@unoverse-platform/studio 0.1.45 → 0.1.47

package/vendor/skills/unoverse-create/references/template.md

@@ -1,10 +1,14 @@
 # Playbook: Templates (MCP apps)
 
-**Read first:** `docs/design/templates.md` (layouts + manifest-as-envelope) +
-`docs/design/state.md` (the state model). Deep law: `UNOVERSE_STATE_MODEL.md` §5
-(the six rules), `UNOVERSE_LAYERS.md`. Everything in the component playbook (closed
-vocabulary, tokens, scale steps) applies here too. **Study the exemplar before
-writing**: `rx/sab/templates/sab-chat-layout` is the canonical State Model v2 template.
+**Read first:** [design/templates](https://docs.unoverse.ai/design/templates.md)
+(layouts + manifest-as-envelope) +
+[design/state](https://docs.unoverse.ai/design/state.md) (the state model). Deep law:
+[UNOVERSE_STATE_MODEL](https://docs.unoverse.ai/unoverse/UNOVERSE_STATE_MODEL.md) §5
+(the six rules), [UNOVERSE_LAYERS](https://docs.unoverse.ai/unoverse/UNOVERSE_LAYERS.md).
+Everything in the component playbook (closed vocabulary, tokens, scale steps) applies
+here too. **Study an exemplar before writing**: read the closest installed template
+through Studio's MCP (`listDefinitions` kind `template` → `readDefinition`); the
+canonical manifest tree is inlined below. (Monorepo: `design/sab/templates/sab-chat-layout`.)
 
 ## THE model: the component drives; the template reacts by name
 
@@ -23,7 +27,7 @@ template knows it = a base substate or template state.**
 
 ## The manifest states tree: one declaration, everything follows
 
-The canonical shape (`rx/sab/templates/sab-chat-layout/manifest.yaml`):
+The canonical shape (a chat layout: a base arrangement plus a reaction ladder):
 
 ```yaml
 states:
@@ -64,7 +68,7 @@ states:
 ## The anatomy: manifest-only (NO `<name>.yaml` envelope)
 
 ```
-apps/unoverse/rx/<project>/templates/<name>/
+design/<project>/templates/<name>/
   manifest.yaml    # THE ENVELOPE: the whole app contract, incl. the states tree
   layouts/         # the ARRANGEMENTS: one per state that owns one (same-name default)
     main.yaml      #   the base: the core alone
@@ -84,7 +88,8 @@ ComponentSlot selecting the matching view.
 
 Required: `name` · `description` (what it IS, ≤120) · `whenToUse` (utterance-shaped: the
 USER's words; findIntent ranks on it, the OPENING words carry the ranking; disqualify by
-property, never by naming siblings; full contract: docs/design/05 §Naming) ·
+property, never by naming siblings; full contract:
+[design/templates](https://docs.unoverse.ai/design/templates.md) §Naming) ·
 `category` · `defaultState: "template"` (the app-level LOAD state, a protocol field,
 nothing to do with component views) · `inputSchema` · `layout` (the BASE layout name) ·
 `states` (the tree above) · `binding` (`workflow` + `trigger`: the app OWNS its
@@ -154,7 +159,7 @@ template states by name exactly as in chat. Audio is never wired in a definition
 
 ## New project?
 
-`rx/<project>/` = `templates/` + optional `components/` (project-private microapps;
+`design/<project>/` = `templates/` + optional `components/` (project-private microapps;
 names unique within the project and never shadowing a marketplace name; two projects
 may share a name, each addressed `<org>/<name>`) + `styles/` holding ONLY the org's
 overrides (the foundation cascades per token; the theme file is the one you copy

package/vendor/skills/unoverse-prompt-component/SKILL.md

@@ -1,11 +1,11 @@
 ---
 name: unoverse-prompt-component
-description: Build or audit a PROMPT component (a briefed, AI-filled Unoverse component) in rx/. Use when adding brief tags, deciding which props an agent may fill, debugging a part the agent never fills or fills wrongly, or checking what a component's MCP tool schema actually contains. Covers the traps that silently discard an authored brief.
+description: Build or audit a PROMPT component (a briefed, AI-filled Unoverse component) in design/. Use when adding brief tags, deciding which props an agent may fill, debugging a part the agent never fills or fills wrongly, or checking what a component's MCP tool schema actually contains. Covers the traps that silently discard an authored brief.
 ---
 
 # Prompt components: the parts an agent fills
 
-A prompt component is an ordinary `rx/` component whose bound nodes carry `brief` tags.
+A prompt component is an ordinary `design/` component whose bound nodes carry `brief` tags.
 The platform compiles those tags into the component's **MCP tool schema**, and that schema
 is the only instruction channel: no side-channel prompt, no per-component agent skill.
 `unoverse-create` covers authoring components in general; this skill is about the briefs.
@@ -19,19 +19,23 @@ one you wrote.
 
 ## Step 1 (do this first, and again at the end): compile the schema
 
+In the **platform monorepo**, run the bundled compiler from the repo root (it resolves
+`@unoverse-platform/base`):
+
 ```bash
 cp .claude/skills/unoverse-prompt-component/verify.ts ./verify.tmp.ts
 npx tsx verify.tmp.ts <org>/<component>   # e.g. better-alpha/deal-page
 rm -f verify.tmp.ts
 ```
 
-It must run from the repo root (it resolves `@unoverse-platform/base`). It prints every
-part the agent can fill, its description, and its limits. Read that output, not the YAML.
-
-Then, always: `node -e "import('./packages/base/src/lint/rx/index.mjs').then(m=>{const r=m.lintDefinitions();console.log(r.problems.length);r.problems.forEach(p=>console.log(p.level,p.file,p.msg))})"`
+It prints every part the agent can fill, its description, and its limits. Read that
+output, not the YAML. Then run the design lint
+(`node -e "import('./packages/base/src/lint/design/index.mjs').then(m=>{const r=m.lintDefinitions();console.log(r.problems.length);r.problems.forEach(p=>console.log(p.level,p.file,p.msg))})"`).
 
-The linter catches two of the five traps below by name. Read what it says rather than
-silencing it.
+In a **Studio developer workspace**, the same linter runs as Studio's publish lint (or
+the authoring MCP's `lintProject` tool); it catches two of the five traps below by
+name. Read what it says rather than silencing it, and always do the final proof in
+Step 6: one real fill.
 
 ---
 
@@ -73,8 +77,9 @@ are briefed or neither is.
 
 ## Step 3: put the brief on the node that BINDS the field
 
-This is the rule from the rulebook (docs/design/CLAUDE.md §3) and it is where authored
-briefs go to die.
+This is the rule from the rulebook
+([design/CLAUDE.md](https://docs.unoverse.ai/design/CLAUDE.md) §3) and it is where
+authored briefs go to die.
 
 ```yaml
 # COMPILES
@@ -114,7 +119,7 @@ silence it. Move them to the `Each`.
 
 ### Trap 3: a briefed atom drags a collection into the schema
 
-Briefs are collected from the **expanded** tree (`packages/base/src/markdown/collect.ts`).
+Briefs are collected from the **expanded** tree (the platform's brief collector).
 An `Each` is recorded whenever its template has briefed fields, whether or not the `Ref`
 itself carries a brief.
 
@@ -135,8 +140,8 @@ each other.
 ### Trap 5: counts that are layout, not preference
 
 If a strip renders `columns: "4"`, then `minItems: 4, maxItems: 4`. Note that `minItems`
-is **guidance only**: the compiler appends it to the description and never gates on it
-(`server/src/mcp/briefSchema.ts`). `maxItems` and `maxLength` are hard. A count that is
+is **guidance only**: the schema compiler appends it to the description and never gates
+on it. `maxItems` and `maxLength` are hard. A count that is
 genuinely structural cannot be enforced by the schema alone, so say so in the description.
 
 ---
@@ -159,18 +164,18 @@ abbreviate and never substitute characters. Say so in the page-level brief.
 ## Step 5: the workflow door
 
 If the component is filled by an agent inside a workflow rather than in chat, read
-`docs/unoverse/UNOVERSE_MCP_TEMPLATE_PROTOCOL.md` §The workflow door. The load-bearing law:
+`UNOVERSE_MCP_TEMPLATE_PROTOCOL.md` §The workflow door (platform spec; in the monorepo
+at `docs/unoverse/`). The load-bearing law:
 **a blank part is a valid final state.** A part the source does not cover stays blank, the
 `visibleWhen` guards render around it, and the page is complete. Gaps are orientation on
-the first read, never standing debt. This is implemented in
-`server/src/runtime/components/executor/briefService.ts`; a component that fights it burns
-every turn to `maxTurns` and returns an empty text output.
+the first read, never standing debt. The platform's brief service implements this; a
+component that fights it burns every turn to `maxTurns` and returns an empty text output.
 
 ### The agent node's system prompt stays ROLE-ONLY
 
 The service port already delivers everything else when the agent connects: the fill
-protocol (`briefService.ts` `getSchema.instructions` — survey once, batch fills, blanks
-are finished, stop when done — folded into the agent's system prompt by MCPServiceRouter),
+protocol (the brief service's `getSchema` instructions: survey once, batch fills, blanks
+are finished, stop when done; folded into the agent's system prompt by the service router),
 the content rules (each part's compiled brief), and the grounding law (injected into the
 schema description). A workflow agent's system prompt therefore carries ONE line of role
 ("You fill the page from this run's documents; the service's instructions and each part's