Agent skill

Personal Knowledge Wiki

by zhayujie in zhayujie/CowAgent

Maintains a structured Markdown knowledge base in a knowledge/ folder by ingesting shared articles, synthesizing conversations and answering questions from it.

MITAuto-check passedKnowledge Management

Install Personal Knowledge Wiki

skills CLI
$ npx skills add zhayujie/CowAgent --skill knowledge-wiki -a claude-code

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

GitHub CLI
$ gh skill install zhayujie/CowAgent knowledge-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/zhayujie/CowAgent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/knowledge-wiki .claude/skills/knowledge-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
knowledge-wiki
GitHub stars
47k
Token cost
~924 tokens
SKILL.md length
367 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Maintains a structured Markdown knowledge base in a knowledge/ folder by ingesting shared articles, synthesizing conversations and answering questions from it.

  • Works in 3 steps: Ingest — User shares an article,… → Synthesize — Conversation produces… → Query — User asks about accumulated…
  • Saving an article or document you share as structured notes
  • SKILL.md covers Core Operations, Page Format, Index Format… and Log Format (knowledge/log.md), plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill keeps a persistent wiki in the knowledge/ directory and has three operations. Ingest reads an article or document you share, extracts key facts, picks or creates a category subfolder, writes a page and updates the index and log. Synthesize turns the insights from a conversation into a page and adds cross-references. Query checks the index for relevant pages and reads them, with memory search as a supplement.

Pages are Markdown files with lowercase kebab-case names, one topic per page and a Source line recording where the material came from. The index is a flat list of links with one-line summaries grouped by category, and the log is append-only with dated ingest and synthesize entries. Pages link to each other, and links are added only to pages that already exist, so the wiki forms a connected graph.

When your agent uses it

  • Saving an article or document you share as structured notes
  • Preserving insights from a conversation as a wiki page
  • Answering a question from the knowledge already collected

Example prompts

  • “Add this article on vector databases to my knowledge wiki.”
  • “Save what we just worked out about our deployment process as a wiki page.”
  • “What does my knowledge base say about prompt caching?”

Workflow steps

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

  1. Ingest — User shares an article, document, or resource
  2. Synthesize — Conversation produces valuable structured knowledge
  3. Query — User asks about accumulated knowledge

What it can do on your machine

Read from SKILL.md and the folder at commit 7142631. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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

Personal Knowledge Wiki loads about 924 tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 367 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~924

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 zhayujie/CowAgent at commit 7142631, republished under its MIT licence (© zhayujie). 367 words, ~924 tokens.

Download SKILL.mdSave it as .claude/skills/knowledge-wiki/SKILL.md (or your agent's skills folder).
name
knowledge-wiki
description
Manage the personal knowledge wiki. Use when the user shares articles, documents, or asks to organize knowledge; when a conversation produces insights worth preserving as structured knowledge; or when the user asks about the knowledge base.

Knowledge Wiki

Maintain a persistent, structured knowledge base in the knowledge/ directory.

Core Operations

1. Ingest — User shares an article, document, or resource
  1. Read and understand the source material
  2. Extract key facts, insights, and structured knowledge
  3. Determine the appropriate subdirectory:
    • Read knowledge/index.md to see existing categories
    • If a matching category exists, follow that structure
    • If not, create a new subdirectory with a clear name
  4. Create the knowledge page: knowledge/<category>/<slug>.md
  5. Update knowledge/index.md and append to knowledge/log.md
2. Synthesize — Conversation produces valuable structured knowledge
  1. Create a knowledge page under the appropriate category
  2. Update related pages with cross-references
  3. Update knowledge/index.md and knowledge/log.md
3. Query — User asks about accumulated knowledge
  1. Check knowledge/index.md (already in your context) for relevant pages
  2. Read specific pages with the read tool
  3. Supplement with memory_search if needed

Page Format

markdown
# Page Title

> Source: <URL or description of the original material>

Content here. Cross-reference related pages with markdown links:
[Related Page](../category/related-page.md)

## Key Points

- ...

## Related

- [Page A](../category/page-a.md) — how it relates
- [Page B](../category/page-b.md) — how it relates

The > Source: line records where the knowledge came from (URL, document name, conversation, etc.). Always include it when the material originates from a specific source.

Cross-references build a knowledge graph. When creating or updating a page, link to related pages and update those pages to link back. Only link to pages that already exist — if a concept deserves its own page, create it first, then add the link.

Show full SKILL.md (159 more words)Show less

Index Format (knowledge/index.md)

Flat list, one line per page: [Title](path) — one-line summary. Group by category (matching subdirectories). No tables, no emoji.

markdown
# Knowledge Index

## Category A
- [Page Title](category-a/page-slug.md) — one-line summary

## Category B
- [Page Title](category-b/page-slug.md) — one-line summary

Category names and structure are flexible — follow whatever organization already exists in the index, or create new categories based on the content.

Log Format (knowledge/log.md)

Append-only, newest at bottom:

markdown
## [YYYY-MM-DD] ingest | Page Title
## [YYYY-MM-DD] synthesize | Page Title

Guidelines

  • File naming: lowercase kebab-case (e.g. machine-learning.md)
  • One topic per page: link between pages rather than duplicating
  • Update, don't duplicate: if a page exists, update it
  • Cross-reference: every page should link to related pages; keep the knowledge graph connected
  • Index is mandatory: always update knowledge/index.md after any change
  • Be concise: capture essence, not copy entire sources
  • Full paths in replies: when referencing knowledge files in conversation replies, use the full path from workspace root (e.g. [Title](knowledge/<category>/<slug>.md)), not relative paths. Relative paths are only for cross-references inside knowledge pages themselves.
  • Cite sources: when answering based on knowledge pages, include links to the relevant pages so the user can explore further.

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

Files

Just SKILL.md in skills/knowledge-wiki of zhayujie/CowAgent.

Open the folder on GitHubat commit 7142631

Compare with similar skills

Personal Knowledge 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.

Personal Knowledge Wiki compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Personal Knowledge Wiki this skillzhayujie/CowAgent47k—~924Automated safety check: PassMIT
LLM Wikilewislulu/llm-wiki-skill655—~3.7kAutomated safety check: PassNone
LLM WikiCharlesHoskinson/sevenlayer116—~1.5kAutomated safety check: PassCustom licence
Wiki Vault Queryjason-effi-lab/karpathy-llm-wiki-vault716—~383Automated safety check: PassNone
Obsidian Wiki Log FoldAgriciDaniel/claude-obsidian15k1 repos~1.2kAutomated safety check: PassMIT
LLM Wiki Knowledge GraphEgonex-AI/Understand-Anything86k1 repos~1.5kAutomated safety check: PassMIT

Similar skills

  • 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

    CharlesHoskinson/sevenlayer

    Builds and maintains a persistent, interlinked Obsidian-compatible markdown knowledge wiki in a git repo via three operations — ingest a source into linked pages, answer a question from the…

    116 GitHub stars~1.5k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed
  • Wiki Vault Query

    jason-effi-lab/karpathy-llm-wiki-vault

    Answers questions from a local Obsidian-style wiki by reading its index first, then the relevant pages, and replying with wiki-link citations instead of model memory.

    716 GitHub stars~383 tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed
  • Obsidian Wiki Log Fold

    AgriciDaniel/claude-obsidian

    Creates a bounded, extractive rollup of recent Obsidian wiki log entries, previewed by default, with one optional apply step and no changes to child pages.

    15k GitHub starsUsed in 1 repo~1.2k tokens
    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 starsUsed in 1 repo~1.5k tokens
    Knowledge ManagementAuto-check passed
  • Wiki Builder

    rohitg00/pro-workflow

    Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base.

    2.9k GitHub stars~1k tokensUpdated 9 days ago
    Knowledge ManagementAuto-check passed

More from zhayujie/CowAgent

  • Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.

    47k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Skill Creator

    zhayujie/CowAgent

    Guides creating, installing and updating agent skills in a workspace: SKILL.md frontmatter, bundled scripts and references, with scripts to scaffold, validate and package.

    47k GitHub stars~4.7k tokensUpdated today
    Auto-check: notes

Questions about Personal Knowledge Wiki

What does Personal Knowledge Wiki do?

Maintains a structured Markdown knowledge base in a knowledge/ folder by ingesting shared articles, synthesizing conversations and answering questions from it. The skill keeps a persistent wiki in the knowledge/ directory and has three operations. Ingest reads an article or document you share, extracts key facts, picks or creates a category subfolder, writes a page and updates the index and log.

When should I use Personal Knowledge Wiki?

Personal Knowledge Wiki fits situations like: saving an article or document you share as structured notes; preserving insights from a conversation as a wiki page; answering a question from the knowledge already collected.

How do I install Personal Knowledge Wiki in Claude Code?

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

How do I install Personal Knowledge Wiki in Codex?

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

Can I use Personal Knowledge 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 zhayujie/CowAgent --skill knowledge-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/knowledge-wiki, .gemini/skills/knowledge-wiki, .github/skills/knowledge-wiki and .opencode/skills/knowledge-wiki in your project.

What does Personal Knowledge Wiki need to run?

SKILL.md names no scripts, command-line tools or credentials: Personal Knowledge Wiki is instructions for the agent only.

Does Personal Knowledge 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 Personal Knowledge 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. Review the folder before installing.

What licence does Personal Knowledge Wiki use?

Personal Knowledge 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 Personal Knowledge Wiki use?

About 924 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Personal Knowledge Wiki?

Skills that share tags, products or a category with Personal Knowledge Wiki: LLM Wiki (lewislulu/llm-wiki-skill, 655 stars), LLM Wiki (CharlesHoskinson/sevenlayer, 116 stars), Wiki Vault Query (jason-effi-lab/karpathy-llm-wiki-vault, 716 stars) and Obsidian Wiki Log Fold (AgriciDaniel/claude-obsidian, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Personal Knowledge Wiki?

zhayujie (a GitHub user) maintains it in zhayujie/CowAgent, which has 47,273 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 8, 2026.

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