What makes Karpathy Wiki Improve notable?

1K downloads. Trust evidence available

How should Karpathy Wiki Improve be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Karpathy Wiki Improve

Karpathy LLM Wiki pattern implementation — full ingest/query/relink/lint/DeepResearch pipeline, automatic knowledge graph maintenance, URL-level source trace... Skill: Karpathy Wiki Improve Owner: zhangmengyang Summary: Karpathy LLM Wiki pattern implementation — full ingest/query/relink/lint/DeepResearch pipeline, automatic knowledge graph maintenance, URL-level source trace... Tags: latest:1.1.2 Version history: v1.1.2 | 2026-06-17T07:52:23.902Z | user Maintenance update: bump version to refresh on Recently Updated v1.1.1 | 2026-05-13T05:45:36.105Z | user - Removed Chinese-

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

1.1.2

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.1.2release · observed Jun 17, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17cw6qwsv2vw3c2g4m57wd06d83m90p:karpathy-wiki-improve

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-zhangmengyang-karpathy-wiki-improve/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

78,375 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: karpathy-wiki-improve
description: "Karpathy LLM Wiki pattern implementation — full ingest/query/relink/lint/DeepResearch pipeline, automatic knowledge graph maintenance, URL-level source traceability. Use when: user says 'organize bookmarks', 'research X', 'run lint', 'relink', or needs a personal knowledge graph."
---

# karpathy-wiki — OpenClaw Implementation

Based on Andrej Karpathy's [LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f).

---

## Trigger Keywords (Activation)

Activate this skill when the user says anything like:
- "organize bookmarks" / "digest this link"
- "research X" / "help me research"
- "run lint" / "lint check"
- "relink" / "build connections"
- "wiki" / "knowledge graph"
- "Deep Research"

---

## wiki Root

```
wiki_root: /path/to/your/wiki  # configure to your local path
```

```
<wiki_root>/
├── raw/
│   ├── sources/          # raw bookmarks/docs (immutable)
│   └── assets/           # images and resources
├── wiki/
│   ├── entities/        # entity pages (people, products, companies, sites, books)
│   ├── concepts/        # concept pages (tech, theory, methodology)
│   ├── comparisons/     # comparison pages
│   ├── synthesis/       # synthesis/overview pages
│   ├── index.md         # wiki index (entry point)
│   ├── log.md           # operation log (append-only)
│   └── overview.md      # global overview
├── purpose.md           # wiki goal definition (wiki constitution)
└── schema.md            # structure conventions
```

---

## Core Principles

1. **sources/ is read-only** — LLM only writes wiki/, never modifies raw sources
2. **wikilink cross-references** — `[[page-slug]]` syntax for page connections
3. **YAML frontmatter** — every page has type/tags/related/sources
4. **Bidirectional links enforced** — every write to related must sync back-link
5. **Two-phase Ingest** — Analysis → Generation
6. **URL-level traceability** — sources contain specific URLs, not just filenames
7. **Lint-driven** — periodic health checks, graph stays clean
8. **Deep Research** — knowledge gaps auto-discovered and filled

---

## Page Type Taxonomy (entity vs concept boundary)

| Type | Definition | Examples |
|------|------------|----------|
| **entity** | Named, discrete things | people/products/companies/sites/books/tools |
| **concept** | Abstract ideas/theories/methodologies | indexing principles, microservices, DI |
| **comparison** | Multi-option comparisons | Vue vs React, MySQL vs PostgreSQL |
| **synthesis** | Comprehensive overview | tech stack panorama, annual summary |

**Boundary Rules**:
- If it has a specific name → entity ("pdai.tech", "Effective Java")
- If it's abstract/generic → concept ("MySQL indexing", "dependency injection")
- Avoid having both entity and concept for the same topic

---

## Naming Convention

```
entity:
  blogs/sites: use domain or person name
    → mysql-zhu-shuangyin
    → pdai-tech
    → jon-index-blog
  books: use simplified book title

README.md

# karpathy-wiki-improve

OpenClaw skill implementing Andrej Karpathy's LLM Wiki pattern — a persistent markdown knowledge wiki with full ingest/query/relink/lint/DeepResearch pipeline.

## What It Does

- **Ingest**: Turn raw bookmarks/links into structured wiki pages with bidirectional links
- **Query**: Answer questions by reading wiki first, then web search to supplement
- **Relink**: Auto-discover and establish page relationships
- **Lint**: Health-check the knowledge graph (orphans, dangling refs, one-way links)
- **Deep Research**: Fill knowledge gaps with targeted search + ingest

## Quick Start

```bash
npx clawhub install zhangmengyang/karpathy-wiki-improve
```

Then in OpenClaw:

```
organize my bookmarks on Go
research MySQL indexing
run lint on my wiki
relink
```

## Wiki Structure

```
wiki/
├── raw/sources/      # immutable original sources
├── wiki/
│   ├── entities/     # people, products, companies, sites
│   ├── concepts/     # tech, theory, methodology
│   ├── comparisons/   # A vs B analysis
│   └── synthesis/    # topic overviews
├── purpose.md        # wiki constitution
├── schema.md         # structure conventions
└── wiki/index.md     # entry point
```

## Source

Based on [Andrej Karpathy's LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f).

_meta.json

{
  "ownerId": "kn7cb0ef0ty28xjmdaq879gb5n83ncwj",
  "slug": "karpathy-wiki-improve",
  "version": "1.1.2",
  "publishedAt": 1781682743902
}

skill-card.md

## Description:

Helps agents organize bookmarks and research into a persistent Markdown knowledge wiki with ingest, query, relink, lint, Deep Research, and URL-level source traceability.

This skill is ready for commercial/non-commercial use.

## Publisher:

[zhangmengyang](https://clawhub.ai/user/zhangmengyang)

### License/Terms of Use:

MIT-0

## Use Case:

Developers, researchers, and knowledge workers use this skill to turn collected links and research topics into a structured personal wiki, then query and maintain it with linting and relinking workflows.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Broad triggers can lead the agent to make persistent local wiki edits beyond the user's intended scope.

Mitigation: Use a dedicated, backed-up wiki folder and review proposed file changes before execution.

Risk: Deep Research and query workflows can introduce unverified or misleading source material into the wiki.

Mitigation: Approve search queries before execution and require URL-level source traceability with confidence annotations.

Risk: Periodic linting or relinking can change wiki relationships without enough explicit consent.

Mitigation: Run maintenance only when explicitly requested or clearly enabled for the configured wiki.

## Reference(s):

- [Andrej Karpathy LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f)
- [Karpathy Wiki Improve ClawHub listing](https://clawhub.ai/zhangmengyang/skills/karpathy-wiki-improve)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Markdown with wiki plans, source links, and inline shell commands]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May propose or create persistent local wiki files within the configured wiki folder.]

## Skill Version(s):

1.1.2 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.