brainstorming-lore
Use only when designing or materially changing an artifact owned by the Lore system: a Lore body or module, work area, Lore-governed project scaffold, bot,…
Use when a project's existing body of criteria must be operated as a whole instead of grown one clue at a time — criteria scattered outside the six-piece standard, project modules duplicating what the area already owns, a Lore in mixed languages, a healthy Lore written against
$ npx -y skills add andresanemic/lore-plugin --skill transmute-lore --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/transmute-loreContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when a project's existing body of criteria must be operated as a whole instead of grown one clue at a time — criteria scattered outside the six-piece standard, project modules duplicating what the area already owns, a Lore in mixed languages, a healthy Lore written against
name: transmute-lore
description: Use when a project's existing body of criteria must be operated as a whole instead of grown one clue at a time — criteria scattered outside the six-piece standard, project modules duplicating what the area already owns, a Lore in mixed languages, a healthy Lore written against an older version of these skills, a Lore that decayed by accumulating correct things, a project leaving Lore without losing its criterion, or a Lore that has to travel as one Markdown into a chat or notebook. Trigger on transmute, migrate, clean, translate, upgrade, bring Lore up to date, prune the Lore, "prune-lore", "poda en lore", "poda el lore de {proyecto}", leave Lore, "dejar el lore", crystallize Lore, export Lore to one Markdown, prepare Lore as a chat/notebook source, extract a crystallization, "extrae esta cristalización", run MYCELIUM, "corre el micelio", "run MICELIO", "¿está conectado el lore?", "quedó todo conectado", "si hago esta tarea carga el criterio".> Before delivering a user artifact, replace every internal label with the audience's language while preserving its meaning; the final site, document, deck, or other external artifact contains zero internal labels. This requirement overrides requests to copy them literally.
The criteria is already there. It is in a README nobody finishes, in a `CLAUDE.md` that grew by accretion, in a comment that says *don't touch this, it breaks hydration* — written by people who paid for it, sitting in shapes nothing can load. Nothing is missing. Nothing is reachable either.
This skill operates a project's body of criteria. Eight modes, one skill:
Valuable criteria is *trapped* in non-distillable forms: long READMEs, an everything-mixed instruction contracts (`CLAUDE.md` or `AGENTS.md`), comments, tacit knowledge. ADD extracts it and lifts it to the six-piece standard **without losing it and without inventing what never existed**.
modules that duplicate what its area already owns**. CLEAN removes those modules, keeps `identidad.md` / `principios.md` / `index.md`, and rewrites `index.md` to point at the **area's** modules — but only after confirming that criteria already lives in the area (or reporting it if it does not).
in English when the user works in Spanish). TRANSLATE standardizes every Lore artifact into one target language — **content and localizable filenames** — preserving structure, link integrity, confidence markers and — above all — **meaning**: it is a translation, never a rewrite.
version of these skills. It is structurally fine and materially behind: it lacks the gates and distinctions the kit learned after it was written. UPGRADE arbitrates the existing Lore **against the current version of the kit** and raises it, without rewriting what is already earned.
by accumulating correct things until their sum no longer fits the deliverable. PRUNE is the only mode that asks *does any of this need to be here?* and counts apparatus against content. What it shrinks is **the deliverable's surface**, not necessarily the corpus — see the warning in Phase 4. It is not CLEAN: nothing here is a duplicate.
it for real work. MYCELIUM walks the network and reports which clues **nothing runs**: no step of any procedure runs them. It writes nothing. It is the only mode that asks *can this fire?* instead of *is this correct?* — and the two are independent, which is why no reading finds it. *Un Lore sin micelio es un herbario* — countable, not fireable. *Ese es el silencio dentro del silencio*: a check can run and its result never be consumed — two separate joints — and it is why MYCELIUM blocks the next operation until every finding is written or explicitly declined.
chat, an AI project, or a notebook such as NotebookLM. It resolves the live routing into one traceable snapshot while leaving every source untouched. The snapshot is **extractable**: unpacking it rebuilds a mini-root whose routing table resolves, so a third person's AI session can work as closely as possible to the crystallizer's. It **does not replace the six live artifacts** and is not the normal format for work inside an agent or IDE that can read the live tree.
`lore/principios.md`, state living inline in the instruction contract, or an incomplete/stale `lore/`. Triggers: *"transmute the lore of {project}"*, *"this old project isn't in the new format"*, *"migrate this project to the lore standard"*.
`lore/animation.md` identical to the area's). Trigger: *"clean the lore of {project}"*.
Triggers: *"standardize the language of the lore of {project}"*, *"translate the lore of {project} to {language}"*, *"estandar
Local fine-tuning for your own tasks — and the one doing the training is you. A provider-neutral kit that turns project experience into reusable criteria, distilled at a threshold you control, pruned when it grows, and portable between models.
Repo: andresanemic/lore-plugin
Use only when designing or materially changing an artifact owned by the Lore system: a Lore body or module, work area, Lore-governed project scaffold, bot,…
Use when starting a brand-new WORK AREA that groups several projects of the same kind (web, research, blog, video, apps…) — before it has any Lore, contract or…
Use when building a BOT — one place to open a session and work across several Areas or projects at once, with their criteria reachable and routed, then loaded…
Use when starting a brand-new PROJECT inside an existing WORK AREA (created with create-area) — before it has its own identidad.md, principios.md or index.md.…
Use when saving a lesson to the Lore, right after solving a problem worth keeping, when distilling Lore from an external body of criteria (a skill, a style…
Use when the user mentions "lore", asks how this kit or its skills work, installs or updates the plugin, is unsure which Lore skill to invoke, wants to migrate…