@tacuchi/agent-workflow-cli 15.1.0 → 16.0.0

package/skills/w/commands/README.md

@@ -1,44 +1,44 @@
 # w — Command map (Layer 1)
 
-> README del namespace `/w:` (`w` = *workflow*): todo lo listado acá es lo **único que el usuario invoca** directamente. Los comandos son la **Capa 1** — single-pass o arrancan un loop; sin lógica de iteración.
+> README of the `/w:` namespace (`w` = *workflow*): everything listed here is the **only thing the user invokes** directly. Commands are **Layer 1** — single-pass or they start a loop; no iteration logic.
 >
-> **Canon**: el modelo completo (3 capas + zona `docs/`, los 3 flujos, invariantes duros) vive en [`../SKILL.md`](../SKILL.md); el **motor de los loops** en [`../loops/CHASSIS.md`](../loops/CHASSIS.md). Este README es solo el índice de la carpeta.
+> **Canon**: the full model (3 layers + `docs/` zone, the 3 flows, hard invariants) lives in [`../SKILL.md`](../SKILL.md); the **loop engine** in [`../loops/CHASSIS.md`](../loops/CHASSIS.md). This README is only the folder index.
 
 ---
 
 ## Bootstrap
 
-[`/w:workspace-init`](workspace-init.md) convierte la carpeta actual en un **workspace** (`.workflow/` + `docs/` + bloque `WORKSPACE` + `.workflow/skills.toml`). Sin distinción project/hub; correr una vez antes de cualquier flujo.
+[`/w:workspace-init`](workspace-init.md) turns the current folder into a **workspace** (`.workflow/` + `docs/` + `WORKSPACE` block + `.workflow/skills.toml`). No project/hub distinction; run once before any flow.
 
 ## Index
 
-| Command | Qué hace | Mode |
+| Command | What it does | Mode |
 |---|---|---|
-| [`workspace-init`](workspace-init.md) | Bootstrap del workspace | single-pass, interactivo |
-| [`spec-new`](spec-new.md) | Genera el borrador de spec (`docs/specs/NNN-spec-<slug>.md`) | single-pass, sin loop |
-| [`spec-refine`](spec-refine.md) | Refina el spec **in place** hasta desambiguarlo | arranca `spec-refine-loop` |
-| [`plan-new`](plan-new.md) | Deriva el plan ejecutable (`docs/plans/PPP-plan-<slug>.md`) del spec | arranca `plan-new-loop` |
-| [`plan-refine`](plan-refine.md) | Refina el plan **in place** antes de ejecutar (aux, opcional) | arranca `plan-refine-loop` |
-| [`plan-exec`](plan-exec.md) | Ejecuta el plan (código/BD/git) y lo mantiene como living doc | arranca `plan-exec-loop` |
-| [`quick`](quick.md) | Atajo liviano para trabajo acotado; no toca `docs/` | arranca `quick-loop` |
-| [`status`](status.md) | Dashboard read-only del workspace | single-pass (transversal) |
-| [`fix-git`](fix-git.md) | Resuelve un merge en curso, git-safe | single-pass (transversal) |
-| [`export-scripts`](export-scripts.md) | Promueve migraciones SQL de sesiones a `docs/scripts/` | single-pass, read-only |
-| [`export-manuals`](export-manuals.md) | Genera manuales en `docs/manuals/` | single-pass, read-only |
-| [`export-diagrams`](export-diagrams.md) | Genera diagramas C4/mermaid en `docs/diagrams/` | single-pass, read-only |
-| [`export-reports`](export-reports.md) | Genera informes en `docs/reports/` | single-pass, read-only |
-
-> **Asimetría intencional:** en SPEC, `spec-new` genera el borrador en single-pass (sin loop) y el loop está en `spec-refine`; en PLAN, los 3 comandos arrancan loops. Total: **6 comandos de flow / 5 loops**.
+| [`workspace-init`](workspace-init.md) | Workspace bootstrap | single-pass, interactive |
+| [`spec-new`](spec-new.md) | Generates the spec draft (`docs/specs/NNN-spec-<slug>.md`) | single-pass, no loop |
+| [`spec-refine`](spec-refine.md) | Refines the spec **in place** until unambiguous | starts `spec-refine-loop` |
+| [`plan-new`](plan-new.md) | Derives the executable plan (`docs/plans/PPP-plan-<slug>.md`) from the spec | starts `plan-new-loop` |
+| [`plan-refine`](plan-refine.md) | Refines the plan **in place** before executing (aux, optional) | starts `plan-refine-loop` |
+| [`plan-exec`](plan-exec.md) | Executes the plan (code/DB/git) and maintains it as a living doc | starts `plan-exec-loop` |
+| [`quick`](quick.md) | Lightweight shortcut for scoped work; never touches `docs/` | starts `quick-loop` |
+| [`status`](status.md) | Read-only workspace dashboard | single-pass (transversal) |
+| [`fix-git`](fix-git.md) | Resolves an in-progress merge, git-safe | single-pass (transversal) |
+| [`export-scripts`](export-scripts.md) | Promotes session SQL migrations to `docs/scripts/` | single-pass, read-only |
+| [`export-manuals`](export-manuals.md) | Generates manuals in `docs/manuals/` | single-pass, read-only |
+| [`export-diagrams`](export-diagrams.md) | Generates C4/mermaid diagrams in `docs/diagrams/` | single-pass, read-only |
+| [`export-reports`](export-reports.md) | Generates reports in `docs/reports/` | single-pass, read-only |
+
+> **Intentional asymmetry:** in SPEC, `spec-new` generates the draft single-pass (no loop) and the loop lives in `spec-refine`; in PLAN, all 3 commands start loops. Total: **6 flow commands / 5 loops**.
 >
-> **Transversales (no flow):** `status` y `fix-git` no pertenecen a SPEC/PLAN/QUICK ni cuentan en 6/5. En el diseño son su propia categoría (`workflow-skills/`); acá se empaquetan bajo `commands/` para que `/w:` las invoque — ver [`../harness/SKILL.md`](../harness/SKILL.md) § *Command packaging*.
+> **Transversal (no flow):** `status` and `fix-git` belong to no SPEC/PLAN/QUICK flow and do not count in 6/5. In the design they are their own category (`workflow-skills/`); here they are packaged under `commands/` so `/w:` can invoke them — see [`../harness/SKILL.md`](../harness/SKILL.md) § *Command packaging*.
 
 ## Schema of each command file
 
-Cada `<command>.md` de esta carpeta usa este frontmatter + estructura de cuerpo — el esquema (incluidos `allowed-tools:` y el tool `Skill`) es el **binding Claude Code**; otros arneses envuelven el mismo contrato en su formato (ver [`../harness/SKILL.md`](../harness/SKILL.md) § *Command packaging*):
+Every `<command>.md` in this folder uses this frontmatter + body structure — the schema (including `allowed-tools:` and the `Skill` tool) is the **Claude Code binding**; other harnesses wrap the same contract in their format (see [`../harness/SKILL.md`](../harness/SKILL.md) § *Command packaging*):
 
 | Field | Description |
 |---|---|
-| `description:` | One line: what + when (drives discovery in `/`-picker) |
+| `description:` | One line: what + when (drives discovery in the `/`-picker) |
 | `argument-hint:` | Argument signature for the user |
 | `allowed-tools:` | YAML list (typically `Bash`/`Read`/`Write`/`Edit`). Loops/exports are **read-and-followed**, not invoked with `Skill:` — so `Skill` is **not** in `allowed-tools`. |
 | Body | 1-3 orienting lines, then the invocation: **read-and-follow** the sibling loop/export `SKILL.md`, or call the `aw` CLI; then `## Plan mode`, `## Resources` |

package/skills/w/commands/export-diagrams.md

@@ -1,5 +1,5 @@
 ---
-description: Genera diagramas C4/mermaid en docs/diagrams/ a partir del código fuente y el plan-doc (AS-IS/TO-BE). Single-pass, explícito.
+description: Generates C4/mermaid diagrams in docs/diagrams/ from the source code and the plan-doc (AS-IS/TO-BE). Single-pass, explicit.
 argument-hint: [--engine <mermaid|c4>] [--sessions <ids>] [--dry-run]
 allowed-tools:
   [
@@ -9,21 +9,21 @@ allowed-tools:
   ]
 ---
 
-# export-diagrams — exportar diagramas
+# export-diagrams — export diagrams
 
-Lee el código de las fuentes del workspace + el plan-doc (secciones `AS-IS`/`TO-BE`) y genera diagramas C4 / mermaid en `docs/diagrams/`. Single-pass, read-only sobre sesiones.
+Reads the workspace sources' code + the plan-doc (`AS-IS`/`TO-BE` sections) and generates C4 / mermaid diagrams in `docs/diagrams/`. Single-pass, read-only over sessions.
 
-Para ejecutar: **leé** `../exports/export-diagrams/SKILL.md` y **seguí** sus instrucciones con `$ARGUMENTS` como input. No intentes `Skill: export-diagrams` (no está registrada por nombre); el SKILL.md hermano es el cuerpo de este export.
+To run: **read** `../exports/export-diagrams/SKILL.md` and **follow** its instructions with `$ARGUMENTS` as input. Do not try `Skill: export-diagrams` (it is not registered by name); the sibling SKILL.md is this export's body.
 
-## Qué produce
+## What it produces
 
-- `docs/diagrams/`: diagramas C4 y/o mermaid, numerados, cross-session.
-- **No** muta sesiones ni abre/cierra loops.
-- Solo escribe en `docs/diagrams/`.
+- `docs/diagrams/`: C4 and/or mermaid diagrams, numbered, cross-session.
+- Does **not** mutate sessions nor open/close loops.
+- Writes only `docs/diagrams/`.
 
 ## Plan mode
 
-Describe los diagramas que generaría (tipo, componentes cubiertos) sin escribir archivos.
+Describes the diagrams it would generate (type, covered components) without writing files.
 
 ## Resources
 

package/skills/w/commands/export-manuals.md

@@ -1,5 +1,5 @@
 ---
-description: Genera manuales de usuario/operación en docs/manuals/ consolidando sesiones, DECISION, plan-doc y código fuente. Single-pass, explícito.
+description: Generates user/operations manuals in docs/manuals/ consolidating sessions, DECISION, plan-doc and source code. Single-pass, explicit.
 argument-hint: [--sessions <ids>] [--mode <complement|regenerate>] [--dry-run]
 allowed-tools:
   [
@@ -9,21 +9,21 @@ allowed-tools:
   ]
 ---
 
-# export-manuals — exportar manuales
+# export-manuals — export manuals
 
-Consolida sesiones + artefactos `DECISION` + plan-doc (`Final behavior`) + código fuente y genera documentación de usuario/operación en `docs/manuals/`. Single-pass, read-only sobre sesiones.
+Consolidates sessions + `DECISION` artifacts + plan-doc (`Final behavior`) + source code and generates user/operations documentation in `docs/manuals/`. Single-pass, read-only over sessions.
 
-Para ejecutar: **leé** `../exports/export-manuals/SKILL.md` y **seguí** sus instrucciones con `$ARGUMENTS` como input. No intentes `Skill: export-manuals` (no está registrada por nombre); el SKILL.md hermano es el cuerpo de este export.
+To run: **read** `../exports/export-manuals/SKILL.md` and **follow** its instructions with `$ARGUMENTS` as input. Do not try `Skill: export-manuals` (it is not registered by name); the sibling SKILL.md is this export's body.
 
-## Qué produce
+## What it produces
 
-- `docs/manuals/`: manuales consolidados, cross-session, dedup.
-- **No** muta sesiones ni abre/cierra loops.
-- Solo escribe en `docs/manuals/`.
+- `docs/manuals/`: consolidated, cross-session, deduplicated manuals.
+- Does **not** mutate sessions nor open/close loops.
+- Writes only `docs/manuals/`.
 
 ## Plan mode
 
-Describe el alcance de los manuales que generaría (secciones, sesiones fuente) sin escribir archivos.
+Describes the scope of the manuals it would generate (sections, source sessions) without writing files.
 
 ## Resources
 

package/skills/w/commands/export-reports.md

@@ -1,5 +1,5 @@
 ---
-description: Genera un informe ejecutivo/funcional en docs/reports/ consolidando el corpus de sesiones (spec, CONCLUSIONS, DECISION), el plan-doc y el estado de docs/. Single-pass, explícito.
+description: Generates an executive/functional report in docs/reports/ consolidating the session corpus (spec, CONCLUSIONS, DECISION), the plan-doc and the docs/ state. Single-pass, explicit.
 argument-hint: [--sessions <ids>] [--audience <gerencia|tecnica>] [--dry-run]
 allowed-tools:
   [
@@ -9,21 +9,21 @@ allowed-tools:
   ]
 ---
 
-# export-reports — exportar informes
+# export-reports — export reports
 
-Consolida el corpus completo de sesiones (`CONCLUSIONS`, `DECISION`, spec) + plan-doc (estado) + `docs/` y genera un informe ejecutivo o funcional en `docs/reports/`. Single-pass, read-only sobre sesiones.
+Consolidates the full session corpus (`CONCLUSIONS`, `DECISION`, spec) + plan-doc (state) + `docs/` and generates an executive or functional report in `docs/reports/`. Single-pass, read-only over sessions.
 
-Para ejecutar: **leé** `../exports/export-reports/SKILL.md` y **seguí** sus instrucciones con `$ARGUMENTS` como input. No intentes `Skill: export-reports` (no está registrada por nombre); el SKILL.md hermano es el cuerpo de este export.
+To run: **read** `../exports/export-reports/SKILL.md` and **follow** its instructions with `$ARGUMENTS` as input. Do not try `Skill: export-reports` (it is not registered by name); the sibling SKILL.md is this export's body.
 
-## Qué produce
+## What it produces
 
-- `docs/reports/`: informe consolidado, cross-session, con dedup y estado de avance.
-- **No** muta sesiones ni abre/cierra loops.
-- Solo escribe en `docs/reports/`.
+- `docs/reports/`: a consolidated, cross-session report with dedup and progress state.
+- Does **not** mutate sessions nor open/close loops.
+- Writes only `docs/reports/`.
 
 ## Plan mode
 
-Describe el alcance e índice del informe que generaría (secciones, sesiones fuente, estado de avance) sin escribir archivos.
+Describes the scope and index of the report it would generate (sections, source sessions, progress state) without writing files.
 
 ## Resources
 

package/skills/w/commands/export-scripts.md

@@ -1,5 +1,5 @@
 ---
-description: Exporta scripts de BD (SCRIPTS.sql tipo-B) de N sesiones a docs/scripts/ como forwards numerados + rollback. Paso explícito y aparte — nunca automático.
+description: Exports DB scripts (type-B SCRIPTS.sql) from N sessions to docs/scripts/ as numbered forwards + rollback. Explicit, separate step — never automatic.
 argument-hint: [--sessions <ids>] [--dry-run]
 allowed-tools:
   [
@@ -9,21 +9,21 @@ allowed-tools:
   ]
 ---
 
-# export-scripts — exportar scripts de BD
+# export-scripts — export DB scripts
 
-Promueve los artefactos `SCRIPTS.sql` (tipo B — migraciones) de N sesiones de `.workflow/sessions/` a `docs/scripts/`. Single-pass, read-only sobre sesiones.
+Promotes the `SCRIPTS.sql` artifacts (type B — migrations) of N sessions from `.workflow/sessions/` to `docs/scripts/`. Single-pass, read-only over sessions.
 
-Para ejecutar: **leé** `../exports/export-scripts/SKILL.md` y **seguí** sus instrucciones con `$ARGUMENTS` como input. No intentes `Skill: export-scripts` (no está registrada por nombre); el SKILL.md hermano es el cuerpo de este export.
+To run: **read** `../exports/export-scripts/SKILL.md` and **follow** its instructions with `$ARGUMENTS` as input. Do not try `Skill: export-scripts` (it is not registered by name); the sibling SKILL.md is this export's body.
 
-## Qué produce
+## What it produces
 
-- `docs/scripts/`: forwards numerados de forma continua (cross-session, dedup) + `00-ROLLBACK.sql`.
-- **No** muta sesiones ni abre/cierra loops.
-- La IA **nunca ejecuta** los scripts — solo los consolida y entrega.
+- `docs/scripts/`: continuously numbered forwards (cross-session, dedup) + `00-ROLLBACK.sql`.
+- Does **not** mutate sessions nor open/close loops.
+- The AI **never executes** the scripts — it only consolidates and delivers them.
 
 ## Plan mode
 
-Describe los scripts que consolidaría y la estructura de `docs/scripts/` que generaría, sin escribir archivos.
+Describes the scripts it would consolidate and the `docs/scripts/` structure it would generate, without writing files.
 
 ## Resources
 

package/skills/w/commands/fix-git.md

@@ -1,5 +1,5 @@
 ---
-description: Resuelve conflictos de un merge en curso para una fuente dada o detectada. Identifica origen (theirs) y destino (ours), analiza la intención de ambos lados y resuelve; pregunta (structured-choice) ante ambigüedad o incoherencia. Git-safe — propone el commit de merge, nunca push/--amend/--no-verify. Transversal (no es flow), sin loop ni session, no toca docs/. Funciona en cualquier repo git, sin workspace inicializado.
+description: Resolves the conflicts of an in-progress merge for a given or detected source. Identifies origin (theirs) and destination (ours), analyzes both sides' intent and resolves; asks (structured-choice) on ambiguity or incoherence. Git-safe — proposes the merge commit, never push/--amend/--no-verify. Transversal (not a flow), no loop, no session, never touches docs/. Works in any git repo, no initialized workspace required.
 argument-hint: "[<source path | alias>]"
 allowed-tools:
   [
@@ -9,25 +9,25 @@ allowed-tools:
   ]
 ---
 
-# fix-git — resolvedor de conflictos de merge (transversal)
+# fix-git — merge-conflict resolver (transversal)
 
-Single-pass, **sin loop ni session**, **no escribe en `docs/`**. Comando **transversal** (no pertenece a SPEC / PLAN / QUICK). **Agnóstico al workspace**: opera sobre cualquier repo git — el `<source>` dado (path o alias), o el cwd — sin requerir `.workflow/`.
+Single-pass, **no loop, no session**, **never writes `docs/`**. **Transversal** command (belongs to no SPEC / PLAN / QUICK flow). **Workspace-agnostic**: operates on any git repo — the given `<source>` (path or alias), or the cwd — without requiring `.workflow/`.
 
-## Ejecutar
+## Run
 
-1. **Detectar + identificar** — corré `aw merge-state [<source>]` (read-only; `--source <alias>` o `--all` si hay workspace; un path directo si no). Del JSON, por repo: `is_merging`, `current_branch` (**destino / ours**), `merge_origin` (**origen / theirs**), `conflicted_files`.
-   - Si **no hay merge en curso** (`is_merging:false`) y el usuario indicó un **target** (p.ej. "merge `<branch>`"): es pedido explícito → `git -C <path> merge <branch>` y seguí. Sin target → informá que no hay merge que resolver y terminá.
-2. **Resolver** — **leé y seguí** la sección ***Resolución de conflictos de merge*** del rol `git` (`../roles/git/SKILL.md`): analizá la intención de cada conflicto (3 versiones `git show :1:/:2:/:3:<file>`, `git log --merge`), resolvé (ours / theirs / combinar / reescribir) y `git add` lo resuelto. Ante **ambigüedad o incoherencia**, preguntá vía *structured-choice* (no inventes la resolución).
-3. **Cerrar** — **proponé** el commit de merge (propose-then-execute, formato canónico, git-safe). Escape: `git merge --abort` tras confirmación del usuario.
+1. **Detect + identify** — run `aw merge-state [<source>]` (read-only; `--source <alias>` or `--all` when a workspace exists; a direct path otherwise). From the JSON, per repo: `is_merging`, `current_branch` (**destination / ours**), `merge_origin` (**origin / theirs**), `conflicted_files`.
+   - If **no merge is in progress** (`is_merging:false`) and the user named a **target** (e.g. "merge `<branch>`"): that is an explicit request → `git -C <path> merge <branch>` and continue. No target → report there is no merge to resolve and stop.
+2. **Resolve** — **read and follow** the ***Merge-conflict resolution*** section of the `git` role (`../roles/git/SKILL.md`): analyze each conflict's intent (3 versions `git show :1:/:2:/:3:<file>`, `git log --merge`), resolve (ours / theirs / combine / rewrite) and `git add` what is resolved. On **ambiguity or incoherence**, ask via *structured-choice* (never invent the resolution).
+3. **Close** — **propose** the merge commit (propose-then-execute, canonical format, git-safe). Escape hatch: `git merge --abort` after user confirmation.
 
-> No intentes `Skill: git` — el rol se **lee y se sigue** (es la capacidad que este comando compone). El comando **es** la entrada; la doctrina de conflictos vive en el rol `git`.
+> Do not try `Skill: git` — the role is **read and followed** (it is the capability this command composes). The command **is** the entry; the conflict doctrine lives in the `git` role.
 
 ## Plan mode
 
-Corré `aw merge-state` (read-only), reportá **origen ↔ destino** y los conflictos por archivo, y describí la **estrategia de resolución** que aplicarías — **sin** editar archivos ni commitear.
+Run `aw merge-state` (read-only), report **origin ↔ destination** and the per-file conflicts, and describe the **resolution strategy** you would apply — **without** editing files or committing.
 
 ## Resources
 
-- Capability: `../roles/git/SKILL.md` (sección *Resolución de conflictos de merge*)
-- CLI: `aw merge-state` (inspector read-only del estado de merge)
+- Capability: `../roles/git/SKILL.md` (section *Merge-conflict resolution*)
+- CLI: `aw merge-state` (read-only merge-state inspector)
 - Design reference: `docs/referencias/workflow-skills/fix-git.md`

package/skills/w/commands/plan-exec.md

@@ -1,5 +1,5 @@
 ---
-description: Inicia o retoma el loop de ejecución (plan-exec-loop) sobre un plan existente. Aquí ocurre el trabajo real: edición de código, scripts SQL propuestos, herramientas creadas. Git-safe.
+description: Starts or resumes the execution loop (plan-exec-loop) over an existing plan. The real work happens here - code edits, proposed SQL scripts, created tools. Git-safe.
 argument-hint: <docs/plans/PPP-plan-<slug>.md>
 allowed-tools:
   [
@@ -10,37 +10,37 @@ allowed-tools:
   ]
 ---
 
-# plan-exec — trampolín al loop de ejecución
+# plan-exec — trampoline to the execution loop
 
-Arranca o retoma `plan-exec-loop` (Layer 2), que ejecuta el trabajo real fase por fase. El plan (`docs/plans/PPP-plan-<slug>.md`) es un documento vivo que el loop mantiene actualizado (estado de fases y tareas).
+Starts or resumes `plan-exec-loop` (Layer 2), which executes the real work phase by phase. The plan (`docs/plans/PPP-plan-<slug>.md`) is a living document the loop keeps updated (phase and task state).
 
-## Ejecutar el loop
+## Run the loop
 
-`plan-exec-loop` **no** es una skill invocable por nombre — es el manual de operación de este comando (un doc hermano del bundle). **Cargalo y ejecutalo de punta a punta**:
+`plan-exec-loop` is **not** a skill invocable by name — it is this command's operating manual (a sibling doc in the bundle). **Load it and execute it end to end**:
 
-1. **Leé** `../loops/plan-exec-loop/SKILL.md` (dentro de la skill `w` instalada — p. ej. `~/.claude/skills/w/loops/…`).
-2. **Seguí** sus instrucciones tomando `$ARGUMENTS` como input: detecta CHECKPOINT/resume, ejecuta fase por fase (git-safe, BD solo-scripts), mantiene el plan vivo y reporta.
+1. **Read** `../loops/plan-exec-loop/SKILL.md` (inside the installed `w` skill — e.g. `~/.claude/skills/w/loops/…`).
+2. **Follow** its instructions taking `$ARGUMENTS` as input: it detects CHECKPOINT/resume, executes phase by phase (git-safe, DB scripts-only), keeps the plan alive and reports.
 
-> No intentes `Skill: plan-exec-loop` — no está registrada como skill. El comando **es** la entrada; el loop es su cuerpo.
+> Do not try `Skill: plan-exec-loop` — it is not registered as a skill. The command **is** the entry; the loop is its body.
 
-## Qué hace el loop (resumen)
+## What the loop does (summary)
 
-- Lee y actualiza `docs/plans/PPP-plan-<slug>.md` (living doc: estado de fases/tareas).
-- Edita código en las fuentes del workspace (una sola sesión de ejecución para el run; la ejecución sigue siendo fase por fase, solo que no hay sesión por fase).
-- Si crea una herramienta/utilidad, la documenta la skill ambiente `creating-tools` en `docs/tools/` (auto-descubierta; el workflow no la bindea).
-- **Gate de revisión de cierre** en cada límite de fase, **antes de proponer los commits**: re-lee el diff (pasada independiente) aplicando las **convenciones ambientes instaladas** y corrige o difiere hallazgos — nada llega a un commit sin revisar (ver `../loops/plan-exec-loop/SKILL.md` § *Delta 5*).
-- Propone commits por fuente (git-safe: verifica rama, propone, nunca push/--amend/--no-verify).
-- Genera artefactos de sesión (`DECISION`, `SCRIPTS.sql`) en `.workflow/sessions/`.
-- **No exporta** a `docs/scripts`, `docs/manuals`, `docs/diagrams`, `docs/reports` — eso lo hacen los `export-*` como paso aparte.
-- Scripts de BD (migraciones) van a `SCRIPTS.sql` tipo B; la IA **nunca ejecuta DML/DDL**, solo lecturas read-only vía MCP.
+- Reads and updates `docs/plans/PPP-plan-<slug>.md` (living doc: phase/task state).
+- Edits code in the workspace sources (a single execution session per run; execution is still phase by phase, there is just no session per phase).
+- If it creates a tool/utility, the ambient `creating-tools` skill documents it in `docs/tools/` (auto-discovered; the workflow does not bind it).
+- **Closing review gate** at every phase boundary, **before proposing the commits**: re-reads the diff (independent pass) applying the **installed ambient conventions** and fixes or defers findings — nothing reaches a commit unreviewed (see `../loops/plan-exec-loop/SKILL.md` § *Delta 5*).
+- Proposes commits per source (git-safe: verifies the branch, proposes, never push/--amend/--no-verify).
+- Generates session artifacts (`DECISION`, `SCRIPTS.sql`) under `.workflow/sessions/`.
+- **Never exports** to `docs/scripts`, `docs/manuals`, `docs/diagrams`, `docs/reports` — the `export-*` do that as a separate step.
+- DB scripts (migrations) go to `SCRIPTS.sql` type B; the AI **never executes DML/DDL**, only read-only reads via MCP.
 
 ## Resumable
 
-Mismo patrón que los demás loops: detecta CHECKPOINT existente y continúa desde ahí.
+Same pattern as the other loops: it detects an existing CHECKPOINT and continues from there.
 
 ## Plan mode
 
-El skill describe fase por fase lo que ejecutaría, qué archivos tocaría, y qué commits propondría, sin aplicar cambios.
+The skill describes, phase by phase, what it would execute, which files it would touch, and which commits it would propose, without applying changes.
 
 ## Resources
 

package/skills/w/commands/plan-new.md

@@ -1,5 +1,5 @@
 ---
-description: Inicia o retoma el loop de planificación (plan-new-loop) a partir de un spec. Convierte el "qué" (spec) en el "cómo" (plan). Input ideal: docs/specs/NNN-spec-<slug>.md ya refinado.
+description: Starts or resumes the planning loop (plan-new-loop) from a spec. Turns the "what" (spec) into the "how" (plan). Ideal input: an already refined docs/specs/NNN-spec-<slug>.md.
 argument-hint: <docs/specs/NNN-spec-<slug>.md | prompt>
 allowed-tools:
   [
@@ -10,40 +10,40 @@ allowed-tools:
   ]
 ---
 
-# plan-new — trampolín al loop de planificación
+# plan-new — trampoline to the planning loop
 
-Puente SPEC → PLAN. Convierte el "qué" (spec refinado) en el "cómo" (plan). Delega a `plan-new-loop` (Layer 2).
+SPEC → PLAN bridge. Turns the "what" (refined spec) into the "how" (plan). Delegates to `plan-new-loop` (Layer 2).
 
-## Resolución de input
+## Input resolution
 
-El skill evalúa `$ARGUMENTS` (los specs viven in place — `docs/specs/NNN-spec-<slug>.md`; localizar vía glob `docs/specs/NNN-spec-*.md` o la ruta exacta):
+The skill evaluates `$ARGUMENTS` (specs live in place — `docs/specs/NNN-spec-<slug>.md`; locate via the `docs/specs/NNN-spec-*.md` glob or the exact path):
 
-1. **Spec refinado** (`docs/specs/NNN-spec-<slug>.md` que **ya tiene** `## Refinement decisions` / `## Q&A traceability`) → ideal. Procede directamente a `plan-new-loop`.
-2. **Spec borrador** (mismo archivo, pero **sin** esas dos secciones) → **soft-suggest** correr `/w:spec-refine` primero; planificar sobre un spec sólido produce mejores planes (el usuario puede proceder igual).
-3. **prompt** (sin spec referenciado) → propone usar el flujo SPEC; **por default lanza `/w:spec-new`** con ese prompt para crear el borrador, y desde ahí continúa el flujo natural.
+1. **Refined spec** (`docs/specs/NNN-spec-<slug>.md` that **already has** `## Refinement decisions` / `## Q&A traceability`) → ideal. Proceed straight to `plan-new-loop`.
+2. **Draft spec** (same file, but **without** those two sections) → **soft-suggest** running `/w:spec-refine` first; planning over a solid spec produces better plans (the user may proceed anyway).
+3. **prompt** (no spec referenced) → propose using the SPEC flow; **by default launch `/w:spec-new`** with that prompt to create the draft, and continue the natural flow from there.
 
-> **Refinado vs borrador** se distingue por la **presencia** de `## Refinement decisions` / `## Q&A traceability` en el spec, no por el nombre del archivo (ya no hay `-refined`).
+> **Refined vs draft** is distinguished by the **presence** of `## Refinement decisions` / `## Q&A traceability` in the spec, never by the filename (there is no `-refined` anymore).
 
-## Ejecutar el loop
+## Run the loop
 
-`plan-new-loop` **no** es una skill invocable por nombre — es el manual de operación de este comando (un doc hermano del bundle). **Cargalo y ejecutalo de punta a punta**:
+`plan-new-loop` is **not** a skill invocable by name — it is this command's operating manual (a sibling doc in the bundle). **Load it and execute it end to end**:
 
-1. **Leé** `../loops/plan-new-loop/SKILL.md` (dentro de la skill `w` instalada — p. ej. `~/.claude/skills/w/loops/…`).
-2. **Seguí** sus instrucciones tomando `$ARGUMENTS` como input (resuelto según las 3 reglas de arriba): detecta estado/resume, corre el motor gap-driven, crea y maneja sessions, converge y reporta.
+1. **Read** `../loops/plan-new-loop/SKILL.md` (inside the installed `w` skill — e.g. `~/.claude/skills/w/loops/…`).
+2. **Follow** its instructions taking `$ARGUMENTS` as input (resolved per the 3 rules above): it detects state/resume, runs the gap-driven engine, creates and manages sessions, converges and reports.
 
-> No intentes `Skill: plan-new-loop` — no está registrada como skill. El comando **es** la entrada; el loop es su cuerpo.
+> Do not try `Skill: plan-new-loop` — it is not registered as a skill. The command **is** the entry; the loop is its body.
 
-## Notas de numeración
+## Numbering notes
 
-El plan se nombra `docs/plans/PPP-plan-<slug>.md`. El CLI solo devuelve el número `PPP`; el loop arma el nombre completo (slug = kebab-case corto del Requirement: `[a-z0-9-]`, ≤ ~5 palabras / ≤ 40 chars). **No hereda el `NNN` del spec**. El vínculo al spec se establece por referencia (`## Origin` / "Derivado de") en el plan, no por número.
+The plan is named `docs/plans/PPP-plan-<slug>.md`. `aw next-number docs/plans` returns JSON (field `next` = `PPP`); the loop builds the full name (slug = short kebab-case from the Requirement: `[a-z0-9-]`, ≤ ~5 words / ≤ 40 chars). It does **not inherit the spec's `NNN`**. The link to the spec is established by reference (`## Origin` / "Derived from") in the plan, never by number.
 
 ## UI → design SPECs
 
-Si el plan **incluye UI**, el loop compone la capacidad `ui-design` y produce **design SPECs** por pantalla (`NNN-SPEC-<SLUG>.md`) como artefactos de su sesión — las Tasks UI del plan los referencian (ver `../loops/plan-new-loop/SKILL.md` § *Delta 4* y `../artifacts/artifacts-design/SPEC.md`).
+If the plan **includes UI**, the loop composes the `ui-design` capability and produces per-screen **design SPECs** (`NNN-SPEC-<SLUG>.md`) as artifacts of its session — the plan's UI Tasks reference them (see `../loops/plan-new-loop/SKILL.md` § *Delta 4* and `../artifacts/artifacts-design/SPEC.md`).
 
 ## Plan mode
 
-El skill resuelve el input según las 3 reglas de arriba y describe las acciones del loop que ejecutaría, sin arrancar la iteración.
+The skill resolves the input per the 3 rules above and describes the loop actions it would run, without starting the iteration.
 
 ## Resources
 

package/skills/w/commands/plan-refine.md

@@ -1,5 +1,5 @@
 ---
-description: Inicia o retoma el loop de refinamiento de un plan (plan-refine-loop). Paso auxiliar y NO obligatorio del flujo PLAN — refina un plan existente in place antes de ejecutarlo. Input ideal: docs/plans/PPP-plan-<slug>.md ya generado por plan-new.
+description: Starts or resumes the plan refinement loop (plan-refine-loop). An auxiliary, NOT mandatory step of the PLAN flow — refines an existing plan in place before executing it. Ideal input: a docs/plans/PPP-plan-<slug>.md already generated by plan-new.
 argument-hint: <docs/plans/PPP-plan-<slug>.md>
 allowed-tools:
   [
@@ -10,46 +10,46 @@ allowed-tools:
   ]
 ---
 
-# plan-refine — trampolín al loop de refinamiento del plan
+# plan-refine — trampoline to the plan refinement loop
 
-Paso **auxiliar y NO obligatorio** del flujo PLAN: el gemelo de `spec-refine`, pero sobre el **plan**. `plan-new` ya produce un plan a partir del spec refinado; `plan-refine` existe para cuando —**antes de ejecutar**— surgen cambios (nuevos requerimientos, ajustes de alcance, deps o riesgos que aparecen al releer el plan) que conviene incorporar sin re-generar el plan desde cero.
+An **auxiliary, NOT mandatory** step of the PLAN flow: `spec-refine`'s twin, but over the **plan**. `plan-new` already produces a plan from the refined spec; `plan-refine` exists for when — **before executing** — changes arise (new requirements, scope adjustments, deps or risks spotted while re-reading the plan) worth incorporating without regenerating the plan from scratch.
 
-Este comando no refina el plan él mismo: delega al loop `plan-refine-loop` (Layer 2), que itera, cierra gaps y edita el plan **in place**.
+This command does not refine the plan itself: it delegates to `plan-refine-loop` (Layer 2), which iterates, closes gaps and edits the plan **in place**.
 
-> **No obligatorio.** `plan-exec` corre **cualquier** plan, refinado o no — no hay gate que exija pasar por aquí. Usalo solo cuando el plan necesite ajustes antes de ejecutar.
+> **Not mandatory.** `plan-exec` runs **any** plan, refined or not — no gate requires passing through here. Use it only when the plan needs adjustments before executing.
 
-## Resolución de input
+## Input resolution
 
-El skill evalúa `$ARGUMENTS` (los planes viven in place — `docs/plans/PPP-plan-<slug>.md`; localizar vía glob `docs/plans/PPP-plan-*.md` o la ruta exacta):
+The skill evaluates `$ARGUMENTS` (plans live in place — `docs/plans/PPP-plan-<slug>.md`; locate via the `docs/plans/PPP-plan-*.md` glob or the exact path):
 
-1. **Plan existente** (`docs/plans/PPP-plan-<slug>.md`) → procede a `plan-refine-loop`.
-2. **Sin plan** (el arg no referencia un plan, o no hay ninguno) → **soft-suggest** correr `/w:plan-new` primero (no hay nada que refinar todavía); el usuario decide.
+1. **Existing plan** (`docs/plans/PPP-plan-<slug>.md`) → proceed to `plan-refine-loop`.
+2. **No plan** (the arg references no plan, or none exists) → **soft-suggest** running `/w:plan-new` first (there is nothing to refine yet); the user decides.
 
-## Ejecutar el loop
+## Run the loop
 
-`plan-refine-loop` **no** es una skill invocable por nombre — es el manual de operación de este comando (un doc hermano del bundle). **Cargalo y ejecutalo de punta a punta**:
+`plan-refine-loop` is **not** a skill invocable by name — it is this command's operating manual (a sibling doc in the bundle). **Load it and execute it end to end**:
 
-1. **Leé** `../loops/plan-refine-loop/SKILL.md` (dentro de la skill `w` instalada — p. ej. `~/.claude/skills/w/loops/…`).
-2. **Seguí** sus instrucciones tomando `$ARGUMENTS` como input: detecta estado/resume, corre el motor gap-driven, crea y maneja sessions, converge y reporta.
+1. **Read** `../loops/plan-refine-loop/SKILL.md` (inside the installed `w` skill — e.g. `~/.claude/skills/w/loops/…`).
+2. **Follow** its instructions taking `$ARGUMENTS` as input: it detects state/resume, runs the gap-driven engine, creates and manages sessions, converges and reports.
 
-> No intentes `Skill: plan-refine-loop` — no está registrada como skill. El comando **es** la entrada; el loop es su cuerpo.
+> Do not try `Skill: plan-refine-loop` — it is not registered as a skill. The command **is** the entry; the loop is its body.
 
-## Resolución de estado (resumable)
+## State resolution (resumable)
 
-El skill detecta el estado previo antes de arrancar, **keyando off el `CHECKPOINT`** (no un archivo "refined"):
+The skill detects prior state before starting, **keying off the `CHECKPOINT`** (never a "refined" file):
 
-1. Busca la sesión de refinamiento del plan en `.workflow/sessions/` (descriptor `<slug>-plan-refine` + `## Origin`) y su `CHECKPOINT.md`.
-2. **En curso** (existe CHECKPOINT) → continúa desde el avance previo (gaps resueltos, Q&A).
-3. **Sin avance** (sin CHECKPOINT y el plan **no** tiene `## Refinement decisions`/`## Q&A traceability`) → arranca desde cero leyendo el plan (`PPP-plan-*.md`).
-4. **Ya refinado / re-refine a demanda** (sin CHECKPOINT abierto pero el plan **ya tiene** `## Refinement decisions`/`## Q&A traceability`) → **soportado de primera clase**: mientras el flujo siga en PLAN podés re-correr `/w:plan-refine` sobre el mismo plan **las veces que haga falta** (nuevos requerimientos, cambios de scope, re-lectura). El loop hace `create_or_resume` — localiza la refine session existente (aunque esté cerrada) y la **reabre** en vez de duplicarla — y re-refina leyendo el **plan mismo**; al `Guardar`, edita in place con confirmación.
+1. Find the plan's refinement session under `.workflow/sessions/` (descriptor `<slug>-plan-refine` + `## Origin`) and its `CHECKPOINT.md`.
+2. **In progress** (a CHECKPOINT exists) → continue from the recorded progress (resolved gaps, Q&A).
+3. **No progress** (no CHECKPOINT and the plan does **not** have `## Refinement decisions`/`## Q&A traceability`) → start from zero reading the plan (`PPP-plan-*.md`).
+4. **Already refined / re-refine on demand** (no open CHECKPOINT but the plan **already has** the 2 sections) → **first-class operation**: while the flow stays in PLAN you can re-run `/w:plan-refine` over the same plan **as many times as needed** (new requirements, scope changes, re-reads). The loop does `create_or_resume` — it locates the existing refine session (even closed) and **reopens** it instead of duplicating — and re-refines reading the **plan itself**; on `Guardar`, edits in place with confirmation.
 
 ## UI → design SPECs
 
-Si el refine **toca UI**, el loop compone `ui-design` y produce/actualiza **design SPECs** (`NNN-SPEC-<SLUG>.md`) en su propia sesión — acotado a las pantallas nuevas/cambiadas — y re-apunta las referencias del plan (ver `../loops/plan-refine-loop/SKILL.md` § *Delta 4*).
+If the refine **touches UI**, the loop composes `ui-design` and produces/updates **design SPECs** (`NNN-SPEC-<SLUG>.md`) in its own session — scoped to the new/changed screens — and re-points the plan references (see `../loops/plan-refine-loop/SKILL.md` § *Delta 4*).
 
 ## Plan mode
 
-El skill resuelve el estado y describe las acciones que ejecutaría el loop (gaps que cerraría, preguntas que haría), sin arrancar la iteración.
+The skill resolves the state and describes the actions the loop would run (gaps it would close, questions it would ask), without starting the iteration.
 
 ## Resources