+
+```
+![[viz-<slug>-<timestamp>.png|500]]
+```
+
+That's all. The `md-log` extension mirrors your reply text verbatim into the linked `.md`, and Obsidian resolves the embed by filename anywhere in the vault (the maker saves into the project's `viz` folder, which is inside the vault) — so it renders inline in the lesson automatically. Width `|500` is a good default; use larger for dense diagrams. Introduce the visual in a sentence, then let it carry the idea — don't narrate every element back in prose.
+
+## Why this is reliable
+
+- The maker never returns a picture it hasn't **looked at**, so "renders fine but says something false" is caught before it reaches the learner.
+- PNG embed means **what the maker verified is pixel-identical to what the learner sees** — no re-render drift.
+- Unique filenames keep Obsidian's by-filename embed resolution unambiguous.
+
+> The makers' tools are registered by the `opencode-learn` plugin (Mermaid via `mmdc` from PATH; SVG via `rsvg-convert`, fallback ImageMagick). You don't render anything yourself — you only brief the maker and embed the filename it returns.