animation
Author animated technical explainer diagrams as .anim.json files for Nimbalyst's Animation…
Initialize or repair a project's knowledge graph in Nimbalyst trackers -- define the entity, claim, question, finding, and investigation kinds, merge the core vocabulary pack (and the market or spec pack when asked) into the label and predicate registries, create the wiki home
$ npx -y skills add nimbalyst/nimbalyst --skill knowledge-setup --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/knowledge-setupContext preview
The summary Claude sees to decide when to auto-load this skill.
Initialize or repair a project's knowledge graph in Nimbalyst trackers -- define the entity, claim, question, finding, and investigation kinds, merge the core vocabulary pack (and the market or spec pack when asked) into the label and predicate registries, create the wiki home
name: knowledge-setup description: Initialize or repair a project's knowledge graph in Nimbalyst trackers -- define the entity, claim, question, finding, and investigation kinds, merge the core vocabulary pack (and the market or spec pack when asked) into the label and predicate registries, create the wiki home page, and install the "How we write this wiki" guide page. Safe to re-run; it never overwrites or deletes. Use when the user wants to start a team wiki or knowledge base, add a vocabulary pack, or check that an existing one is set up.
<!-- GENERATED by scripts/build-wiki-plugin.mjs from packages/extensions/knowledge/claude-plugin/skills. Do not edit; edit the source and re-run the script. Its references/ files are generated from the same source. -->
> **Remote wiki tools.** This copy of the skill runs against the Nimbalyst wiki server, not the desktop app. Every `wiki_*` call takes `repo` (the output of `git remote get-url origin`) and, when `.nimbalyst/wiki.json` pins one, `project: { orgId, projectId }`. Every write (`wiki_create_item`, `wiki_update_item`, `wiki_define_type`) requires a `changesetId` from `wiki_begin_changeset`. The `wiki-keeper` skill covers resolving the project and changesets.
On the wiki server, `wiki_define_type` and the other tools act on the team project `wiki_status` resolved, and connecting a repository (`wiki_bind_repo` or `wiki_create_project`) already runs this setup there with the core pack. Use this skill when the user asks to check or repair a wiki's setup, or to add the market or spec pack.
Sets up everything the `knowledge-graph` skill writes into. Every step checks what exists first, adds only what is missing, and reports each step as **created**, **already present**, or **conflict**. Never delete, rename, or overwrite anything; stop and ask when a step would.
The kind definitions are in `../knowledge-graph/references/` (five kind files). The vocabulary is in `../knowledge-graph/references/packs/<pack>/`, each pack a `labels.yaml` (labels, field-stored properties, claim-property extensions) and a `predicates.yaml` (claim-stored verbs). The base wiki guide is `references/wiki-guide.md` next to this file. Copy them; do not paraphrase them.
| Pack | Adds | When | | --- | --- | --- | | `core` | Labels `area`, `home`, `topic`, `person`, `organization` (and the deprecated `concept`, loadable only); the general relationship verbs. | Always. | | `market` | Labels `product`, `market`, `capability`, `technology`, `protocol`, `format`, `connector`; market, maker and competition verbs; dated organization and product facts. | The team tracks the products, companies and markets it decides against. | | `spec` | Labels `subsystem`, `feature`, `surface`, `requirement`, `invariant`, `data-store`, `integration`, `wire-protocol`; structure and provenance verbs that point pages at code paths, decisions and sessions. | The wiki is the project's specification. |
Always install `core`. Ask the user which of `market` and `spec` to add, unless they already said. A pack is already installed when its first label exists (`market`: `product`; `spec`: `subsystem`); offer only the missing ones.
1. Call `wiki_list_types` and note which of `entity`, `claim`, `question`, `finding`, `investigation` already exist and who owns them (`personal` or `team:<name>`). 2. Sharing: nothing to decide. The server stores every kind as a team kind whatever `sharing` says. 3. For each missing kind, read its reference file and call `wiki_define_type` with `schema` set to the YAML converted to a JSON object (drop comments; change nothing else). 4. If a kind already exists, compare it to the reference. Missing fields or options (for example `entity.labels`) may be added with a `schema` + `overwrite: true` that keeps every existing field. Never remove, rename, or change the type of an existing field or option, never pass `confirmDestructive` on your own, and never overwrite a kind that differs in an incompatible way. Report each conflict to the user with the field names and stop for that kind.
Read the project's current registries from the `predicates` array and the `labels` object in the `wiki_list_types` result (missing means empty). Ignore any `.nimbalyst/*.yaml`: they are not the server's copy.
For `core`, then each chosen pack, in that order, make at most one `wiki_define_type` call carrying both halves. Both arguments merge by id: an entry replaces the entry with its id or is added, and entries you omit are kept. So send only what is new, never an entry the project already has.
Predicates are applied before labels in the same call, so a label may name a predicate the call adds. A property id that is already a predicate (or the reverse) is a conflict; report it and leave both alone. Never send `removePredicates` or `labels.remove`. If nothing is missing for a pack, make no call.
Look for an `entity` with `kind: home` (`wiki_list` with `type: entity` and `where` on `kind`). If one exists, use it and report it. Otherwise create one: `kind: home`, `labels: [home]`, no `parent`, a tit
Nimbalyst - The open-source visual workspace for Claude Code, Codex, and OpenCode. Run multiple coding agents in parallel, edit their work visually in markdown, mockups, and diagrams, and track tasks. Free, MIT-licensed desktop app for macOS, Windows, Linux, with mobile companion for iOS and Android.
Repo: nimbalyst/nimbalyst
Author animated technical explainer diagrams as .anim.json files for Nimbalyst's Animation…
Author Nimbalyst Project Canvas boards (.canvas files) — an infinite canvas whose cards are…
Create visual data models for database schemas using Nimbalyst's DataModelLM editor. Use when…
Create git commits using Nimbalyst's interactive commit proposal widget. ONLY use when the…
Create diagrams and visual drawings using Excalidraw (.excalidraw files). Use when the user…
Build, install, and hot-reload Nimbalyst extensions using MCP tools. Use when developing,…