New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Knowledge Setup

by nimbalyst in nimbalyst/nimbalyst

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…

MITAuto-check passedKnowledge Management

Install Knowledge Setup

skills CLI
$ npx skills add nimbalyst/nimbalyst --skill knowledge-setup -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nimbalyst/nimbalyst knowledge-setup --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nimbalyst/nimbalyst.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/nimbalyst-wiki/skills/knowledge-setup .claude/skills/knowledge-setup && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
knowledge-setup
GitHub stars
1.8k
Token cost
~2.2k tokens
SKILL.md length
1,194 words
Files
2 (incl. references)
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

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…

  • Works in 5 steps: Packs → Kinds → Vocabulary → …
  • The user wants to start a team wiki
  • SKILL.md covers 0. Packs, 1. Kinds, 2. Vocabulary and 3. Wiki home page, plus 2 more sections
  • Calls git

What it does

Knowledge Setup is an agent skill from nimbalyst/nimbalyst. 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.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/wiki-guide.md`).

It sits in Knowledge Management, covering Knowledge graphs and Knowledge bases. The repository describes itself as: 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… The licence is MIT.

When your agent uses it

  • The user wants to start a team wiki
  • Add a vocabulary pack
  • Check that an existing one is set up

Example prompts

  • “How we write this wiki”
  • “/knowledge-setup”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Packs
  2. Kinds
  3. Vocabulary
  4. Wiki home page
  5. Guide page

What it can do on your machine

Read from SKILL.md and the folder at commit a3dbdb4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Knowledge Setup loads about 2.2k tokens when it runs, and up to ~3.8k if it reads all its reference files. Until then it costs about 132 tokens; SKILL.md has 1,194 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~132
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nimbalyst/nimbalyst at commit a3dbdb4, republished under its MIT licence (© nimbalyst). 1,194 words, ~2,182 tokens.

Download SKILL.mdSave it as .claude/skills/knowledge-setup/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
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/legacy/wiki-v1-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.

Knowledge setup

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.

0. Packs

PackAddsWhen
coreLabels area, home, topic, person, organization (and the deprecated concept, loadable only); the general relationship verbs.Always.
marketLabels 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.
specLabels 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. Kinds

  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.

2. Vocabulary

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: every predicate in the pack's predicates.yaml whose id is not in the registry. An existing predicate with the same id but a different definition is a conflict: keep it and report it.
  • labels.labels: every label whose id is not in the registry. A label that already exists (a pack may extend one another pack defines, as market does with organization) is sent only if the pack adds to it: send the existing entry unchanged except properties, factBox and expects extended with the pack's entries it lacks (existing order first). Never change any other key of an existing label.
  • labels.properties: every field property whose id is not in the registry. An existing one that differs is a conflict.
  • labels.claimProperties: every entry whose predicate id has none yet.

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.

Show full SKILL.md (470 more words)Show less

3. Wiki home page

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 title such as "<Project> wiki", and a short body saying what the wiki covers. There is one home page per project; if you find several, report them and use none until the user picks.

4. Guide page

The guide tells people and agents what belongs in the wiki. It is a wiki page, so it syncs to the team and the web console like any other page, and a team may rewrite it completely.

  • Base version: 2. Bump it whenever references/wiki-guide.md changes.
  • Assemble the text: references/wiki-guide.md holds a section per optional pack between <!-- pack:<id> --> and <!-- /pack:<id> --> lines. Keep the sections of installed packs, drop the rest, and remove the marker lines. That text is "the base" below.
  • Find it: an entity whose aliases contain wiki-guide (include archived items; an archived guide means the team retired it, so report that and do not recreate it).

If there is no guide page, create it:

  • type: entity, title: How we write this wiki, kind: topic, labels: [topic], parent set to the home page, aliases: [wiki-guide].
  • tags: [wiki-guide-base:2] (the base version it was installed from).
  • description: the assembled base, unchanged.
  • Read it back with wiki_get and confirm it has an issue key and the body.

If a guide page already exists, never overwrite it. Compare its body with the base, ignoring whitespace-only differences, and read its wiki-guide-base:<n> tag:

  • Same text: report "already present, matches base version <n>".
  • The only difference is the section of a pack installed after the guide was: report "already present, missing the <pack> section".
  • Different text, tag equals the current base version: the team has edited it. Report "already present, edited by the team".
  • Different text, older or missing tag: the base guide has changed since it was installed, and the team may also have edited it. Report both facts.

In the "different" and "missing section" cases, offer the user a diff between their page and the base, and offer a merge: keep every team edit, and propose only the base changes (or the missing pack section) that do not conflict with them. Write the merged body with wiki_update_item (description, plus the tag set to the current base version, keeping other tags) only after the user approves the merged text. A team that has replaced the guide on purpose may decline; that is final until they ask again.

Report

End with one line per step: packs (installed, added this run), kinds (each kind: created / already present / fields added / conflict), vocabulary (per pack: labels, properties and predicates added, labels extended, or none; conflicts), home page (key), guide page (key and status from step 4).

© nimbalyst, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in plugins/nimbalyst-wiki/skills/knowledge-setup of nimbalyst/nimbalyst.

  • SKILL.md
  • references/wiki-guide.md

Open the folder on GitHubat commit a3dbdb4

Compare with similar skills

Knowledge Setup next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Knowledge Setup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Knowledge Setup this skillnimbalyst/nimbalyst1.8k—~2.2kAutomated safety check: PassMIT
LLM Wiki Knowledge GraphEgonex-AI/Understand-Anything85k1 repos~1.5kAutomated safety check: PassMIT
My WikiNimaChu/my-wiki124—~674Automated safety check: PassMIT
Openloomi Memorymelandlabs/openloomi1k—~6kAutomated safety check: PassApache-2.0
HypatiaMarchLiu/hypatia239—~7.9kAutomated safety check: NotesMIT
Askagenticnotetaking/arscontexta3.5k1 repos~5.7kAutomated safety check: PassMIT

Similar skills

  • LLM Wiki Knowledge Graph

    Egonex-AI/Understand-Anything

    Detects a Karpathy-pattern LLM wiki and builds an interactive knowledge graph with entities, implicit relationships and topic clusters.

    85k GitHub starsUsed in 1 repo~1.5k tokens
    Knowledge ManagementAuto-check passed

  • My Wiki

    NimaChu/my-wiki

    Work with a local My Wiki knowledge base, Dashboard, and knowledge graph.

    124 GitHub stars~674 tokensUpdated 22 days ago
    Knowledge ManagementAuto-check passed

  • Openloomi Memory

    melandlabs/openloomi

    openloomi Memory tools - search and manage the holistic context (people, projects, decisions, knowledge base, chat insights).

    1k GitHub stars~6k tokensUpdated 13 days ago
    Knowledge ManagementAuto-check passed

  • Hypatia

    MarchLiu/hypatia

    Interact with the Hypatia AI memory system using natural language.

    239 GitHub stars~7.9k tokensUpdated 8 days ago
    Knowledge ManagementAuto-check: notes

  • Ask

    agenticnotetaking/arscontexta

    Query the bundled research knowledge graph for methodology guidance.

    3.5k GitHub starsUsed in 1 repo~5.7k tokens
    Knowledge ManagementAuto-check passed

  • Mini Context Graph

    github/awesome-copilot

    Official

    A persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph.

    40k GitHub starsUsed in 1 repo~2k tokens
    Knowledge ManagementAuto-check passed

More from nimbalyst/nimbalyst

All 14 skills in this repo

  • Knowledge Graph

    nimbalyst/nimbalyst

    Write a project's knowledge pages in Nimbalyst Pages -- record what people said and decided in the page it affects, keep typed pages for the things the team tracks (its own types, such as modules…

    1.8k GitHub stars~3.5k tokensUpdated 2 days ago
    Auto-check passed

  • Knowledge Setup

    nimbalyst/nimbalyst

    Set up or check a project's knowledge pages in Nimbalyst Pages -- install the editable "How we write this wiki" guide page, define the team's own page types (and subtypes) and the named relations…

    1.8k GitHub stars~1.8k tokensUpdated 2 days ago
    Auto-check passed

  • Canvas

    nimbalyst/nimbalyst

    Author Nimbalyst Project Canvas boards (.canvas files) — an infinite canvas whose cards are live editors for real workspace files and shared documents, arranged spatially and wired with edges.

    1.8k GitHub stars~2.6k tokensUpdated 2 days ago
    Auto-check passed

  • Datamodellm

    nimbalyst/nimbalyst

    Create visual data models for database schemas using Nimbalyst's DataModelLM editor.

    1.8k GitHub stars~713 tokensUpdated 2 days ago
    Auto-check passed

  • Excalidraw

    nimbalyst/nimbalyst

    Create diagrams and visual drawings using Excalidraw (.excalidraw files).

    1.8k GitHub stars~1.4k tokensUpdated 2 days ago
    Auto-check passed

  • Extension Development

    nimbalyst/nimbalyst

    Build, install, and hot-reload Nimbalyst extensions using MCP tools.

    1.8k GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Knowledge Setup

What does Knowledge Setup do?

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…. Knowledge Setup is an agent skill from nimbalyst/nimbalyst. 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.

When should I use Knowledge Setup?

Knowledge Setup fits situations like: the user wants to start a team wiki; add a vocabulary pack; check that an existing one is set up.

How do I install Knowledge Setup in Claude Code?

Run `npx skills add nimbalyst/nimbalyst --skill knowledge-setup -a claude-code`. Or copy the skill folder (plugins/nimbalyst-wiki/skills/knowledge-setup in nimbalyst/nimbalyst) into .claude/skills/knowledge-setup in your project. Claude Code loads it when a task matches its description.

How do I install Knowledge Setup in Codex?

Run `npx skills add nimbalyst/nimbalyst --skill knowledge-setup -a codex`. Or copy the skill folder (plugins/nimbalyst-wiki/skills/knowledge-setup in nimbalyst/nimbalyst) into .agents/skills/knowledge-setup in your project. Codex loads it when a task matches its description.

Can I use Knowledge Setup in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nimbalyst/nimbalyst --skill knowledge-setup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/knowledge-setup, .gemini/skills/knowledge-setup, .github/skills/knowledge-setup and .opencode/skills/knowledge-setup in your project.

What does Knowledge Setup need to run?

Going by SKILL.md and its folder, Knowledge Setup needs the command-line tools its instructions call (git).

Does Knowledge Setup access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Knowledge Setup safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Knowledge Setup use?

Knowledge Setup is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Knowledge Setup use?

About 2.2k tokens (SKILL.md is roughly 8.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.

What are the alternatives to Knowledge Setup?

Skills that share tags, products or a category with Knowledge Setup: LLM Wiki Knowledge Graph (Egonex-AI/Understand-Anything, 85k stars), My Wiki (NimaChu/my-wiki, 124 stars), Openloomi Memory (melandlabs/openloomi, 1k stars) and Hypatia (MarchLiu/hypatia, 239 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Knowledge Setup?

nimbalyst (a GitHub organization) maintains it in nimbalyst/nimbalyst, which has 1,847 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 5, 2026.

Source: nimbalyst/nimbalyst on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.