Agent skill

My Wiki

by NimaChu in NimaChu/my-wiki

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

MITAuto-check passedKnowledge Management

Install My Wiki

skills CLI
$ npx skills add NimaChu/my-wiki --skill my-wiki -a claude-code

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

GitHub CLI
$ gh skill install NimaChu/my-wiki my-wiki --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/NimaChu/my-wiki.git skills-src && mkdir -p .claude/skills && cp -r skills-src/my-wiki-skill .claude/skills/my-wiki && 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
my-wiki
GitHub stars
124
Token cost
~674 tokens
SKILL.md length
276 words
Files
16 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

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

  • Explicitly requested remote/public knowledge access
  • Runs JavaScript scripts from its folder
  • Including 远程知识库

What it does

My Wiki is an agent skill from NimaChu/my-wiki. Work with a local My Wiki knowledge base, Dashboard, and knowledge graph. Also use for explicitly requested remote/public knowledge access, including “远程知识库”, “远程服务”, “公网知识库”, and “公网服务”.

Its SKILL.md is about 670 tokens, which your agent loads only when the skill is triggered. The skill folder holds 18 other files, including scripts and reference files (for example `.my-wiki-skill.json`, `agents/openai.yaml` and `references/commands.md`).

It sits in Knowledge Management, covering Knowledge graphs and Knowledge bases. It works with Obsidian. The repository describes itself as: Local-first AI knowledge app and Agent Skill with evidence-backed Wiki, an interactive knowledge universe, Viki Q&A, and shareable knowledge galaxies. The licence is MIT.

When your agent uses it

  • Explicitly requested remote/public knowledge access
  • Including 远程知识库

Example prompts

  • “/my-wiki”

Requirements

  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit f033614. 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

    Ships 3 files in scripts/ (JavaScript), which the agent can run.

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

  • Network

    No URLs in SKILL.md.

    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

My Wiki loads about 674 tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 49 tokens; SKILL.md has 276 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~674
With references · SKILL.md plus every file in references/, read only if the agent opens them
~15k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from NimaChu/my-wiki at commit f033614, republished under its MIT licence (© NimaChu). 276 words, ~674 tokens.

Download SKILL.mdSave it as .claude/skills/my-wiki/SKILL.md (or your agent's skills folder). This skill also uses 15 other files; get the full folder from GitHub.
name
my-wiki
description
Work with a local My Wiki knowledge base, Dashboard, and knowledge graph. Also use for explicitly requested remote/public knowledge access, including “远程知识库”, “远程服务”, “公网知识库”, and “公网服务”.

My Wiki

This Skill routes Agent work to the My Wiki project or an explicitly requested remote service. It contains a lightweight CLI bridge, not the application or a vault.

Choose A Route

Without a saved remote connection, normal My Wiki, knowledge-base, Dashboard, and graph requests use the local installation. Only explicit remote/public requests or a remote server URL initiate a first remote connection. A saved, enabled remote authorization makes ordinary bridge commands default to that service; use the Remote access reference when where reports remote mode. Explicit local intent overrides the saved connection with --local or --vault. Bare “连接 mywiki” must not initiate a first public connection.

RequestRead
Local installation, missing project/vault, selecting a local vaultLocal setup
Local CLI syntax and Dashboard launch commandsLocal commands
Query or answer from knowledgeQuery workflow
Capture a URL, document, folder, or image bundleIngest workflow
Distill, repair, or inspect knowledge healthMaintenance workflow
Galaxy naming, Concept/Reference structure, and OKF metadataKnowledge model
Evidence gates, OCR quality, formula review, and closureEvidence rules
Import or export a knowledge galaxySharing workflow
Open or operate the local DashboardDashboard workflow
Explicit remote/public connection and operationsRemote access
Dashboard Agent/provider behaviorDashboard Agent reference
IMA migration requestedIMA import
Firecrawl requested or ordinary webpage capture failedFirecrawl

Read only the references relevant to the task. Use the bundled scripts/my-wiki.mjs where to resolve the current target; follow Local setup only when a local layer is missing. Operational knowledge comes from the selected vault, not from searching the application source.

Use native OKF terms: Concept, Reference, and original. Keep private knowledge, credentials, and runtime state out of the application repository.

© NimaChu, 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 15 other files (scripts, references) in my-wiki-skill of NimaChu/my-wiki.

  • SKILL.md
  • .my-wiki-skill.json
  • agents/openai.yaml
  • references/commands.md
  • references/dashboard-agent.md
  • references/dashboard-runtime.md
  • references/evidence-rules.md
  • references/firecrawl-mcp.md
  • references/ima-local-import.md
  • references/knowledge-model.md
  • references/remote.md
  • references/setup.md
  • references/workflows.md
  • scripts/install.mjs
  • scripts/my-wiki.mjs
  • scripts/remote.mjs

Open the folder on GitHubat commit f033614

Compare with similar skills

My Wiki 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.

My Wiki compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
My Wiki this skillNimaChu/my-wiki124—~674Automated safety check: PassMIT
Engraphdevwhodevs/engraph171—~792Automated safety check: PassMIT
Obsidian Canvas BoardsAgriciDaniel/claude-obsidian15k—~1.4kAutomated safety check: PassMIT
LLM Wikilewislulu/llm-wiki-skill655—~3.7kAutomated safety check: PassNone
LLM Wiki Knowledge GraphEgonex-AI/Understand-Anything86k—~1.5kAutomated safety check: PassMIT
LLM Wikipraneybehl/llm-wiki-plugin118—~5.7kAutomated safety check: PassMIT

Similar skills

  • Engraph

    devwhodevs/engraph

    Index and search document collections using hybrid semantic + graph + full-text search.

    171 GitHub stars~792 tokensUpdated 4 mo ago
    Knowledge ManagementAuto-check passed
  • Obsidian Canvas Boards

    AgriciDaniel/claude-obsidian

    Creates, inspects and updates Obsidian JSON Canvas boards in a vault, with text, file, link, group and edge nodes, using safe recoverable edits.

    15k GitHub stars~1.4k tokensUpdated 28 days ago
    Knowledge ManagementAuto-check passed
  • LLM Wiki

    lewislulu/llm-wiki-skill

    Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers…

    655 GitHub stars~3.7k tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed
  • 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.

    86k GitHub stars~1.5k tokensUpdated today
    Knowledge ManagementAuto-check passed
  • LLM Wiki

    praneybehl/llm-wiki-plugin

    Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings.

    118 GitHub stars~5.7k tokensUpdated 26 days ago
    Knowledge ManagementAuto-check passed
  • Subscription Videos Metadata

    EfficientStreet/youtube-subscriptions-ingest

    Pull metadata from YouTube subscription videos into a second-brain vault as a real cross-linked knowledge graph — not just a flat archive.

    178 GitHub stars~7.1k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check: notes

Works with

Questions about My Wiki

What does My Wiki do?

Work with a local My Wiki knowledge base, Dashboard, and knowledge graph. My Wiki is an agent skill from NimaChu/my-wiki. Work with a local My Wiki knowledge base, Dashboard, and knowledge graph.

When should I use My Wiki?

My Wiki fits situations like: explicitly requested remote/public knowledge access; including 远程知识库.

How do I install My Wiki in Claude Code?

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

How do I install My Wiki in Codex?

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

Can I use My Wiki 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 NimaChu/my-wiki --skill my-wiki -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/my-wiki, .gemini/skills/my-wiki, .github/skills/my-wiki and .opencode/skills/my-wiki in your project.

What does My Wiki need to run?

Going by SKILL.md and its folder, My Wiki needs JavaScript for the scripts in its folder. Our summary lists: Node.js.

Does My Wiki access the network?

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.

Is My Wiki 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does My Wiki use?

My Wiki 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 My Wiki use?

About 674 tokens (SKILL.md is roughly 2.7k 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 15k tokens, read only when the agent opens those files.

What are the alternatives to My Wiki?

Skills that share tags, products or a category with My Wiki: Engraph (devwhodevs/engraph, 171 stars), Obsidian Canvas Boards (AgriciDaniel/claude-obsidian, 15k stars), LLM Wiki (lewislulu/llm-wiki-skill, 655 stars) and LLM Wiki Knowledge Graph (Egonex-AI/Understand-Anything, 86k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains My Wiki?

NimaChu (a GitHub user) maintains it in NimaChu/my-wiki, which has 124 GitHub stars. The repository was last updated on October 8, 2026.

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