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.
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…
$ npx skills add nimbalyst/nimbalyst --skill knowledge-setup -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nimbalyst/nimbalyst knowledge-setup --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/nimbalyst/nimbalyst.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/nimbalyst-pages/skills/knowledge-setup .claude/skills/knowledge-setup && rm -rf skills-srcUse ~/.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/
Install the "knowledge-setup" agent skill from https://github.com/nimbalyst/nimbalyst/tree/main/plugins/nimbalyst-pages/skills/knowledge-setup into .claude/skills/knowledge-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-setup", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/nimbalyst/nimbalyst/tree/main/plugins/nimbalyst-pages/skills/knowledge-setupType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add nimbalyst/nimbalyst --skill knowledge-setup -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nimbalyst/nimbalyst knowledge-setup --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nimbalyst/nimbalyst.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/nimbalyst-pages/skills/knowledge-setup .agents/skills/knowledge-setup && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "knowledge-setup" agent skill from https://github.com/nimbalyst/nimbalyst/tree/main/plugins/nimbalyst-pages/skills/knowledge-setup into .agents/skills/knowledge-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-setup", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nimbalyst/nimbalyst --skill knowledge-setup -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nimbalyst/nimbalyst knowledge-setup --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nimbalyst/nimbalyst.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/nimbalyst-pages/skills/knowledge-setup .cursor/skills/knowledge-setup && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "knowledge-setup" agent skill from https://github.com/nimbalyst/nimbalyst/tree/main/plugins/nimbalyst-pages/skills/knowledge-setup into .cursor/skills/knowledge-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-setup", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/nimbalyst/nimbalyst.git --path plugins/nimbalyst-pages/skills/knowledge-setup--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add nimbalyst/nimbalyst --skill knowledge-setup -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nimbalyst/nimbalyst knowledge-setup --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nimbalyst/nimbalyst.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/nimbalyst-pages/skills/knowledge-setup .gemini/skills/knowledge-setup && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "knowledge-setup" agent skill from https://github.com/nimbalyst/nimbalyst/tree/main/plugins/nimbalyst-pages/skills/knowledge-setup into .gemini/skills/knowledge-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-setup", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install nimbalyst/nimbalyst knowledge-setupInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add nimbalyst/nimbalyst --skill knowledge-setup -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nimbalyst/nimbalyst.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/nimbalyst-pages/skills/knowledge-setup .github/skills/knowledge-setup && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "knowledge-setup" agent skill from https://github.com/nimbalyst/nimbalyst/tree/main/plugins/nimbalyst-pages/skills/knowledge-setup into .github/skills/knowledge-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-setup", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nimbalyst/nimbalyst --skill knowledge-setup -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nimbalyst/nimbalyst knowledge-setup --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nimbalyst/nimbalyst.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/nimbalyst-pages/skills/knowledge-setup .opencode/skills/knowledge-setup && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "knowledge-setup" agent skill from https://github.com/nimbalyst/nimbalyst/tree/main/plugins/nimbalyst-pages/skills/knowledge-setup into .opencode/skills/knowledge-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-setup", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
knowledge-setupSet 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…
Knowledge Setup is an agent skill from 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 between them, and report content from the earlier knowledge graph without changing it. Safe to re-run; it never overwrites or deletes. Use when the user wants to start a team wiki or knowledge base, add a type or a relation, or check that an existing setup is complete. To write pages, use the knowledge-graph skill.
Its SKILL.md is about 1.8k 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.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit a3dbdb4. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are json).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Knowledge Setup loads about 1.8k tokens when it runs, and up to ~3k if it reads all its reference files. Until then it costs about 132 tokens; SKILL.md has 883 words of instructions outside code blocks.
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.
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.
The full file from nimbalyst/nimbalyst at commit a3dbdb4, republished under its MIT licence (© nimbalyst). 883 words, ~1,846 tokens.
.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.<!-- GENERATED by scripts/build-wiki-plugin.mjs from packages/extensions/knowledge/skills-source. Do not edit; edit the source and re-run the script. Its references/ files are generated from the same source. -->
Sets up what the knowledge-graph skill writes into. Every step checks what exists first, adds only what is missing, and reports created, already present, conflict, or needs the person. Never delete, rename, archive or overwrite anything; stop and ask when a step would.
The base guide is references/wiki-guide.md next to this file. Example relations are in ../knowledge-graph/references/relations.yaml.
Setup works on a team project's pages on the Nimbalyst server. Follow the connect skill first: pages_status must report bound, and every call below takes the same repo and project arguments. A project created with pages_create_project already has its Home page. Types defined here are always the team's.
Read only; change nothing in this step.
tracker_list_types: the types that exist, any extends, and the relations (predicates) that exist.entity, claim, question, finding, investigation, ontology-proposal, project types that held decisions (keystone, decision-exploration), .nimbalyst/labels.yaml, predicates whose only subjectKinds is entity, and an entity titled "How we write this wiki". Report them as "earlier model, left in place". Do not edit or remove them, do not add labels or vocabulary packs, and never pass labels to tracker_define_type. Offer the move into pages as a separate job the person starts (../knowledge-graph/references/migrating-v1.md).references/wiki-guide.md, unchanged; its last line names the version.pages_status returns its guideLink when the project has one; listPages gives its uri, which you read with readCollabDoc.createSharedDoc (section, title: How we write this wiki, no parent, after the Home page's node when there is one, initialContent = the base text). Read it back at the returned uri and confirm the text is there.entity titled "How we write this wiki"): leave it. Offer to create the new page and carry over the team's own edits that still apply; create it only after the person approves the merged text.If the guide page exists, never overwrite it. Compare it with the base, ignoring whitespace:
When it differs, offer a diff and a merge that keeps every team edit and proposes only the base changes that do not conflict. Write it with applyCollabDocEdit only after the person approves the merged text. A team that rewrote the guide on purpose may decline; that is final until they ask again.
Define types only when the person asks or agrees. Ask what the team keeps several of and would want in a table. Suggest from what the project already discusses (module, technology, competitor, person are common); the team decides. A type for a single page is not a type.
Reuse first. Match on id and display name in tracker_list_types. If the project already has a fitting type (for example a competitor type), use it.
Define with tracker_define_type and schema. Keep it small: title plus two to four single-valued fields (select, string, boolean, user, date). Only single-valued fields show in a page header; multi-valued fields show only in tables. No labels, kind or qualifier fields.
{
"type": "technology",
"displayName": "Technology",
"displayNamePlural": "Technologies",
"icon": "memory",
"color": "#7c3aed",
"modes": { "inline": true, "fullDocument": true },
"idPrefix": "tech",
"idFormat": "ulid",
"fields": [
{ "name": "title", "type": "string", "required": true },
{ "name": "maturity", "type": "select", "options": [
{ "value": "ga", "label": "Generally available" },
{ "value": "beta", "label": "Beta" },
{ "value": "deprecated", "label": "Deprecated" }
] },
{ "name": "inStack", "type": "boolean" }
],
"roles": { "title": "title" }
}Subtypes set extends: <base type> and declare only what they add ({ "type": "library", "extends": "technology", "displayName": "Library", "displayNamePlural": "Libraries" }). A subtype's pages show in its base type's table and nest inside it in the tree.
Existing types: never pass overwrite without the person's approval, and then keep every existing field and option. Never pass confirmDestructive on your own.
Place each new type where the person wants it with moveSharedItem (kind: type, itemId = the type id, newParentFolderId = the parent page, or none for the top of the section). A subtype is not placed; it shows inside its base. Offer two or three sentences for the type's page saying what belongs in it.
Add a relation when the team links two of its types often and the link means one specific thing ("built on", "competes with"). Each one is a predicate with:
id (kebab-case), label, and inverseLabel (how it reads from the other page; the same as label when direction: symmetric)subjectKinds: the types a link can be written on; objectKinds: the types it can point at. Use the project's type ids; subtypes are covered through extends.valueShape: entity and direction: directed or symmetric. No qualifiers.Copy the shape from ../knowledge-graph/references/relations.yaml, renamed to the project's types, and send only new ids with tracker_define_type (predicates: [...]; it merges by id and keeps the rest). Do not add generic relations ("related to", "depends on"): a plain link says that already.
objectKinds to an existing predicate narrows it and counts as destructive. Propose it to the person; only with their approval pass confirmDestructive.removePredicates.End with one line per step: section, earlier-model content found (types, labels file, guide entity), guide page (link and status), types (each: created, already present, conflict, or needs placing), relations (added, already present, conflicts), and what the person still has to do in Pages.
© nimbalyst, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (references) in plugins/nimbalyst-pages/skills/knowledge-setup of nimbalyst/nimbalyst.
Open the folder on GitHubat commit a3dbdb4
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Knowledge Setup this skillnimbalyst/nimbalyst | 1.8k | — | ~1.8k | Automated safety check: Pass | MIT | |
| LLM Wiki Knowledge GraphEgonex-AI/Understand-Anything | 85k | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| My WikiNimaChu/my-wiki | 124 | — | ~674 | Automated safety check: Pass | MIT | |
| Openloomi Memorymelandlabs/openloomi | 1k | — | ~6k | Automated safety check: Pass | Apache-2.0 | |
| HypatiaMarchLiu/hypatia | 239 | — | ~7.9k | Automated safety check: Notes | MIT | |
| Askagenticnotetaking/arscontexta | 3.5k | 1 repos | ~5.7k | Automated safety check: Pass | MIT |
Egonex-AI/Understand-Anything
Detects a Karpathy-pattern LLM wiki and builds an interactive knowledge graph with entities, implicit relationships and topic clusters.
NimaChu/my-wiki
Work with a local My Wiki knowledge base, Dashboard, and knowledge graph.
melandlabs/openloomi
openloomi Memory tools - search and manage the holistic context (people, projects, decisions, knowledge base, chat insights).
MarchLiu/hypatia
Interact with the Hypatia AI memory system using natural language.
agenticnotetaking/arscontexta
Query the bundled research knowledge graph for methodology guidance.
github/awesome-copilot
A persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured 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…
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.
nimbalyst/nimbalyst
Create visual data models for database schemas using Nimbalyst's DataModelLM editor.
nimbalyst/nimbalyst
Create diagrams and visual drawings using Excalidraw (.excalidraw files).
nimbalyst/nimbalyst
Build, install, and hot-reload Nimbalyst extensions using MCP tools.
nimbalyst/nimbalyst
Create git commits using Nimbalyst's interactive commit proposal widget.
Categories
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…. Knowledge Setup is an agent skill from 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 between them, and report content from the earlier knowledge graph without changing it.
Knowledge Setup fits situations like: the user wants to start a team wiki; check that an existing setup is complete.
Run `npx skills add nimbalyst/nimbalyst --skill knowledge-setup -a claude-code`. Or copy the skill folder (plugins/nimbalyst-pages/skills/knowledge-setup in nimbalyst/nimbalyst) into .claude/skills/knowledge-setup in your project. Claude Code loads it when a task matches its description.
Run `npx skills add nimbalyst/nimbalyst --skill knowledge-setup -a codex`. Or copy the skill folder (plugins/nimbalyst-pages/skills/knowledge-setup in nimbalyst/nimbalyst) into .agents/skills/knowledge-setup in your project. Codex loads it when a task matches its description.
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.
SKILL.md names no scripts, command-line tools or credentials: Knowledge Setup is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
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.
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.
About 1.8k tokens (SKILL.md is roughly 7.4k 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 1.1k tokens, read only when the agent opens those files.
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.
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.