@ericrisco/rsc 2.0.20 → 2.2.0

package/skills/bro/evals/cases.yaml

@@ -1,62 +0,0 @@
-skill: bro
-
-# `bro` is the final-language pass: it rewrites an existing answer/draft or
-# drafts requested text in a natural register. It does not define a reusable
-# brand system, translate content, or choose a documentation/copy strategy.
-should_trigger:
-  - prompt: "Bro, escribe como un humano."
-    why: "A terse bro-style instruction after an answer is the canonical request to rewrite the last assistant message naturally."
-
-  - prompt: "Rewrite your last answer so it sounds like a person, not a consultant."
-    why: "The user wants a human-language pass over the previous answer while preserving its content."
-
-  - prompt: "Haz este correo más natural y directo, pero no cambies las fechas ni los compromisos."
-    why: "Rewriting a supplied draft while preserving facts and commitments is the skill's core contract."
-
-  - prompt: "Això sona escrit per una IA. Fes-ho més humà i sense tanta cerimònia."
-    why: "Catalan request to remove AI-shaped formality tests multilingual semantic triggering."
-
-  - prompt: "Can you say that again in plain language without all the corporate jargon?"
-    why: "The symptom is jargon and artificial formality rather than the skill name, but the needed action is the same rewrite."
-
-  - prompt: "Escríbeme una respuesta breve y humana para decirle que llegaremos un día tarde."
-    why: "The user requests new text rather than a rewrite, but explicitly wants the same natural, truthful voice."
-
-  - prompt: "Keep all the technical details, just make it sound less robotic."
-    why: "Humanizing without deleting precision exercises the distinction between plain language and simplification."
-
-should_not_trigger:
-  - prompt: "Define a reusable voice guide so every writer and channel sounds like our brand."
-    route_to: "brand-voice"
-    why: "A standing voice system is brand-voice; bro only performs a local writing pass."
-
-  - prompt: "Translate this onboarding email from English to Spanish and adapt the date and currency formats."
-    route_to: "translation-l10n"
-    why: "Translation and locale-aware adaptation are owned by translation-l10n, even when natural prose matters."
-
-  - prompt: "Turn this mixed README into a clean tutorial and API reference with runnable examples."
-    route_to: "technical-writing"
-    why: "Choosing documentation modes and restructuring technical docs is technical-writing, not a final tone pass."
-
-  - prompt: "Write the hero, value proposition and CTA for our pricing page."
-    route_to: "landing-copy"
-    why: "Conversion architecture and finished landing-page copy belong to landing-copy; bro may only polish its language afterward."
-
-  - prompt: "Rewrite this function to be simpler and remove the unnecessary abstractions."
-    route_to: "simplify-code"
-    why: "The requested source-code simplification is owned by simplify-code; 'rewrite' does not make it a prose task."
-
-  - prompt: "Revisa este README antes de publicarlo y dime qué frases suenan a IA, una por una."
-    route_to: "unslop"
-    why: "A named, per-phrase audit of an existing text before shipping is unslop's contract; bro rewrites the register instead of enumerating tells."
-
-capability:
-  - scenario: "The previous assistant answer is a long Spanish status update full of headings, repeated summaries, corporate jargon and fake enthusiasm. Rewrite it for a client while preserving a June 30 deadline, a EUR 2,400 price, one unresolved risk, two URLs and the original uncertainty."
-    must_include:
-      - "preserves June 30, EUR 2,400, both URLs, the unresolved risk and the original uncertainty exactly"
-      - "uses natural Spanish appropriate for a client rather than automatically becoming slangy or over-casual"
-      - "removes needless headings, repeated conclusions, corporate filler and canned enthusiasm"
-      - "uses concrete verbs and readable sentence rhythm without adding typos or forced fragments"
-      - "does not invent evidence, anecdotes, opinions, commitments or certainty"
-      - "returns the rewritten message without a meta preface or an explanation of the edits"
-      - "keeps any harness orientation clearly outside the client-ready artifact"

package/skills/eli5/SKILL.md

@@ -1,63 +0,0 @@
----
-name: eli5
-description: "Use when a topic must be explained from zero to someone who knows nothing about it: one page, big pictures, very few words, everyday analogies, no jargon and nothing assumed. NOT the smallest in-conversation visual for someone already following (that is `show-me`), NOT a course with exercises (that is `course-builder`)."
-tags: [eli5, explain, beginner, simple, analogy, no-jargon, explicame]
-recommends: [show-me, technical-writing, course-builder]
-profiles: [minimal, core, full]
-origin: risco
----
-
-# eli5 — explain it to someone who knows nothing
-
-The topic is whatever the user named. With no topic named, it is the one the conversation is already
-on. The audience is someone with **zero** background: no vocabulary, no context, no patience for a
-definition that needs another definition.
-
-## The contract
-
-1. **A page, not a paragraph.** The output is one self-contained HTML page, big visuals first, words
-   second. Open it when it is written.
-2. **Picture carries the idea, words label it.** If the page still makes sense with the text removed,
-   it is working. Aim for a caption per picture, not a paragraph per picture.
-3. **Everyday objects only.** Compare to things a person has physically handled: boxes, keys, queues
-   at a counter, post, a light switch. Never explain one unknown with another unknown.
-4. **Zero jargon, and zero smuggled jargon.** No term appears without being shown first. "It caches"
-   is jargon; "it keeps a copy nearby so it doesn't have to walk back" is the same fact.
-5. **Simple, never false.** When the simplification would make something untrue, say what got left
-   out, in one line, at the end. A comfortable lie is worse than a hard truth.
-6. **No condescension.** Simple words, adult tone. The reader is new to the topic, not a child.
-
-## The shape of the page
-
-```text
-one sentence: what this thing is, in words a stranger would use
-big picture 1 : the thing, drawn
-big picture 2 : the thing doing its job, step by step
-one line      : the part people get wrong
-one line      : what this explanation left out (only if it left something out)
-```
-
-Three to five visuals is the whole page. Inline SVG or plain HTML boxes beat any chart library here:
-the drawing has to be readable on a phone, at a glance, with no legend to study.
-
-```bash
-open path/to/eli5-<topic>.html
-```
-
-## Anti-patterns
-
-| Anti-pattern | Why it fails | Do this instead |
-| --- | --- | --- |
-| Define a term with two more terms | The reader loses the thread on line one | Show the thing, then name it |
-| A wall of text with one decorative image | That is a blog post with a picture | Picture first, caption second |
-| "Imagine you're a packet travelling…" | Cute framing, still abstract | Compare to an object the reader has held |
-| Simplify until it is wrong | The reader now has to unlearn it | Keep it true and name what you dropped |
-| Baby talk, emoji, exclamation marks | Talks down to the reader | Plain adult words, short sentences |
-| Five diagrams of the same idea | Repetition reads as padding | One picture per genuinely new idea |
-
-## Where this ends
-
-- Someone already following the conversation who needs the shape of one mechanism: `show-me`.
-- A structured curriculum with exercises, assessment and progression: `course-builder`.
-- Documentation an informed reader will keep coming back to: `technical-writing`.
-- Making an existing text sound human rather than simpler: `bro`.

package/skills/eli5/evals/README.md

@@ -1,22 +0,0 @@
-# Evals — eli5
-
-Two claims: that a from-zero request routes here instead of to the in-conversation visual skill or to
-teaching material, and that the loaded skill produces a page a genuine beginner can follow.
-
-## Triggering
-
-Load only `eli5` and run every prompt in 3–5 fresh sessions. A positive passes when `eli5` loads in a
-majority of trials; a negative passes when it stays quiet and the declared `route_to` skill is the
-real owner. Require at least 90% accuracy.
-
-`show-me` is the negative that matters: both are "explain it visually". The discriminator is the
-reader's starting knowledge, and it must survive any description edit on either side.
-
-## Capability
-
-Run the scenario without the skill and with it, same topic and one grader, three trials. The
-with-skill condition must satisfy at least 80% of the rubric and beat the baseline by at least 20
-percentage points.
-
-Grade the jargon point strictly: a baseline answer almost always keeps one unexplained term, which is
-exactly the failure the skill exists to prevent.

package/skills/eli5/evals/cases.yaml

@@ -1,54 +0,0 @@
-skill: eli5
-
-# `eli5` owns one move: a from-zero explanation of one topic, as a page of big
-# pictures and few words, for someone with no background at all. It does not own
-# in-conversation diagrams for someone already following, curricula, or docs.
-should_trigger:
-  - prompt: "Explícame qué es una API como si tuviera cinco años."
-    why: "The canonical from-zero request, named outright, in the user's own language."
-
-  - prompt: "My mum asked me what a VPN is. I need something she can actually look at."
-    why: "A named audience with zero background and an explicit ask for something visual."
-
-  - prompt: "eli5 how a blockchain works"
-    why: "The bare skill name plus a topic is the shortest form of the same request."
-
-  - prompt: "No tengo ni idea de esto. Empieza por lo más básico, sin palabras raras."
-    why: "Zero background plus an explicit no-jargon constraint, with no topic named: the topic is the current one."
-
-  - prompt: "Can you explain what an index is in a database, but for someone who has never programmed?"
-    why: "A technical topic aimed at a non-technical reader is the audience this skill is written for."
-
-  - prompt: "Necesito explicarle a mi cliente, que no es técnico, qué es un webhook. Que lo entienda de una."
-    why: "Explaining to a named non-technical third party is the same job, one step removed."
-
-should_not_trigger:
-  - prompt: "Show me the call order when the form is submitted, I'm lost in the code."
-    route_to: "show-me"
-    why: "The user is already inside the topic and needs one mechanism drawn, not a from-zero page."
-
-  - prompt: "Build a four-week course on SQL with exercises and a final project."
-    route_to: "course-builder"
-    why: "Curriculum, progression and assessment are course-builder; eli5 is a single explanation."
-
-  - prompt: "Write the getting-started docs for our SDK, with runnable examples."
-    route_to: "technical-writing"
-    why: "Reference and tutorial documentation is technical-writing, even when it must be beginner-friendly."
-
-  - prompt: "Make this paragraph sound less robotic before I send it."
-    route_to: "bro"
-    why: "A register and tone pass over existing text is bro; nothing here needs explaining from zero."
-
-  - prompt: "Design the hero section for our homepage so it feels premium."
-    route_to: "design-loop"
-    why: "Visual identity is the design area; eli5's visuals serve comprehension, not brand."
-
-capability:
-  - scenario: "A non-technical business owner asks what a webhook is, after two failed explanations that used the words 'endpoint', 'payload' and 'HTTP POST'."
-    must_include:
-      - "produces one self-contained page with three to five large visuals, not a wall of text"
-      - "uses an everyday physical analogy the reader has handled, not another abstraction"
-      - "introduces no term without showing the thing first, and never uses endpoint, payload or POST unexplained"
-      - "keeps the explanation true, and names in one line whatever was left out"
-      - "stays adult in tone: no baby talk, no emoji, no exclamation marks"
-      - "opens the page for the user instead of only writing the file"

package/skills/show-me/SKILL.md

@@ -1,140 +0,0 @@
----
-name: show-me
-description: "Use when the user needs to see how something works instead of reading about it: picks the smallest visual that carries the point — pseudocode, call tree, file tree, component tree, Mermaid, a shaped diff, or one HTML page. NOT visual identity (that is `design-loop`), NOT slides (that is `presentations`), NOT a from-zero explainer (that is `eli5`)."
-tags: [show-me, explain, diagram, visual, mermaid, diff, call-tree, ensename]
-recommends: [eli5, presentations, technical-writing, codebase-onboarding]
-profiles: [minimal, core, full]
-origin: risco
----
-
-# show-me — the smallest picture that answers the question
-
-A second paragraph never fixes the first one. Pick the smallest view that makes the point, put two
-lines of prose beside it, stop.
-
-## The contract
-
-1. **One form, chosen on purpose.** Read what the question is *about*, pick the matching form from
-   the table, draw that. Several forms in one answer is the failure mode, not thoroughness.
-2. **Only the parts that answer the question.** Keep the calls, files, props, states and boundaries
-   the user asked about. Everything else is noise that hides the answer.
-3. **Prose shrinks to fit.** No preamble, no "here is a diagram of". The picture leads; the words
-   caption it.
-4. **Real names.** Actual paths, actual function and component names, actual state values. A diagram
-   of `ServiceA → ServiceB` explains nothing.
-5. **Say so when there is nothing to draw.** A topic with no shape gets a straight answer in prose.
-   A decorative diagram costs the reader time and buys nothing.
-
-## Pick the form from what the topic is
-
-| The question is about | Draw | Why this one |
-| --- | --- | --- |
-| Logic, an algorithm, a decision | pseudocode | branches read top-down; syntax would distract |
-| What calls what at runtime | call tree | shows order and nesting, which prose loses |
-| UI structure | component tree, with state and module boundaries | ownership is the answer most of the time |
-| Which file is responsible for what | shallow file tree with one comment per entry | depth hides the point; one level shows it |
-| Interaction, control flow, data flow between pieces | Mermaid sequence or flow diagram | two-way traffic over time needs an axis |
-| What changes in a shape that already exists | `diff`, in the shape of the topic | the reader keeps their bearings |
-| Layout, visual state, a dense comparison | one self-contained HTML page | text cannot hold it |
-| Nothing with a shape | prose | see contract rule 5 |
-
-```text
-on(save)
-  if content is unchanged
-    return cached result
-  write new content
-  return fresh result
-```
-
-```text
-submitForm
-  createSession
-    persistPrompt
-    launchAgent
-  navigateToSession
-```
-
-```tsx
-<SessionPage> (apps/example/src/routes/session.tsx)
-  useSessionEvents()
-  <SessionToolbar>
-    <RunSkillButton> (packages/ui)
-```
-
-```text
-src/
-├── commands/       # parses user actions
-├── sessions/       # owns session state
-└── transport/      # sends API requests
-```
-
-```mermaid
-sequenceDiagram
-    participant User
-    participant UI
-    participant Daemon
-    User->>UI: choose command
-    UI->>Daemon: send expanded prompt
-    Daemon-->>UI: stream result
-```
-
-## The diff rule
-
-Use `diff` when the surrounding shape already exists and the point is what moves. **Match the diff
-to the topic**: a component change is a component diff, a layout change is a file-tree diff, a
-control-flow change is a pseudocode diff. A unified source diff for a structural change makes the
-reader rebuild the structure in their head.
-
-```diff
- src/
- ├── commands/
-+│   └── show-me.ts       # expands the slash command
- ├── sessions/
--└── transport.ts
-+└── transport/
-+    ├── client.ts
-+    └── stream.ts
-```
-
-```diff
- on(save)
--  write content
-+  if content is unchanged
-+    return cached result
-+  write new content
-+  invalidate cache
-```
-
-Show the whole block instead of a diff when most of it is new, when the omitted context would hide
-ownership or order, or when the user needs something copyable.
-
-## When it earns an HTML page
-
-Layout, visual state, a side-by-side comparison, or a concept too dense for a text diagram. One
-page, self-contained, real labels and real data, readable on a phone and on a desktop. Inherit the
-product's colours, type and spacing from where it lives; this skill borrows an identity, it never
-invents one. Then open it:
-
-```bash
-open path/to/show-me-<topic>.html
-```
-
-## Anti-patterns
-
-| Anti-pattern | Why it fails | Do this instead |
-| --- | --- | --- |
-| Ship four forms because each adds a little | The reader now has to pick; that was your job | One form, the smallest that answers it |
-| Diagram the whole system when asked about one path | The answer is in there somewhere, which is the same as absent | Draw the path, drop the rest |
-| Placeholder names (`ModuleA`, `doThing`) | Nothing maps back to the codebase | Real paths and real identifiers |
-| A unified source diff for a structural change | Forces the reader to rebuild the shape | Diff in the shape of the topic |
-| Mermaid for a layout question | Boxes and arrows cannot show visual space | One HTML page |
-| A diagram to look thorough | Costs attention, adds nothing | Answer in prose and say why there is nothing to draw |
-
-## Where this ends
-
-- The visual **identity** of an interface, a landing page or a poster is `design-loop` and `design`.
-- A **deck** someone presents from is `presentations`.
-- **Zero prior knowledge**, big pictures, few words, is `eli5`.
-- Restructuring a document, a README or a reference is `technical-writing`.
-- A guided tour of an unfamiliar repository is `codebase-onboarding`; this skill draws the pieces it
-  finds, it does not run the tour.

package/skills/show-me/evals/README.md

@@ -1,23 +0,0 @@
-# Evals — show-me
-
-Two claims are under test: that "show me / I don't get it / draw me" routes here without stealing
-design, deck or beginner-explainer work, and that the loaded skill answers with **one** well-chosen
-visual instead of more prose.
-
-## Triggering
-
-Load only `show-me` and run every `should_trigger` and `should_not_trigger` prompt in 3–5 fresh
-sessions. A positive passes when `show-me` loads in a majority of trials. A negative passes when it
-stays quiet and the declared `route_to` skill is the genuine owner. Require at least 90% accuracy.
-
-The negatives that matter most are `eli5` and `design-loop`: both are adjacent enough that a sloppy
-description pulls them in. Re-run these two after any description edit.
-
-## Capability
-
-Run the scenario in two fresh conditions, without the skill and with it, same source discussion and
-one grader. Score each `must_include` point over three trials. The with-skill condition must satisfy
-at least 80% of the rubric and beat the baseline by at least 20 percentage points.
-
-The discriminating point is **form choice**: a baseline answer typically produces prose plus a
-generic box diagram. Count "picked one form, and the right one" strictly.

package/skills/show-me/evals/cases.yaml

@@ -1,61 +0,0 @@
-skill: show-me
-
-# `show-me` owns one move: the smallest visual that answers the question being
-# asked, placed inside the conversation. It does not own visual identity, decks,
-# teaching material for a beginner, or restructuring a document.
-should_trigger:
-  - prompt: "No entiendo cómo funciona el login. Enséñamelo."
-    why: "An explicit ask to be shown rather than told, about a mechanism that has a shape to draw."
-
-  - prompt: "Can you show me visually how these three services talk to each other?"
-    why: "Interaction between pieces over time is the canonical Mermaid sequence case."
-
-  - prompt: "Draw me the component tree of this page so I can see which component owns the form state."
-    why: "UI structure with an ownership question is the component-tree form, named outright."
-
-  - prompt: "Antes de tocar nada, qué archivo es responsable de qué en src/?"
-    why: "File responsibility maps to the shallow file tree; the user wants the shape before editing."
-
-  - prompt: "I read your explanation twice and still don't get the order things happen in. Picture?"
-    why: "A second failed prose attempt is the trigger this skill exists for; runtime order is a call tree."
-
-  - prompt: "Show me what would change in the folder layout if we split transport.ts into a module."
-    why: "A change to an existing shape is the shaped-diff case, with the diff in the topic's own form."
-
-  - prompt: "Explícame con un diagrama qué pasa cuando el usuario cancela a mitad del pago."
-    why: "An edge path through a flow, explicitly requested as a diagram."
-
-should_not_trigger:
-  - prompt: "Design the landing page for our new pricing tier, it should look premium."
-    route_to: "design-loop"
-    why: "Visual identity and composition are owned by the design area; show-me explains, it does not design."
-
-  - prompt: "Build me a 12-slide deck to present the roadmap to the board on Thursday."
-    route_to: "presentations"
-    why: "A deck someone presents from is presentations; this skill draws inside the conversation."
-
-  - prompt: "Explain how a database index works to someone who has never programmed, like they're five."
-    route_to: "eli5"
-    why: "Zero prior knowledge with big pictures and few words is eli5's contract, not the smallest in-context visual."
-
-  - prompt: "Reorganise this README into a proper tutorial and an API reference."
-    route_to: "technical-writing"
-    why: "Restructuring a document is technical-writing; a diagram inside it would be at most one paragraph of the job."
-
-  - prompt: "Walk me through this whole unfamiliar repo: what it does, how it's built, where to start."
-    route_to: "codebase-onboarding"
-    why: "A guided tour of an unknown codebase is its own skill; show-me only draws the pieces once they are known."
-
-  - prompt: "Build a dashboard with our monthly revenue and churn charts."
-    route_to: "dashboard"
-    why: "A standing analytics surface is dashboard; this is not an explanation of a mechanism."
-
-capability:
-  - scenario: "The user asks, after a dense prose answer, why saving a document sometimes does not trigger a re-render. The real cause is a cache check inside the save handler plus a subscription set up after navigation. Show them."
-    must_include:
-      - "picks one form rather than stacking several, and the form matches the topic (control flow or call tree, not a file tree)"
-      - "uses the real handler, cache and subscription names from the discussion instead of placeholders"
-      - "shows only the path involved in the bug, not the whole module"
-      - "puts at most two lines of prose beside the visual, with no 'here is a diagram of' preamble"
-      - "marks what changes with a diff in the topic's own shape if it proposes a fix"
-      - "does not produce an HTML page for something a text diagram already carries"