@damiangilgonzalez/harness 1.3.8 → 1.3.10

package/README.md

@@ -8,7 +8,7 @@
 
 [![npm](https://img.shields.io/npm/v/@damiangilgonzalez/harness?color=63d68a&labelColor=12161c&label=npm)](https://www.npmjs.com/package/@damiangilgonzalez/harness)
 [![downloads](https://img.shields.io/npm/dm/@damiangilgonzalez/harness?color=63d68a&labelColor=12161c&label=downloads)](https://www.npmjs.com/package/@damiangilgonzalez/harness)
-[![skills](https://img.shields.io/badge/skills-290-63d68a?labelColor=12161c)](#the-catalog)
+[![skills](https://img.shields.io/badge/skills-291-63d68a?labelColor=12161c)](#the-catalog)
 [![license](https://img.shields.io/badge/license-MIT-63d68a?labelColor=12161c)](LICENSE)
 [![stars](https://img.shields.io/github/stars/ericrisco/rsc-harness?color=63d68a&labelColor=12161c)](https://github.com/ericrisco/rsc-harness/stargazers)
 
@@ -202,7 +202,7 @@ $ rsc onboard
  ██████╗ ███████╗ ██████╗     ← animated gradient wordmark
  ██╔══██╗██╔════╝██╔════╝
  ██████╔╝███████╗██║
-  290 skills · one CLI · zero bloat
+  291 skills · one CLI · zero bloat
 
 How technical should the conversation be?
 How much accompaniment do you want?
@@ -241,7 +241,7 @@ rsc add youtube-api remotion-video   # …grow a channel, edit with Remotion
 rsc add fastapi --target claude,codex   # install into several assistants at once
 rsc install --profile minimal        # the base: orient + suggest + bro + unslop + show-me + eli5 + harness + init + teach
 rsc install --profile core           # floor + the full SDD workflow
-rsc install --profile full           # everything (all 290 skills)
+rsc install --profile full           # everything (all 291 skills)
 rsc install --profile full --without go
 rsc consult "I want to launch a SaaS"  # recommend only, no install
 rsc registry refresh                 # write .rsc/skill-registry.{json,md}
@@ -383,7 +383,7 @@ just asks in plain language.
 
 ## The catalog
 
-290 skills, grouped by what you're trying to do. Click any skill to read its
+291 skills, grouped by what you're trying to do. Click any skill to read its
 `SKILL.md`. It fires on its own when a task matches.
 
 ### 🧭 Core & control plane
@@ -423,11 +423,7 @@ Take a fuzzy intent to a shipped, verified change — phase by phase. `npx @dami
 
 [source-grounded-development](skills/source-grounded-development/) · [simplify-code](skills/simplify-code/)
 
-> The actual spec-first chain — clarify, specify, plan, break into tickets, build, verify, debug,
-> ship — now lives in the personal catalog below: `grill-with-docs`/`wayfinder` → `to-spec`
-> (+ `write-adr` for decisions) → `superpowers:writing-plans` → `superpowers:executing-plans`, or
-> `to-tickets` → `implement`, with `superpowers:systematic-debugging` for bugs and
-> `superpowers:verification-before-completion` before calling anything done. This section keeps
+> The actual spec-first chain lives in the personal catalog below, phase by phase. This section keeps
 > the two skills that stay stack-agnostic in-phase regardless of which chain built the code:
 > grounding an implementation or review in current version-specific docs, and simplifying working
 > code without changing its behaviour.
@@ -523,17 +519,101 @@ Three engines + engine-agnostic disciplines. Every engine skill pins the current
 
 [knowledge-ops](skills/knowledge-ops/) · [codebase-onboarding](skills/codebase-onboarding/) · [research-ops](skills/research-ops/) · [continuous-learning](skills/continuous-learning/) · [skill-scout](skills/skill-scout/) · [context-budget](skills/context-budget/) · [roast-me](skills/roast-me/) · [show-me](skills/show-me/) · [eli5](skills/eli5/) · [fable-operator](skills/fable-operator/)
 
-### 🇪🇸 Personal catalog — workflow (Spanish)
-
-The user's own 37-skill catalog, brought in as-is: bodies stay in Spanish, only each
-`description` was translated to English so Claude can still decide when to
-fire them. Split into a workflow half and an interface-design half.
-
-[grill-me](skills/grill-me/) · [grill-with-docs](skills/grill-with-docs/) · [grilling](skills/grilling/) · [wayfinder](skills/wayfinder/) · [to-spec](skills/to-spec/) · [to-tickets](skills/to-tickets/) · [to-questionnaire](skills/to-questionnaire/) · [implement](skills/implement/) · [revision-de-cambios](skills/revision-de-cambios/) · [code-review](skills/code-review/) · [research](skills/research/) · [prototype](skills/prototype/) · [domain-modeling](skills/domain-modeling/) · [handoff](skills/handoff/) · [write-adr](skills/write-adr/) · [wait-what](skills/wait-what/) · [writing-for-agents](skills/writing-for-agents/) · [claude-project-setup](skills/claude-project-setup/) · [muscle-memory](skills/muscle-memory/) · [teach](skills/teach/)
-
-### 🇪🇸 Personal catalog — interface design (Spanish)
-
-[animar](skills/animar/) · [diseno-apple](skills/diseno-apple/) · [diseno-landing](skills/diseno-landing/) · [ingeniero-diseno-web](skills/ingeniero-diseno-web/) · [leyes-de-percepcion](skills/leyes-de-percepcion/) · [leyes-de-retencion](skills/leyes-de-retencion/) · [mejor-accesibilidad](skills/mejor-accesibilidad/) · [mejor-colores](skills/mejor-colores/) · [mejor-layout](skills/mejor-layout/) · [mejor-redaccion](skills/mejor-redaccion/) · [mejor-tipografia](skills/mejor-tipografia/) · [mejor-ui](skills/mejor-ui/) · [sitios-calidad-premio](skills/sitios-calidad-premio/) · [tastemaker](skills/tastemaker/) · [video-a-superprompt](skills/video-a-superprompt/) · [vocabulario-animacion](skills/vocabulario-animacion/) · [revision-interfaz](skills/revision-interfaz/)
+### 🇪🇸 Personal catalog — spec-driven development (Spanish)
+
+The user's own 37-skill catalog, grouped by the phase of the cycle where each one is used.
+The full guide, in Spanish, with one page per phase and a version for teaching: [`docs/skills/`](docs/skills/).
+Bodies stay in Spanish; only each `description` was translated to English so Claude can still
+decide when to fire them.
+
+The source of truth is a written document, not a chat message. The chain, as the per-turn gate
+routes it:
+
+![The philosophy: spec-driven development](docs/img/00-filosofia.svg)
+
+Always: `superpowers:test-driven-development` and `superpowers:verification-before-completion`.
+Bugs start at `superpowers:systematic-debugging`.
+
+#### 1 · Plan
+
+Everything before code. What comes out is a spec and a plan, not an idea.
+
+![Plan phase flow](docs/img/01-planificar.svg)
+
+| Skill | What it does |
+|---|---|
+| [grill-with-docs](skills/grill-with-docs/) | Interrogates the plan and writes the glossary as it goes. The default way to ground an idea. |
+| [wayfinder](skills/wayfinder/) | Only when the work does not fit one session: a map of decision tickets. |
+| [to-spec](skills/to-spec/) | Turns the idea into a spec: what and why. `superpowers:brainstorming` is the alternative. |
+| [write-adr](skills/write-adr/) | Records every hard-to-reverse decision under `docs/adr/`. |
+| [research](skills/research/) | Investigates against primary sources and leaves the finding written and dated. |
+| [to-questionnaire](skills/to-questionnaire/) | Turns a decision you cannot make alone into a questionnaire for whoever can. |
+| [prototype](skills/prototype/) | A throwaway prototype to answer a design question. |
+| [to-tickets](skills/to-tickets/) | Splits the work into one-sitting tickets. Used after `wayfinder`. |
+| [claude-project-setup](skills/claude-project-setup/) | `CLAUDE.md`, rules, commands and agents. Once per repo. |
+
+`grilling`, `grill-me` and `domain-modeling` are installed but rarely called by hand: they run
+inside `grill-with-docs`.
+[grilling](skills/grilling/) · [grill-me](skills/grill-me/) · [domain-modeling](skills/domain-modeling/)
+
+#### 2 · Implement
+
+![Implement phase flow](docs/img/02-implementar.svg)
+
+| Skill | What it does |
+|---|---|
+| [implement](skills/implement/) | Builds one ticket from `to-tickets`. Ordinary work runs `superpowers:executing-plans` instead. |
+
+#### 3 · Interface
+
+When the work touches a screen. Sixteen overlapping skills; pick the one that matches the job.
+
+![Interface chain flow](docs/img/03-interfaz.svg)
+
+| Skill | What it does |
+|---|---|
+| [flujo-interfaz](skills/flujo-interfaz/) | The router: which design skill leads and in what order the rest follow. Start here when the work touches a screen. |
+| [ingeniero-diseno-web](skills/ingeniero-diseno-web/) | Runs the whole job: art direction, a declared design system, checkpoints and a scored critique. |
+| [diseno-landing](skills/diseno-landing/) | A conversion landing end to end: structure, copy and a strict visual system. |
+| [sitios-calidad-premio](skills/sitios-calidad-premio/) | Cinematic sites: GSAP, one smooth-scroll engine, Three.js only with a purpose. |
+| [animar](skills/animar/) | Decides in order whether to animate, why, with what, which properties, curve and duration. |
+| [diseno-apple](skills/diseno-apple/) | Fluid, physical motion: springs, interruptibility, velocity hand-off, materials. |
+| [mejor-layout](skills/mejor-layout/) | Grouping, alignment, reading order, breakpoints, RTL. |
+| [mejor-tipografia](skills/mejor-tipografia/) | Scale, line height, variable fonts, wrapping, truncation, punctuation. |
+| [mejor-colores](skills/mejor-colores/) | Ramps, semantic tokens, measured contrast, dark mode. |
+| [mejor-accesibilidad](skills/mejor-accesibilidad/) | Native before ARIA, focus, keyboard, hit areas, forms. |
+| [mejor-ui](skills/mejor-ui/) | Concentric radii, optical alignment, surfaces, icon transitions. |
+| [mejor-redaccion](skills/mejor-redaccion/) | Voice and tone, verb buttons, errors that say how to fix them, empty states. |
+| [tastemaker](skills/tastemaker/) | UI that does not look AI-made: pixel-measured colour, generated palettes. |
+| [leyes-de-percepcion](skills/leyes-de-percepcion/) | Gestalt for interfaces: proximity, similarity, figure-ground, hierarchy. |
+| [leyes-de-retencion](skills/leyes-de-retencion/) | Why people abandon a flow: Hick, Fitts, Miller, Jakob, Doherty, peak-end. |
+| [vocabulario-animacion](skills/vocabulario-animacion/) | Reverse glossary: turns "that thing that bounces" into the exact term. |
+| [video-a-superprompt](skills/video-a-superprompt/) | Turns a reference video into a detailed recreation prompt. |
+
+#### 4 · Review and close
+
+![Review and close flow](docs/img/04-revisar.svg)
+
+| The work | Order |
+|---|---|
+| Did not touch a screen | `code-review` |
+| Touched a screen | `revision-de-cambios` → `revision-interfaz` → `code-review` |
+
+| Skill | What it does |
+|---|---|
+| [code-review](skills/code-review/) | Two axes in parallel: the repo's standards and the spec. |
+| [revision-de-cambios](skills/revision-de-cambios/) | Reviews the change, reads the removed lines and classifies each finding. Only if it touched a screen. |
+| [revision-interfaz](skills/revision-interfaz/) | Runs the six `mejor-*` skills as one report with a verdict. Only if it touched a screen. |
+| [handoff](skills/handoff/) | Compacts the session into a handoff document. Optional. |
+
+#### 9 · Other
+
+| Skill | What it does |
+|---|---|
+| [teach](skills/teach/) | Teaching across sessions. |
+| [muscle-memory](skills/muscle-memory/) | A Python kata gym. |
+| [wait-what](skills/wait-what/) | Handbrake: stop and restate. |
+| [writing-for-agents](skills/writing-for-agents/) | How to write documents an agent consumes. |
 
 ---
 

package/manifest.json

@@ -1,7 +1,7 @@
 {
-  "version": "1.3.8",
+  "version": "1.3.10",
   "counts": {
-    "skills": 290,
+    "skills": 291,
     "agents": 33,
     "commands": 43,
     "fixedCommands": 10
@@ -1861,6 +1861,24 @@
       ],
       "profiles": []
     },
+    {
+      "id": "flujo-interfaz",
+      "description": "Use when work touches a screen — building or reshaping a landing, dashboard, app screen, component or prototype — to pick WHICH design skill leads and in what order the rest follow. Routes: direction first (diseno-landing or ingeniero-diseno-web), then motion, polish, originality and perception. NOT the review itself (that is `revision-interfaz`), NOT how the interface is wired (that is `ui-engineering`).",
+      "tags": [
+        "ui-design",
+        "routing",
+        "workflow"
+      ],
+      "recommends": [
+        "ingeniero-diseno-web",
+        "diseno-landing",
+        "revision-interfaz"
+      ],
+      "profiles": [
+        "ui",
+        "full"
+      ]
+    },
     {
       "id": "flutter",
       "description": "Use when building, structuring, testing or optimizing a Flutter app — feature-first layering, Riverpod 3 or Bloc, typed go_router, freezed models, a dio data layer, Material 3, jank hunting, widget/golden tests. Targets Flutter 3.44 / Dart 3.12. NOT React Native (that is `react-native`), NOT Compose Multiplatform (that is `compose-multiplatform`).",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@damiangilgonzalez/harness",
-  "version": "1.3.8",
+  "version": "1.3.10",
   "description": "A guided harness builder that turns your goal into a minimal, verified AI-agent setup using strict best practices.",
   "type": "module",
   "bin": {

package/scripts/lib/domains.js

@@ -28,7 +28,7 @@ export const DOMAINS = [
   { title: 'Design & content craft', ids: ['design-loop', 'design', 'design-dna', 'presentations', 'course-storytelling', 'course-builder', 'technical-writing', 'translation-l10n'] },
   { title: 'Knowledge & meta', ids: ['knowledge-ops', 'codebase-onboarding', 'research-ops', 'continuous-learning', 'skill-scout', 'context-budget', 'roast-me', 'show-me', 'eli5', 'fable-operator'] },
   { title: 'Personal catalog — workflow (Spanish)', ids: ['grill-me', 'grill-with-docs', 'grilling', 'wayfinder', 'to-spec', 'to-tickets', 'to-questionnaire', 'implement', 'revision-de-cambios', 'code-review', 'research', 'prototype', 'domain-modeling', 'handoff', 'write-adr', 'wait-what', 'writing-for-agents', 'claude-project-setup', 'muscle-memory', 'teach'] },
-  { title: 'Personal catalog — interface design (Spanish)', ids: ['animar', 'diseno-apple', 'diseno-landing', 'ingeniero-diseno-web', 'leyes-de-percepcion', 'leyes-de-retencion', 'mejor-accesibilidad', 'mejor-colores', 'mejor-layout', 'mejor-redaccion', 'mejor-tipografia', 'mejor-ui', 'sitios-calidad-premio', 'tastemaker', 'video-a-superprompt', 'vocabulario-animacion', 'revision-interfaz'] },
+  { title: 'Personal catalog — interface design (Spanish)', ids: ['flujo-interfaz', 'animar', 'diseno-apple', 'diseno-landing', 'ingeniero-diseno-web', 'leyes-de-percepcion', 'leyes-de-retencion', 'mejor-accesibilidad', 'mejor-colores', 'mejor-layout', 'mejor-redaccion', 'mejor-tipografia', 'mejor-ui', 'sitios-calidad-premio', 'tastemaker', 'video-a-superprompt', 'vocabulario-animacion', 'revision-interfaz'] },
 ];
 
 export function allDomainIds() {

package/skills/flujo-interfaz/SKILL.md

@@ -0,0 +1,87 @@
+---
+name: flujo-interfaz
+description: "Use when work touches a screen — building or reshaping a landing, dashboard, app screen, component or prototype — to pick WHICH design skill leads and in what order the rest follow. Routes: direction first (diseno-landing or ingeniero-diseno-web), then motion, polish, originality and perception. NOT the review itself (that is `revision-interfaz`), NOT how the interface is wired (that is `ui-engineering`)."
+tags: ["ui-design", "routing", "workflow"]
+profiles: [ui, full]
+recommends: [ingeniero-diseno-web, diseno-landing, revision-interfaz]
+---
+
+# Flujo de interfaz — quien manda en cada paso
+
+Hay dieciseis skills de diseno y se solapan. Esta skill no disena nada: decide **cual toca** y en
+que orden, para que ninguna pantalla se construya a ojo.
+
+**El orden, en una linea:** que dice -> como se ve -> como se mueve -> pulido -> originalidad ->
+psicologia.
+
+La direccion la marca una skill, nunca el criterio del agente. Empezar a escribir CSS sin haber
+elegido direccion es el error que esta skill existe para evitar.
+
+## Paso 1 · Direccion (obligatorio, elige UNA)
+
+| Construyes | Skill | Por que esa |
+|---|---|---|
+| Una landing, una web de marketing | `diseno-landing` | Es la unica que habla de negocio: oferta, objeciones, FAQ, reversion de riesgo, SEO. Su Parte B ya trae las reglas visuales. |
+| Cualquier otra cosa: dashboard, pantalla de app, prototipo, presentacion, visualizacion | `ingeniero-diseno-web` | Direccion de arte, design system declarado, 25 recetas ancladas y puntos de control que frenan a confirmar. |
+
+Para una landing no uses `ingeniero-diseno-web`: `diseno-landing` ya la cubre entera. Se solapan
+porque son de autores distintos que resolvieron lo mismo.
+
+Si el usuario no sabe que aspecto quiere, `ingeniero-diseno-web` propone tres escuelas con
+referencias reales antes de construir nada.
+
+## Paso 2 · Espectaculo, solo si toca
+
+`sitios-calidad-premio` para un lanzamiento, un portafolio o algo que tiene que impresionar: GSAP,
+un unico motor de scroll suave, Three.js solo con proposito.
+
+En un dashboard o una herramienta de uso diario, saltatela: el espectaculo se paga en cada uso.
+
+## Paso 3 · Movimiento
+
+- `animar` — decide en orden si debe animarse, con que proposito, herramienta, propiedades, curva y
+  duracion. Su puerta de frecuencia puede concluir que lo correcto es no animar.
+- `diseno-apple` — solo si hay gestos, arrastre u hojas deslizantes: muelles con fisica real,
+  interrumpibilidad, traspaso de velocidad.
+- `vocabulario-animacion` — cuando el usuario describe un efecto y no sabe como se llama.
+- `video-a-superprompt` — cuando aporta un video de referencia.
+
+## Paso 4 · Pulido
+
+`revision-interfaz` orquesta las seis `mejor-*` (layout, tipografia, colores, accesibilidad, ui,
+redaccion) y consolida un unico informe ordenado por severidad. Invoca una `mejor-*` suelta solo
+para una duda puntual de su terreno.
+
+## Paso 5 · Que no parezca de IA
+
+`tastemaker` va despues del pulido, porque necesita algo que auditar, y antes que las leyes, porque
+cambia estructura y no solo detalles. Tiene un modo auditar que no toca nada. Necesita Python.
+
+## Paso 6 · Psicologia
+
+- `leyes-de-percepcion` — que ve el ojo primero y como se agrupan las cosas.
+- `leyes-de-retencion` — por que se abandona un flujo a mitad. Su tabla sintoma -> ley es lo mas
+  rentable de las dieciseis.
+
+## Como se construye por dentro
+
+La arquitectura de la interfaz —limites de componentes, estado en la URL o en el componente,
+estados de carga, vacio y error, formularios, actualizacion optimista— es de `ui-engineering`, no
+de las skills de diseno. Las mecanicas del framework son de `angular`, `react` o `nextjs`.
+
+## Atajos
+
+| Situacion | Cadena |
+|---|---|
+| Landing nueva | `diseno-landing` -> `animar` -> `revision-interfaz` |
+| Dashboard o pantalla nueva | `ingeniero-diseno-web` -> `revision-interfaz` |
+| Pantalla que parece hecha por IA | `tastemaker` (auditar) -> `leyes-de-percepcion` |
+| Un flujo pierde usuarios a mitad | `leyes-de-retencion` -> `mejor-redaccion` -> `mejor-accesibilidad` |
+| Solo pulir lo que ya hay | `revision-interfaz` |
+
+## Donde encaja en la metodologia
+
+Esta cadena vive **dentro** del paso de construir, no lo sustituye. El trabajo sigue llegando con
+su spec escrita y su plan, y al cerrar se revisa igual: `revision-de-cambios` (que se ha roto),
+`revision-interfaz` (como esta la pantalla) y `code-review` (si hace lo que pedia la spec), antes
+de fusionar.

package/skills/flujo-interfaz/evals/cases.yaml

@@ -0,0 +1,32 @@
+skill: flujo-interfaz
+
+should_trigger:
+  - prompt: "Vamos a construir la pantalla de detalle de incidencia, por donde empiezo?"
+    why: "Trabajo que toca pantalla sin direccion elegida: flujo-interfaz decide que skill manda."
+  - prompt: "Tengo dieciseis skills de diseno y no se cual toca para esta pantalla."
+    why: "Disparador directo de flujo-interfaz: enrutar entre las skills de diseno."
+  - prompt: "Que skill de diseno uso para un dashboard nuevo?"
+    why: "La eleccion de direccion entre diseno-landing e ingeniero-diseno-web es de flujo-interfaz."
+  - prompt: "Empezamos el frontend de este modulo, cual es el orden de trabajo?"
+    why: "Pide el orden de la cadena de interfaz, que es lo que flujo-interfaz define."
+  - prompt: "Which design skill should lead this new app screen, and what comes after?"
+    why: "Disparador directo de flujo-interfaz en ingles: direccion primero, resto despues."
+
+should_not_trigger:
+  - prompt: "Revisa esta pantalla y dame un informe ordenado por severidad."
+    route_to: "revision-interfaz"
+    why: "Revisar la pantalla es el trabajo de revision-interfaz, no de flujo-interfaz, que solo enruta."
+  - prompt: "Donde guardo el estado de este formulario, en la URL o en el componente?"
+    route_to: "ui-engineering"
+    why: "La arquitectura de la interfaz es el trabajo de ui-engineering, no de flujo-interfaz."
+  - prompt: "Genera la paleta de colores de la marca desde cero."
+    route_to: "mejor-colores"
+    why: "Generar la paleta es el trabajo de mejor-colores, no de flujo-interfaz."
+  - prompt: "Implementa el endpoint que devuelve las incidencias del tecnico."
+    route_to: "implement"
+    why: "Un ticket de backend es el trabajo de implement, no de flujo-interfaz."
+
+capability:
+  - scenario: "El usuario va a construir una pantalla nueva y no sabe que skill de diseno manda."
+    must_include:
+      - "direccion"

package/skills/suggest/SKILL.md

@@ -33,9 +33,11 @@ The shape of the chain:
 
 - Still fuzzy, or an open question? Open with `grill-with-docs`; reach for `wayfinder` instead
   when the effort will not fit one sitting.
-- Once the shape is known, capture it as a spec, noting any call that would be costly to undo.
-- Size the build: a single sitting runs straight through its own plan-then-build pair; anything
-  bigger, or anything that grew out of the wayfinding step, gets broken into tickets first.
+- Once the shape is known, capture it as a spec, and give any call that would be costly to undo
+  its own ADR.
+- Build from a written plan. Tickets are the exception: only work that grew out of the
+  wayfinding step is broken into them first. A screen also routes through `flujo-interfaz`.
+- Review the finished change against the repo's standards and against the spec before merging.
 
 Two exceptions, and say out loud when you take one:
 
@@ -53,10 +55,11 @@ whole run — advance through the phases without re-asking.
 If a step's skill is not installed, offer to add it (§2) before routing. `implement` always
 pairs with test-driven development and a verification pass before anything is called done.
 
-Exact skill names and order: `grill-with-docs` or `wayfinder` -> `to-spec` (and `write-adr` for
-decisions) -> `superpowers:writing-plans` -> `superpowers:executing-plans`, or `to-tickets` ->
-`implement`. On Claude Code this rule also arrives as a per-turn hook; the brevity here is
-deduplication, not relaxation.
+Exact skill names and order: `grill-with-docs` or `wayfinder` -> `superpowers:brainstorming` or
+`to-spec` (and `write-adr` for decisions) -> `superpowers:writing-plans` ->
+`superpowers:executing-plans` (after `wayfinder`: `to-tickets` -> `implement`) -> `code-review`.
+On Claude Code this rule also arrives as a per-turn hook; the brevity here is deduplication,
+not relaxation.
 
 ---
 

package/targets/_md-block.js

@@ -20,7 +20,7 @@ export function writeSkill(id, fromDir, toPath) {
 export function wireHook(paths, sourceMd, policy = {}) {
   const full = stripFrontmatter(readFileSync(sourceMd, 'utf8'));
   const body = policy.codeHooks === false
-    ? `# rsc-suggest — always-on operations layer\n\nRead \`docs/wiki/harness/user-profile.md\` before acting. If the user wants to build, add or change something, route it through \`grill-with-docs\` or \`wayfinder\` then \`to-spec\` before any code, then build it with \`superpowers:writing-plans\` (or \`to-tickets\` then \`implement\` for ticket-sized work) — unless it is a one-line change, typo, or config bump, which skips the chain. Use \`orient\` to keep the user situated and \`suggest\` to offer a missing skill only when the current task needs it. Close with the configured orientation block.\n`
+    ? `# rsc-suggest — always-on operations layer\n\nRead \`docs/wiki/harness/user-profile.md\` before acting. If the user wants to build, add or change something, route it through \`grill-with-docs\` or \`wayfinder\`, then write the spec with \`superpowers:brainstorming\` or \`to-spec\` (decisions go to \`write-adr\`) before any code, then build it with \`superpowers:writing-plans\` (or \`to-tickets\` then \`implement\` when it came out of \`wayfinder\`), and review it with \`code-review\` before merging (si toca pantalla, \`flujo-interfaz\` dice que skill de diseno manda) — unless it is a one-line change, typo, or config bump, which skips the chain. Use \`orient\` to keep the user situated and \`suggest\` to offer a missing skill only when the current task needs it. Close with the configured orientation block.\n`
     : full;
   const block = `${MARK_START}\n${body}\n${MARK_END}`;
   let doc = existsSync(paths.hookTarget) ? readFileSync(paths.hookTarget, 'utf8') : '';

package/targets/hook-once.mjs

@@ -89,21 +89,25 @@ export function claimOnce(key, { dir = markerDir(), windowMs = 30_000, now = Dat
 // The workflow gate text lives here, not inline in userprompt-gate.mjs, so it has exactly one
 // definition: the hook emits it and `rsc doctor` measures it from the same constant. Anything
 // that reports a byte count for text it does not own drifts the moment the text changes.
-export const WORKFLOW_GATE_TEXT = `===== workflow gate (highest precedence) =====
-Before acting on this turn: if the user wants to BUILD, ADD or CHANGE something — in ANY
-language, judged by intent, not by keywords — route it through the chain below FIRST. No
-feature code is written by ANY skill until the what is clear and the user has approved it.
-1. Not clear yet? -> \`grill-with-docs\` for a green idea or an open question; \`wayfinder\`
-   when the work is too large to hold in one session.
-2. Clear? -> \`to-spec\` writes the spec. Record every hard-to-reverse call with \`write-adr\`,
-   which leaves its trail under docs/adr/.
-3. Then build. Pick by size, and ask when unsure: ordinary work goes
-   \`superpowers:writing-plans\` -> \`superpowers:executing-plans\`; work that came out of
-   \`wayfinder\`, or too large for one plan, goes \`to-tickets\` -> \`implement\`, ticket by ticket.
-Always: \`superpowers:test-driven-development\`, and \`superpowers:verification-before-completion\`
-before calling anything done. Bugs enter through \`superpowers:systematic-debugging\`.
-One-line change, typo, or config bump? -> skip the chain, do it, say so.
-==============================================
+export const WORKFLOW_GATE_TEXT = `===== workflow gate · metodologia (maxima prioridad) =====
+Si el usuario pide construir, anadir o cambiar algo (en cualquier idioma, se juzga la intencion),
+sigue esta cadena ANTES de escribir codigo. Ninguna skill escribe codigo de una feature hasta que
+el que esta claro y el usuario ha dado el visto bueno.
+1. Aclarar el que:
+   - Peticion concreta y acotada -> \`grill-with-docs\`.
+   - Tema amplio, o el usuario no sabe como abordarlo -> recomiendale \`wayfinder\`.
+   - \`superpowers:brainstorming\` vale para lo mismo si el usuario lo prefiere.
+   Cada decision dificil de revertir se registra con \`write-adr\`, en docs/adr/.
+2. Escribir la spec: \`to-spec\`, o \`superpowers:brainstorming\` para cerrarla por secciones.
+   Sin spec escrita no se programa.
+3. Construir: \`superpowers:writing-plans\` -> \`superpowers:executing-plans\`. Solo el trabajo que
+   salio de \`wayfinder\` va con \`to-tickets\` -> \`implement\`, ticket a ticket.
+   Si la tarea toca pantalla, invoca ademas \`flujo-interfaz\`: dice que skill de diseno manda.
+4. Antes de fusionar: \`code-review\` (estandares del repo + lo que pedia la spec).
+Siempre: \`superpowers:test-driven-development\` y \`superpowers:verification-before-completion\`
+antes de dar nada por terminado. Los bugs entran por \`superpowers:systematic-debugging\`.
+Cambio de una linea, typo o ajuste de configuracion -> hazlo y di que te saltas la cadena.
+==========================================================
 `;
 
 /**