@damiangilgonzalez/harness 1.3.17 → 1.3.18

package/README.md

@@ -1,755 +1,210 @@
 <div align="center">
 
-<img src="https://raw.githubusercontent.com/ericrisco/rsc-harness/main/site/og.png" alt="rsc-harness — You decide what to build. rsc-harness builds your agent’s harness, following strict best practices instead of improvising a Frankenstein stack." width="960">
+![harness: un agente dentro de un arnés de cinco cintas (memoria, herramientas, conocimiento, reglas y método)](docs/img/readme/readme-00-portada.png)
 
-# `rsc-harness` — You decide what to build. It builds your agent's harness.
-
-> Este proyecto es un fork del trabajo original de Eric Risco: [github.com/ericrisco/rsc-harness](https://github.com/ericrisco/rsc-harness).
+**Tú decides qué construir. harness construye el arnés de tu agente:**
+le da el método, la memoria y los reflejos.
 
 [![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-294-63d68a?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)
-
-**You decide what to build. rsc-harness builds your agent’s harness.** Tell it whether you are
-shipping software, running operations, researching, creating content, or mixing them. Its wizard
-reads the project, applies strict best practices, and shows the exact harness plan before writing.
-
-Give this URL to your agent:
-
-```text
-Read https://ericrisco.github.io/rsc-harness/ and set up rsc for this project.
-Ask me the onboarding questions, show me the exact plan, and wait for my acceptance before writing.
-```
-
-Or start from the terminal:
 
 ```bash
 npx @damiangilgonzalez/harness@latest onboard
 ```
 
-<img src="https://raw.githubusercontent.com/ericrisco/rsc-harness/main/site/meta-harness.png" alt="rsc-harness wizard turns an outcome into a verified plan: memory, tools, knowledge and rules selected, deferred or excluded according to evidence." width="960">
-
 </div>
 
-## Your agent needs a harness. It should not improvise one.
-
-A model is only the brain. Real work also needs project memory, tools, domain knowledge, rules and
-repeatable workflows. Add those pieces ad hoc and the result becomes a **Frankenstein harness**:
-duplicated instructions, unrelated skills, premature hooks, unnecessary MCPs and no clear owner.
+---
 
-Open standards already cover individual parts — [Agent Skills](https://agentskills.io/specification),
-[MCP](https://modelcontextprotocol.io/) and [AGENTS.md](https://agents.md/) — but they do not decide
-which complete harness this project needs. rsc-harness does that job through one guided flow:
+## Qué es
 
-1. **You state the outcome.** No skill, hook or MCP vocabulary required.
-2. **The wizard reads only the project root** and asks technical level, accompaniment, project kind,
-   goal and assistants.
-3. **A proportional plan explains every choice.** Selected, deferred and excluded pieces all have a
-   reason. Nothing writes before you accept the exact plan.
-4. **The result is verified.** Shared sources prevent duplication; knowledge loads progressively;
-   local state stays local; deterministic checks prove the installed harness matches the plan.
-5. **It grows from evidence.** A deferred capability is proposed later only when the project actually
-   develops the need for it.
+![El modelo es el cerebro; el harness es todo lo demás: memoria, conocimiento, método, reglas y herramientas](docs/img/readme/readme-01-que-es.png)
 
-That is what “best practices” means here: a small, separated, project-bound and auditable harness —
-not a pile of whatever an agent happened to install.
+El modelo es el cerebro. El harness es todo lo demás.
+Si esas piezas se añaden a ratos, sale un harness **Frankenstein**: reglas duplicadas, skills que no
+vienen a cuento y hooks antes de tiempo.
 
----
+![El mismo encargo sin harness y con harness](docs/img/readme/readme-02-antes-despues.png)
 
-## 🤖 For agents: "install this harness"
+Mismo modelo. Distinto resultado.
 
-If you're an AI coding agent (Claude Code, Cursor, Copilot, Codex, Gemini…) and your user
-asked you to **install rsc / this harness / these skills**, run this in the **root of the
-project they're equipping** — not inside a clone of this repo (see the note under *Install*):
+![Tira cómica: petición, preguntas, test primero y PR](docs/img/readme/readme-03-tira-comica.png)
 
-```bash
-npx @damiangilgonzalez/harness@latest onboard
-```
+Pides algo, te pregunta lo que falta, escribe el test primero y te entrega una PR con evidencia.
 
-That launches the binding plain-language onboarding. It asks the user for technical level,
-accompaniment, project kind and goal **before it writes anything**, reads only the selected project
-root, and shows every selected or deferred skill, agent and hook with its reason. Relay those
-questions to the user; never invent or default their answers. The first pass writes nothing and
-prints a SHA-256 plan id. Only rerun with `--accept-plan <id>` after the user accepts that exact plan.
-If the project already has a skill of its own with a catalog name, the plan lists it under
-**Your own skills this plan replaces** — tell the user before accepting; renaming their folder and
-regenerating the plan keeps theirs.
+---
 
-For a non-interactive agent, collect the answers and preview the same plan explicitly:
+## Cómo trabajamos
 
-```bash
-npx @damiangilgonzalez/harness@latest onboard --technical-level mixed --accompaniment L1 \
-  --project-kind software --goal "small compound-interest website" \
-  --software-scope small --target codex
-# After the user accepts the printed plan:
-npx @damiangilgonzalez/harness@latest onboard --technical-level mixed --accompaniment L1 \
-  --project-kind software --goal "small compound-interest website" \
-  --software-scope small --target codex --accept-plan PRINTED_SHA256_ID
-```
+![Mapa de implementación: la cadena depende del tamaño de la tarea](docs/img/readme/readme-04-metodo.png)
 
-- **Choose assistants non-interactively:** add `--target claude` (comma-separate for several) to `onboard`.
-- **Two assistants already installed?** rsc asks instead of guessing. `--target` settles it in one word.
-- **Already installed, just refreshing skills + hooks:** `rsc sync` (or re-run the command above).
-- **Add one skill by id:** `rsc add <id>` · **browse the catalog:** `rsc consult "<what you want>"` or `rsc list`.
+La cadena depende del **tamaño**. El agente la encadena solo; no hace falta escribir cada comando.
 
-From then on it's self-driving: `rsc-suggest` proposes the next skill as tasks appear, and in
-Claude Code a hook re-asserts the spec-first **new-feature gate** on every turn — so a feature
-request routes through `to-spec` (or `grill-with-docs`/`wayfinder` first, when the shape is still
-fuzzy) before any skill writes code.
+| Tamaño | Cadena |
+|---|---|
+| Una línea (errata, config) | Hazlo sin más |
+| Pequeño (una sesión, un ticket) | `superpowers:brainstorming` o `grill-with-docs` → `implement` |
+| Grande (varias sesiones, muchas piezas) | `grill-with-docs` o `wayfinder` → `to-spec` → `to-tickets` → `implement-spec` |
+| Siempre, al final | `code-review` → `pr` |
 
----
+![El trabajo grande paso a paso, con lo que deja cada paso](docs/img/readme/readme-05-cadena-grande.png)
 
-## Why this exists
-
-An improvised harness tends to grow by accumulation: more files, more context and more rules, with
-no method deciding whether each piece belongs. rsc-harness keeps that construction disciplined:
-
-- **Granular by default.** The unit of installation is *one skill*. Install
-  `fastapi` without ever pulling `go`. Nothing you don't use touches your context.
-- **Self-recommending.** Both the terminal (`rsc consult`) and the chat
-  (`rsc-suggest`, an always-on detector) watch what you're doing and propose the
-  *next* skill the moment a task needs it — a one-word confirm installs it.
-- **Not code-only.** First-class support for running a *company*: bookkeeping,
-  invoicing, hiring, GDPR, pitch decks, SEO, a YouTube/TikTok/LinkedIn presence —
-  each wired to a `docs/` knowledge loop that learns from your own results.
-- **Specialists follow the stack.** The four base agents stay small; installing a
-  supported stack adds only its reviewer and build resolver. `rsc add go`, for
-  example, adds the Go pair without pulling reviewers for every other language.
-- **A new local session continues the old one.** Claude Code, Codex, Gemini CLI
-  and OpenCode load a bounded checkpoint for the current branch and worktree at
-  session start. Cursor desktop uses an assisted read-before-action fallback.
-- **Honestly good.** Every skill was built by a research → spec → implement →
-  *adversarial review* pipeline and had to clear an objective rubric
-  (`scripts/skill-rubric.md`, written *before* any skill existed). The bar was
-  real: skills that scored 8.0 were sent back and fixed, not waved through.
-
-`skills/<name>/` is the single source of truth. There are no bundles to argue
-over: you start with a tiny floor and grow one piece at a time.
+Cada paso deja un documento: glosario, spec, ADR, tickets, rama y PR.
+La fuente de verdad es lo escrito, no el chat.
 
----
+![implement-spec: un grafo de tickets resuelto por varios subagentes a la vez](docs/img/readme/readme-06-tickets-en-paralelo.png)
 
-## New sessions pick up the latest local work
+`implement-spec` coge los tickets libres y los reparte entre subagentes, cada uno en su worktree.
+Todo confluye en una rama de integración.
 
-On supported local targets, rsc checkpoints observable repository state at safe
-boundaries: branch, worktree, HEAD, changed paths, commits and SDD ledger status.
-When a new session opens in the same checkout, that state is injected before the
-first agent action. A completed edit is preserved even if the previous client
-closed before its normal session-end event.
+![Revisar antes de fusionar: estándares del repo y lo que pedía la spec](docs/img/readme/readme-17-revision.png)
 
-- **Full:** Claude Code, Codex, Gemini CLI and OpenCode. Codex asks you to inspect
-  and trust the project hook once with `/hooks`; until then `doctor` reports that
-  trust is still required.
-- **Assisted:** Cursor desktop. Its start hook is fire-and-forget, so rsc also
-  installs a local always-on rule that performs the read before acting.
-- **Never cloud:** Cursor Cloud, Codex Cloud, remote agents, cloud storage and
-  synchronization are intentionally unsupported. The memory runtime makes no
-  network request.
+`code-review` revisa contra los estándares del repo y contra la spec. `pr` abre la PR con
+resumen, evidencia y peligro de fusión.
 
-The journal never stores prompts, responses, tool output, file contents or
-secrets. It stays in a git-excluded project-local path, retains 30 days, and
-injects at most 4,096 bytes. Disable every memory surface for a project with
-`rsc memory off`; re-enable it with `rsc memory on`.
+La guía completa del método, fase a fase: [`docs/skills/`](docs/skills/).
 
 ---
 
-## Install
+## Instalar
 
-```bash
-npx @damiangilgonzalez/harness@latest onboard
-```
+![Instalar: un comando, cuatro preguntas y un plan que apruebas](docs/img/readme/readme-08-instalacion.png)
 
-Prefer the short `rsc` command? Install once, globally:
+Cuatro preguntas (nivel técnico, acompañamiento, tipo de proyecto, objetivo) y un plan exacto.
+Lee solo la raíz del proyecto y **no escribe nada antes de que aceptes**.
 
 ```bash
-npm install -g @damiangilgonzalez/harness   # then just: rsc
+npx @damiangilgonzalez/harness@latest onboard
 ```
 
-Run it inside any project and describe what you want. Working on the catalog
-itself? Clone and link:
+¿Usas un agente? Pega esto en el chat:
 
-```bash
-git clone https://github.com/ericrisco/rsc-harness.git ~/rsc-skills
-cd ~/rsc-skills && npm install && npm link
+```text
+Lee https://github.com/damiangilgonzalez1995/rsc-harness y prepara rsc para este proyecto.
+Hazme las preguntas del onboarding, enséñame el plan exacto y espera a que lo acepte antes de escribir.
 ```
 
-> **Run it inside the project you're equipping — not inside this repo.** The
-> catalog's own `package.json` is named `@damiangilgonzalez/harness`, so `npx @damiangilgonzalez/harness`
-> *from within a `rsc-harness` clone* resolves to the local (unlinked) bin and
-> dies with `sh: rsc: command not found`. Working on the catalog itself? Use
-> `node scripts/rsc.js …`, the `npm link` above, or pin the published build with
-> `npx @damiangilgonzalez/harness@latest …`.
-
-The first run asks **how technical the conversation should be**, the accompaniment level, what the
-project is for, its goal and the assistants to target. It then presents the complete plan. A small
-website can defer SDD, agents and code guards; an operations harness does not receive them merely
-because it lives in a repository. Deferred components record the evidence that would make rsc
-recommend them later. `rsc reassess` reports that evidence but still cannot install anything
-without a newly accepted plan.
-
-Everything stays **in the project**, and the real skill files are written
-**once** to `.rsc/skills/<id>/`. Each assistant you pick gets a lightweight
-symlink back to that shared base — no copy is duplicated across IDEs. (If the
-filesystem can't symlink, it falls back to a real copy automatically.)
-On targets with file-based agents, the four base agents are installed too;
-stack specialists remain selective. Native command targets receive only entry
-points whose backing skill, agent or local-memory capability actually exists.
+<details>
+<summary>Para agentes: el mismo flujo sin modo interactivo</summary>
 
----
-
-## 30-second tour
+Pasa las preguntas a la persona; no inventes ni rellenes sus respuestas. La primera pasada
+no escribe nada e imprime un id de plan; solo se repite con `--accept-plan` cuando la persona lo acepta.
 
-```
-$ rsc onboard
- ██████╗ ███████╗ ██████╗     ← animated gradient wordmark
- ██╔══██╗██╔════╝██╔════╝
- ██████╔╝███████╗██║
-  294 skills · one CLI · zero bloat
-
-How technical should the conversation be?
-How much accompaniment do you want?
-What are you building or running?
-What do you want this project to achieve?
-
-RSC_ONBOARDING_PLAN
-Plan id: <sha256>
-Selected: …
-Deferred: …
-Accept this exact harness plan?
+```bash
+npx @damiangilgonzalez/harness@latest onboard --technical-level mixed --accompaniment L1 \
+  --project-kind software --goal "small compound-interest website" \
+  --software-scope small --target claude
+# Cuando la persona acepte el plan impreso:
+npx @damiangilgonzalez/harness@latest onboard --technical-level mixed --accompaniment L1 \
+  --project-kind software --goal "small compound-interest website" \
+  --software-scope small --target claude --accept-plan PRINTED_SHA256_ID
 ```
 
-The terminal and chat adapters produce the same normalized answers and plan id. If project evidence
-changes between preview and acceptance, rsc returns `RSC_PLAN_CHANGED` and writes nothing. After an
-accepted application it verifies the receipt and managed state before printing `RSC_ONBOARDING_READY`.
-That verdict is not just about the receipt: it also requires the harness floor to exist —
-`01-TOOLS/_TEMPLATE/` and `docs/wiki/harness/`.
-If the floor is missing, the install applied but prints `RSC_ONBOARDING_INCOMPLETE` with each
-missing path and the action that creates it, because a plan that promised little used to be able to
-report success with three markdown files.
-
----
+</details>
 
-## The CLI
+![Cuatro perfiles concéntricos: minimal, core, ui y full](docs/img/readme/readme-10-perfiles.png)
 
-Fresh projects enter through `rsc onboard`. The direct `add` and `install --profile` forms below
-are maintenance controls for projects that already carry an `.rsc.json` declaration; they cannot
-bypass onboarding in a new folder.
+Empiezas pequeño. El resto se carga bajo demanda: el harness te propone una skill cuando la tarea
+la pide, con la evidencia que lo justifica.
 
 ```bash
-rsc onboard                         # binding plain-language onboarding (recommended)
-rsc reassess                        # check persisted deferral triggers; never installs by itself
-rsc add fastapi postgresdb           # install specific skills, by name
-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 294 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}
-rsc list                             # installed skills, agents and commands
-rsc capabilities                    # installed/available surfaces + memory mode
-rsc doctor                           # health, missing backing, hooks and local memory; exits 1 when unhealthy
-rsc memory status                    # full / assisted / unsupported / degraded
-rsc memory save --session handoff    # force a deterministic local checkpoint
-rsc memory resume                    # print this branch/worktree continuation
-rsc memory learn --text "…" --evidence "…" --confidence 0.8 --approve
-rsc memory off                       # disable hooks, commands and injection project-wide
-rsc sync --target claude,codex       # refresh managed skills/hooks from the current package version
-rsc backups                          # list project-local snapshots
-rsc restore latest --dry-run         # preview restoring the newest snapshot
-rsc restore <snapshot-id>            # restore a project-local snapshot
-rsc upgrade --dry-run                # show npm upgrade + sync commands
-rsc uninstall postgresdb --dry-run   # preview a removal
+rsc install --profile minimal   # la base: orient + suggest + bro + unslop + show-me + eli5 + harness + init + teach
+rsc install --profile core      # la base + el método completo
+rsc install --profile full      # todo el catálogo
 ```
 
 ---
 
+## Qué se instala
 
-## 👥 Sharing a harness with your team
+![Qué deja en tu proyecto: qué se sube a git y qué se queda en local](docs/img/readme/readme-09-que-se-instala.png)
 
-The harness travels by git, but not all of it — and the split is the point.
+Las skills se escriben una vez en `.rsc/skills/` y cada asistente las enlaza.
+Lo que se comparte va a git; el estado de la máquina, no.
 
-**Commit these:**
+![Los reflejos: gate, danger-guard, ship-guard, gitmoji-guard, memoria y limpieza de worktrees](docs/img/readme/readme-07-guardias.png)
 
-| | |
-| --- | --- |
-| `.rsc.json` | The decision: which assistants, which skills, **which catalog version**, the developer tier, which gates you disarmed |
-| `01-TOOLS/` · `docs/` | Your tooling and your wiki, if you use them |
-| Skills and agents you wrote by hand | They are yours. rsc does not claim them, does not count them as drift, and does not touch them |
+Hooks que vigilan por ti: recuerdan la cadena, piden confirmación antes de un `rm -rf` o un
+`git push --force` y paran antes de volver a `main` sin abrir la PR.
 
-**Do not commit these** — rsc adds them to `.gitignore` for you:
+![Plugins de serie: superpowers, skins, savvy-progress, filetree y cache-tax](docs/img/readme/readme-16-plugins.png)
 
-| | Why |
-| --- | --- |
-| `.rsc/` | Machine state: hook scripts, seals, logs and fallback session memory |
-| `docs/raw/worklog/.rsc-memory/` | Preferred session journal when a local wiki exists; protected with git's local exclude |
-| The skill entries rsc manages | Symlinks on macOS/Linux, real copies on Windows — two incompatible shapes of one thing |
+En Claude Code quedan activados `skins`, `savvy-progress`, `filetree` y `cache-tax`
+(mantiene caliente la caché, y eso gasta tokens). `superpowers` llega cuando el proyecto usa el método.
 
-Three files carry the harness through git: `.rsc.json` (what the team decided),
-`.claude/settings.json` (the wiring), and `.claude/rsc-bootstrap.mjs` — the small file that
-notices, in a clone, that the rest is not there yet. **Commit all three.** If your project
-ignores the assistant's directory wholesale, rsc adds the lines that keep those files versioned —
-verified against git, not against the pattern.
+En cifras: 294 skills, 34 agentes y 43 entradas de comando, para 17 asistentes
+(Claude Code, Codex, Cursor, Copilot, Gemini…). Detalle en la [referencia técnica](docs/referencia-tecnica.md).
 
-**And say it plainly, because committing it is the point:** `.claude/rsc-bootstrap.mjs` is code that
-runs on every session and every shell call, so a pull request that edits *that file* runs on the
-machine of whoever reviews the branch. That is true of `.claude/settings.json` already, and of any
-hook-based harness — but it is worth knowing before you agree to commit a third one. Review changes
-to it the way you would review a CI workflow.
-
-Whoever clones runs **one command** and ends up with the same harness — at the version the
-project pinned, which is the `catalogVersion` in its `.rsc.json`:
-
-```bash
-npx @damiangilgonzalez/harness@<catalogVersion> sync
-```
-
-**You do not have to know that, or find it.** Open the project and the assistant tells you, in
-the first message: what is missing, what would be installed, and the exact command, naming the
-pinned version. It asks; it does not install anything on its own and it does not hold up
-whatever you sat down to do. Say no and it stops asking on that machine.
-
-Not `@latest`, and the difference is the whole point of sharing: a teammate who clones in three
-months gets what you had, not what shipped since. Upgrading is something a person decides, writes
-into `.rsc.json`, and commits — and then it reaches everyone through git, like any other change.
+---
 
-When someone changes the harness and you `git pull`, `rsc doctor` tells you what no longer
-matches. **Nothing is ever written to your machine by a pull** — you are told, and you decide.
+## El día a día
 
-**Own skills.** A skill your team wrote lives in the repo and already works for whoever clones,
-with no command at all. rsc never installs, updates or overwrites it: its version is the commit.
-Installing a catalog skill of the same name is refused rather than silently winning, and `doctor`
-lists what is yours by reading the files themselves — no list to keep in `.rsc.json`, because a
-list somebody has to remember to update is a list that goes quietly stale. Declaring a skill under
-`ownSkills` still works and still reports when someone is missing it.
+![Un update y todos tus proyectos al día](docs/img/readme/readme-11-actualizar.png)
 
+En un proyecto que ya tiene harness, el mismo comando ofrece *Update this project*.
+Respeta lo que quitaste a mano y hace una copia antes de tocar nada.
 
-## 🩹 Something's off? One command
+```bash
+npx @damiangilgonzalez/harness@latest
+```
 
-Recognise any of these? They are all the same fix.
+![Compartir con el equipo: commit, clone y sync a la versión fijada](docs/img/readme/readme-12-equipo.png)
 
-| What you see | |
-| --- | --- |
-| `"target": "codex"` when you work in Claude Code | |
-| `This target has no hook injection` and you did not expect that | |
-| Skills appear that you never asked for | |
-| A hook seems to run several times per turn | |
-| Template lines showed up inside your hand-written `AGENTS.md` | |
+Tres ficheros llevan el harness por git. **Súbelos los tres:**
+`.rsc.json` (lo que decidió el equipo), `.claude/settings.json` (el cableado) y
+`.claude/rsc-bootstrap.mjs` (el que detecta, en un clon, que falta lo demás).
 
-(A *fresh* clone is not in this table any more: nothing is broken there, the harness was simply
-never built on that machine, and the assistant now says so itself — see **sharing by git** above.)
+Quien clona abre el proyecto y el asistente te lo dice en el primer mensaje: qué falta y el
+comando exacto, con la versión fijada (el `catalogVersion` de `.rsc.json`). Pregunta; no instala solo.
 
 ```bash
-npx @damiangilgonzalez/harness@latest repair
+npx @damiangilgonzalez/harness@<catalogVersion> sync
 ```
 
-Safe in any folder: with no rsc there, it says so and writes nothing. It shows what it
-found before touching anything, keeps a recoverable copy, and running it twice changes
-nothing the second time. Add `--dry-run` to see the whole pass without a single write.
+Nunca `@latest` a escondidas: quien clone dentro de tres meses tendrá lo mismo que tú.
+Un `git pull` no escribe nada en tu máquina; `rsc doctor` te dice qué ya no cuadra.
 
-**What it fixes on its own** — putting the harness back to what was already declared:
-dangling links from a clone, hooks wired several times, the 0.1 layout no assistant reads.
+> `.claude/rsc-bootstrap.mjs` es código que se ejecuta en cada sesión. Revisa los cambios a ese
+> fichero como revisarías un workflow de CI.
 
-**What it asks about** — anything that changes a decision: moving the harness to another
-assistant, or touching files you already committed.
+**Skills propias.** Las que escribe tu equipo viven en el repo y funcionan al clonar.
+rsc nunca las instala, actualiza ni sobrescribe: su versión es el commit.
 
-**What it never touches:** skills and agents you wrote by hand. rsc did not install them,
-so rsc does not repair, move or delete them — not even when rebuilding from scratch.
+![Memoria entre sesiones: cada sesión retoma donde lo dejó la anterior](docs/img/readme/readme-13-memoria.png)
 
-## Update
+Al cerrar, guarda rama, ficheros y commits; al abrir, te dice dónde lo dejaste.
+Nunca guarda prompts, respuestas ni secretos, y no sale de tu máquina. `rsc memory off` lo apaga.
 
-`rsc` is an npm package, so updating is two steps — bump the package, then
-re-sync what's already wired into your project:
+![Una rama, una copia de trabajo](docs/img/readme/readme-18-worktrees.png)
 
-```bash
-npm install -g @damiangilgonzalez/harness@latest   # global install: pull the newest catalog
-rsc sync                               # refresh managed skills + hooks (auto-detects your assistant)
-```
-
-Not sure what a bump touches? Preview the exact commands without writing anything:
+Cada rama en su worktree, cortada siempre desde `origin`.
 
 ```bash
-rsc upgrade --dry-run                  # prints the npm install + rsc sync lines for your target
+rsc worktrees new avisos
+rsc worktrees reap --merged --confirm   # borra los ya fusionados, nunca los que tienen cambios
 ```
 
-Running through `npx` (no global install)? There's nothing to upgrade —
-`npx @damiangilgonzalez/harness@latest` always fetches the latest published catalog; just run
-`rsc sync` afterwards if the project already has skills installed.
+![¿Algo raro? doctor y repair](docs/img/readme/readme-14-doctor.png)
 
-Every sync snapshots the project first, so a bad update is always reversible:
+`doctor` diagnostica; `repair` devuelve el harness a lo declarado. Enseña lo que va a tocar,
+guarda una copia y nunca toca las skills que escribiste a mano.
 
 ```bash
-rsc backups                            # list project-local snapshots
-rsc restore latest --dry-run           # preview restoring the newest
-rsc restore <snapshot-id>              # restore it
+npx @damiangilgonzalez/harness doctor
+npx @damiangilgonzalez/harness@latest repair --dry-run
 ```
 
 ---
 
-## How recommendation works
-
-Two faces, one catalog (`manifest.json`):
-
-- **In the terminal** — `rsc` / `rsc consult` rank the catalog against your words
-  (multilingual TF-IDF blended with exact tag/id weights and intent synonyms), merge that with what they
-  detect in your repo, and expand via each skill's `recommends`.
-- **In the chat** — `rsc-suggest` is a tiny always-on skill. When a task would
-  benefit from a skill you don't have, it names it and (one-word confirm) runs
-  `rsc add <id>` for you. It's the floor — installed with every profile.
-
-Repo detection maps real signals to skills: `package.json` + `next` → `nextjs`;
-`go.mod` → `go`; `pyproject.toml` → `fastapi`; `*.sql`/`prisma/` → `postgresdb`;
-`Dockerfile`/`.github/` → `docker`/`github-actions`; and so on. An empty repo
-just asks in plain language.
-
----
-
-## The catalog
-
-294 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
-The front door and the workspace brain.
-
-[init](skills/init/) · [harness](skills/harness/) · [orient](skills/orient/) · [suggest](skills/suggest/) · [bro](skills/bro/) · [unslop](skills/unslop/) · [author-skill](skills/author-skill/)
-
-> **harness** is the Karpathy *chaos→knowledge* engine — a `01-TOOLS/` layer (one
-> folder per provider, each with a working `test_connection`) and a `docs/`
-> self-improving wiki. It governs software *or* a whole company. **orient** is the
-> always-on compass that keeps a non-technical human oriented after every step.
-> **bro** is installed with every profile and rewrites any answer in plain, natural
-> language when the user asks — without making its full body always-on.
-
-> #### 📦 The `docs/` brain is now 100% Open Knowledge Format (OKF v0.1) conformant
->
-> Google Cloud published the [**Open Knowledge Format**](https://github.com/GoogleCloudPlatform/knowledge-catalog/tree/main/okf)
-> — a vendor-neutral standard for portable, agent-readable knowledge — built on the
-> same Karpathy *LLM-wiki* pattern our `docs/` engine has used from day one. We
-> independently converged on the same design, so adopting the standard cost almost
-> nothing. As of now, **every `docs/wiki/` is a valid, portable OKF bundle**:
->
-> - **Markdown + YAML frontmatter**, `type` on every concept doc, OKF-standard
->   fields (`title`, `description`, `resource`, `tags`, `timestamp`).
-> - **Standard markdown links** (not wikilinks) form the knowledge graph — any OKF
->   consumer reads it, *and* it stays a native Obsidian vault (graph, backlinks,
->   Properties, Bases). Same files, no export step.
-> - **Reserved files** honored: `index.md` (no frontmatter) for navigation,
->   `log.md` (newest-first, ISO 8601) for history.
->
-> Tarball a `wiki/` and any OKF tool — including Google's own viewer — can read it.
-> And the brain now **keeps your repo clean**: a loose file it ingests (a PDF at the
-> root, anything in `inbox/`) is *moved* into `raw/`, never left as clutter.
-
-### 📐 Spec-Driven Development
-Take a fuzzy intent to a shipped, verified change — phase by phase. `npx @damiangilgonzalez/harness install --profile core`.
-
-[source-grounded-development](skills/source-grounded-development/) · [simplify-code](skills/simplify-code/)
-
-> 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.
-
-### 💼 Run a business
-
-[finance-ops](skills/finance-ops/) · [invoicing](skills/invoicing/) · [bookkeeping](skills/bookkeeping/) · [pricing](skills/pricing/) · [sales-pipeline](skills/sales-pipeline/) · [lead-gen](skills/lead-gen/) · [cold-outreach](skills/cold-outreach/) · [proposals](skills/proposals/) · [contracts](skills/contracts/) · [customer-support](skills/customer-support/) · [client-onboarding](skills/client-onboarding/) · [retention](skills/retention/) · [hiring](skills/hiring/) · [people-ops](skills/people-ops/) · [inventory](skills/inventory/) · [logistics-ops](skills/logistics-ops/) · [procurement](skills/procurement/) · [meeting-notes](skills/meeting-notes/) · [sop-builder](skills/sop-builder/) · [project-ops](skills/project-ops/)
-
-### 💸 Raise & model money
-
-[pitch-deck](skills/pitch-deck/) · [investor-materials](skills/investor-materials/) · [financial-model](skills/financial-model/) · [fundraising](skills/fundraising/) · [unit-economics](skills/unit-economics/) · [grants](skills/grants/)
-
-### ⚖️ Legal, privacy & compliance
-
-[gdpr-privacy](skills/gdpr-privacy/) · [terms-conditions](skills/terms-conditions/) · [compliance](skills/compliance/) · [data-policy](skills/data-policy/) · [ip-trademark](skills/ip-trademark/)
-
-### 📣 Market & brand
-
-[marketing](skills/marketing/) · [seo-geo](skills/seo-geo/) · [content-engine](skills/content-engine/) · [social-publisher](skills/social-publisher/) · [brand-voice](skills/brand-voice/) · [brand-identity](skills/brand-identity/) · [newsletter](skills/newsletter/) · [landing-copy](skills/landing-copy/) · [ads](skills/ads/) · [article-writing](skills/article-writing/) · [case-studies](skills/case-studies/) · [video-shorts](skills/video-shorts/) · [podcast](skills/podcast/) · [market-research](skills/market-research/) · [competitor-watch](skills/competitor-watch/) · [press-kit](skills/press-kit/) · [community](skills/community/) · [webinar](skills/webinar/) · [review-management](skills/review-management/)
-
-### 🎬 Grow a channel
-Each with a `docs` feedback loop that learns from your own results. `remotion-video` edits programmatically — transitions, Whisper captions, silence removal.
-
-[youtube-api](skills/youtube-api/) · [youtube-strategy](skills/youtube-strategy/) · [youtube-ideation](skills/youtube-ideation/) · [youtube-thumbnails](skills/youtube-thumbnails/) · [youtube-packaging](skills/youtube-packaging/) · [remotion-video](skills/remotion-video/) · [tiktok-api](skills/tiktok-api/) · [instagram-api](skills/instagram-api/) · [shortform-strategy](skills/shortform-strategy/) · [shortform-ideation](skills/shortform-ideation/) · [shortform-packaging](skills/shortform-packaging/) · [shortform-editing](skills/shortform-editing/) · [viral-score](skills/viral-score/) · [linkedin-api](skills/linkedin-api/) · [linkedin-strategy](skills/linkedin-strategy/) · [linkedin-content](skills/linkedin-content/) · [linkedin-carousels](skills/linkedin-carousels/) · [linkedin-outreach](skills/linkedin-outreach/) · [medium-writing](skills/medium-writing/) · [medium-publishing](skills/medium-publishing/) · [medium-strategy](skills/medium-strategy/)
-
-### 🔌 Connect & automate
-
-[stripe](skills/stripe/) · [email-connector](skills/email-connector/) · [google-workspace](skills/google-workspace/) · [notion-connector](skills/notion-connector/) · [whatsapp-telegram](skills/whatsapp-telegram/) · [automation-flows](skills/automation-flows/) · [api-connector-builder](skills/api-connector-builder/) · [webhooks](skills/webhooks/) · [data-scraper](skills/data-scraper/) · [spreadsheet-ops](skills/spreadsheet-ops/) · [calendar-scheduling](skills/calendar-scheduling/) · [document-processing](skills/document-processing/) · [e-signature](skills/e-signature/)
-
-### ⚙️ Automation
-
-Operate the big automation platforms **programmatically or via MCP** — create and manage automations *dynamically*, not just design them on a canvas. `automation-strategy` decides whether / what / which platform; the platform skills drive the live REST API or MCP server (harness connectors ship for each). Complements `automation-flows` (visual design + importable workflow JSON).
-
-[automation-strategy](skills/automation-strategy/) · [n8n](skills/n8n/) · [make](skills/make/) · [zapier](skills/zapier/) · [power-automate](skills/power-automate/)
-
-### 📊 Data & analytics
-
-[analytics](skills/analytics/) · [dashboard](skills/dashboard/) · [kpi-framework](skills/kpi-framework/) · [reporting](skills/reporting/) · [ab-testing](skills/ab-testing/) · [forecasting](skills/forecasting/) · [data-cleaning](skills/data-cleaning/) · [business-intelligence](skills/business-intelligence/)
-
-### 🤖 AI — build it in
-
-[building-agents](skills/building-agents/) · [rag](skills/rag/) · [embeddings-search](skills/embeddings-search/) · [prompt-engineering](skills/prompt-engineering/) · [llm-pipeline](skills/llm-pipeline/) · [agent-eval](skills/agent-eval/) · [chatbot](skills/chatbot/) · [ai-media](skills/ai-media/) · [replicate-images](skills/replicate-images/) · [structured-extraction](skills/structured-extraction/) · [agent-safety](skills/agent-safety/) · [cost-tracking](skills/cost-tracking/)
-
-### 🛰️ AI — run it on
-
-[replicate](skills/replicate/) · [runpod](skills/runpod/) · [modal](skills/modal/) · [huggingface](skills/huggingface/) · [ollama](skills/ollama/) · [together-fireworks](skills/together-fireworks/) · [fal](skills/fal/)
-
-### 🎓 AI — train it
-
-Train and adapt open models end to end: classic ML, deep learning, NLP, fine-tuning (with Unsloth), building training datasets, choosing open-weight models by license/size, and serving them at throughput with vLLM. Facts that move monthly (versions, model licenses) are verified at author time and hedged.
-
-[machine-learning](skills/machine-learning/) · [deep-learning](skills/deep-learning/) · [nlp](skills/nlp/) · [finetuning](skills/finetuning/) · [training-data](skills/training-data/) · [unsloth](skills/unsloth/) · [open-weights](skills/open-weights/) · [vllm](skills/vllm/)
-
-### 🗣️ Languages
-
-[typescript](skills/typescript/) · [python](skills/python/) · [java](skills/java/) · [csharp-dotnet](skills/csharp-dotnet/) · [php](skills/php/) · [ruby](skills/ruby/) · [cpp](skills/cpp/) · [elixir](skills/elixir/) · [bash-scripting](skills/bash-scripting/) · [sql](skills/sql/) · [go](skills/go/)
-
-### 🏗️ Frameworks & app stacks
-
-[fastapi](skills/fastapi/) · [nextjs](skills/nextjs/) · [react](skills/react/) · [react-native](skills/react-native/) · [vue-nuxt](skills/vue-nuxt/) · [angular](skills/angular/) · [svelte](skills/svelte/) · [astro](skills/astro/) · [solid-js](skills/solid-js/) · [htmx](skills/htmx/) · [nodejs](skills/nodejs/) · [nestjs](skills/nestjs/) · [django](skills/django/) · [laravel](skills/laravel/) · [rails](skills/rails/) · [spring-boot](skills/spring-boot/) · [phoenix](skills/phoenix/) · [flutter](skills/flutter/) · [swift-ios](skills/swift-ios/) · [kotlin-android](skills/kotlin-android/) · [compose-multiplatform](skills/compose-multiplatform/) · [expo](skills/expo/) · [tauri](skills/tauri/) · [electron](skills/electron/) · [rust](skills/rust/) · [wordpress](skills/wordpress/) · [shopify](skills/shopify/) · [no-code-app](skills/no-code-app/) · [chrome-extension](skills/chrome-extension/) · [api-design](skills/api-design/)
-
-### 🎮 Game development
-
-Three engines + engine-agnostic disciplines. Every engine skill pins the current version and bans deprecated APIs, so the agent stops emitting stale Godot-3 / legacy-Unity code.
-
-[godot](skills/godot/) · [unity](skills/unity/) · [unreal](skills/unreal/) · [game-design](skills/game-design/) · [game-storytelling](skills/game-storytelling/) · [level-design](skills/level-design/) · [gamedev-shaders](skills/gamedev-shaders/) · [gamedev-multiplayer](skills/gamedev-multiplayer/) · [gamedev-physics](skills/gamedev-physics/) · [gamedev-pathing](skills/gamedev-pathing/) · [gamedev-shipping](skills/gamedev-shipping/)
-
-### 🗄️ Databases & data layer
-
-[postgresdb](skills/postgresdb/) · [mysql](skills/mysql/) · [mongodb](skills/mongodb/) · [redis](skills/redis/) · [supabase](skills/supabase/) · [neon](skills/neon/) · [planetscale](skills/planetscale/) · [sqlite-turso](skills/sqlite-turso/) · [prisma-orm](skills/prisma-orm/) · [drizzle-orm](skills/drizzle-orm/) · [firebase](skills/firebase/) · [dynamodb](skills/dynamodb/) · [vector-db](skills/vector-db/) · [clickhouse-analytics](skills/clickhouse-analytics/) · [duckdb](skills/duckdb/) · [db-migrations](skills/db-migrations/) · [backups](skills/backups/)
-
-### ☁️ Ship & operate — platforms
-
-[vercel](skills/vercel/) · [netlify](skills/netlify/) · [cloudflare](skills/cloudflare/) · [railway](skills/railway/) · [render](skills/render/) · [fly-io](skills/fly-io/) · [coolify](skills/coolify/) · [hetzner](skills/hetzner/) · [digitalocean](skills/digitalocean/) · [aws-essentials](skills/aws-essentials/) · [gcp-essentials](skills/gcp-essentials/)
-
-### 🛠️ Ship & operate — devops
-
-[docker](skills/docker/) · [github-actions](skills/github-actions/) · [git-workflow](skills/git-workflow/) · [domains-dns](skills/domains-dns/) · [monitoring](skills/monitoring/) · [email-deliverability](skills/email-deliverability/) · [scaling](skills/scaling/) · [deployment](skills/deployment/) · [deprecation](skills/deprecation/)
-
-### 🔒 Ship & operate — quality & security
-
-[code-review](skills/code-review/) · [security-scan](skills/security-scan/) · [secure-coding](skills/secure-coding/) · [testing-py](skills/testing-py/) · [testing-web](skills/testing-web/) · [testing-go](skills/testing-go/) · [e2e-testing](skills/e2e-testing/) · [accessibility](skills/accessibility/) · [performance](skills/performance/) · [error-handling](skills/error-handling/) · [observability](skills/observability/)
-
-### 🌀 Motion & interface craft
-
-[motion-craft](skills/motion-craft/) · [ui-engineering](skills/ui-engineering/) · [variant-explorer](skills/variant-explorer/)
-
-### 🎨 Design & content craft
-
-[design-loop](skills/design-loop/) · [design](skills/design/) · [design-dna](skills/design-dna/) · [presentations](skills/presentations/) · [course-storytelling](skills/course-storytelling/) · [course-builder](skills/course-builder/) · [technical-writing](skills/technical-writing/) · [translation-l10n](skills/translation-l10n/)
-
-### 🧠 Knowledge & meta
-
-[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 — 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-spec](skills/implement-spec/) | Builds a whole spec from its `to-tickets` graph: parallel subagents in worktrees, one integration branch, `code-review` at the end. |
-| [implement](skills/implement/) | Builds one loose 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` → `pr` |
-| Touched a screen | `revision-de-cambios` → `revision-interfaz` → `code-review` → `pr` |
-
-| 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. |
-| [pr](skills/pr/) | Writes the PR body: a visual summary, before/after evidence, and the merge danger (one-way or two-way door, blast radius). |
-| [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. |
-| [retro](skills/retro/) | Retrospective on a session: what to change in the agent's environment. You approve every change. |
-| [writing-for-agents](skills/writing-for-agents/) | How to write documents an agent consumes. |
-
----
-
-## Multi-target
-
-`skills/<name>/` is the catalog source. On install the real files land **once**
-in the project at `.rsc/skills/<id>/`; each assistant you pick gets a symlink
-(or a converted file) back to that shared base — pick several and nothing is
-duplicated. The wizard asks which ones; `--target a,b` does it non-interactively.
-
-| Target | Skill destination (→ `.rsc/skills/<id>/`) | Always-on detector |
-| --- | --- | --- |
-| `claude` | `.claude/skills/<id>/` → symlink (copy on Windows) | SessionStart hook in `.claude/settings.json` |
-| `codex` | `.codex/rsc/<id>/` → symlink | block in `AGENTS.md` |
-| `copilot` | `.github/rsc/<id>/` → symlink | block in `.github/copilot-instructions.md` |
-| `cursor` | `.cursor/rules/<id>.mdc` (converted) | always-apply rule |
-| `gemini` | `.gemini/rsc/<id>/` → symlink | block in `GEMINI.md` |
-| `windsurf` | `.windsurf/rsc/<id>/` → symlink | rule in `.windsurf/rules/rsc-suggest.md` |
-| `cline` | `.clinerules/rsc/<id>/` → symlink | rule in `.clinerules/rsc-suggest.md` |
-| `antigravity` | `.antigravity/rsc/<id>/` → symlink | block in `.antigravity/AGENTS.md` |
-| `zed` | `.zed/rsc/<id>/` → symlink | block in `AGENTS.md` |
-| `continue` | `.continue/rsc/<id>/` → symlink | rule in `.continue/rules/rsc-suggest.md` |
-| `roo` | `.roo/rsc/<id>/` → symlink | rule in `.roo/rules/rsc-suggest.md` |
-| `amp` | `.amp/rsc/<id>/` → symlink | block in `AGENTS.md` |
-| `opencode` | `.opencode/rsc/<id>/` → symlink | block in `AGENTS.md` |
-| `jules` | `.jules/rsc/<id>/` → symlink | block in `AGENTS.md` |
-| `junie` | `.junie/rsc/<id>/` → symlink | block in `.junie/guidelines.md` |
-| `kiro` | `.kiro/rsc/<id>/` → symlink | doc in `.kiro/steering/rsc-suggest.md` |
-| `aider` | `.aider/rsc/<id>/` → symlink | block in `CONVENTIONS.md` |
-
-> `codex`, `zed`, `amp`, `opencode` and `jules` all share the one root
-> `AGENTS.md`; the block is idempotent, so picking several writes it once.
-
-The richer surfaces are intentionally narrower than skill support:
-
-| Targets | Stack agents | Native commands | Local session continuation |
-| --- | --- | --- | --- |
-| Claude Code | yes | agent + memory entries; skills already invoke natively | full |
-| Codex | yes | no separate project-command surface | full after `/hooks` trust |
-| Cursor desktop | yes | yes | assisted |
-| Gemini CLI, OpenCode | yes | yes | full |
-| GitHub Copilot | yes | yes | unsupported |
-| Junie, Kiro | yes | unsupported | unsupported |
-| Windsurf, Cline, Roo | unsupported | yes | unsupported |
-| Antigravity, Zed, Continue, Amp, Jules, Aider | unsupported | unsupported | unsupported |
-
-`manifest.json` is the generated public inventory: 34 agents (5 base + 29
-selective specialists) and 43 command entries (10 fixed + 33 stack aliases).
-Unsupported means rsc writes nothing for that surface; it does not emulate a
-provider feature with an unverified file.
-
----
-
-## Skill format
+## Catálogo
 
-Each skill is a directory under `skills/<name>/` whose `SKILL.md` frontmatter
-drives both triggering and the installer's recommendations:
+![294 skills por dominio](docs/img/readme/readme-15-catalogo.png)
 
-```yaml
----
-name: my-skill
-description: Use when [specific triggers]… Triggers: 'phrase', 'frase'. NOT x (that is sibling).
-tags: [keyword, keyword]        # what the consult advisor searches over
-recommends: [sibling-skill]     # what the system offers to install next
-profiles: [core, full]          # optional: named-profile membership
-origin: risco
----
-```
+294 skills en 25 dominios: software, negocio, contenido, datos e IA.
+Cada una se activa sola cuando la tarea encaja.
 
-The full agent-skill spec lives at
-[agentskills.io/specification](https://agentskills.io/specification).
+**[Ver el catálogo completo →](docs/catalogo.md)** · [Referencia técnica](docs/referencia-tecnica.md) ·
+[Cómo funciona por dentro](docs/como-funciona/README.md)
 
 ---
 
-## Repo layout & contributing
-
-`skills/<name>/` is the **single source of truth** — every skill is authored
-there, once. After editing any skill:
-
-```bash
-npm run manifest      # regenerate manifest.json from skills/*/SKILL.md
-npm run validate      # ajv-validate frontmatter + check recommends integrity
-npm test              # unit + integration tests
-bash scripts/eval-lint.sh   # validate every skills/*/evals/cases.yaml
-```
-
-`manifest.json` is generated, never hand-edited; CI runs `npm run manifest:check`
-and fails if it's stale or the skill count drifts. Adding a skill is: create
-`skills/<id>/SKILL.md` with `tags` + `recommends`, run `npm run manifest`, done —
-the rubric to hold it to is `scripts/skill-rubric.md`.
-
-This is a personal catalog. Bug reports welcome via GitHub issues; PRs fixing
-detector patterns, provider endpoints, or typos are appreciated.
-
-## Third-party skills
-
-Most of this catalog is written here. These are not, and they keep their author's credit:
-
-| Skills | Source | License |
-| --- | --- | --- |
-| `design-eng` · `animate` · `animate-expo` · `review-animations` · `improve-animations` · `find-animation-opportunities` · `animation-vocabulary` · `apple-design` · `prototype` · `pick-ui-library` · `write-swift` · `ask-sonner` | [emilkowalski/skills](https://github.com/emilkowalski/skills) by Emil Kowalski, commit `d23d7f8` | MIT |
-| part of the AI-tell corpus in `design` | [Leonxlnx/taste-skill](https://github.com/Leonxlnx/taste-skill) | MIT |
-
-Adapted, not mirrored: each one carries rsc frontmatter, routing evals, hand-offs to its siblings
-and — where it declares a binding rule — a checker with a test. The craft bar in them is the
-original author's. If you want the source of the motion material rather than this adaptation, go to
-[animations.dev](https://animations.dev/).
-
-## License
-
-MIT. See [LICENSE](LICENSE).
+<sub>Deriva del trabajo de Eric Risco en [ericrisco/rsc-harness](https://github.com/ericrisco/rsc-harness).</sub>