Wiki Self Heal

Autonomously audit an LLM wiki (Karpathy pattern) for gaps, contradictions, orphans, and stale data, then research and fill high-priority gaps using quality-gated web research. Supports audit-only dry-run mode. Operates on a dedicated branch and commits changes for human review — never auto-merges. Use when the user asks to "lint my wiki", "self-heal my knowledge base", "find gaps in my wiki", "update my second brain", "auto-research my wiki", "run a health check on my LLM wiki", "audit my wiki without making changes", "dry run the lint", or wants to schedule periodic wiki maintenance.

103 stars 17 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add NulightJens/ai-second-brain-skills --skill wiki-self-heal
Manual install
git clone --depth 1 https://github.com/NulightJens/ai-second-brain-skills.git /tmp/ai-second-brain-skills
mkdir -p ~/.claude/skills
cp -r /tmp/ai-second-brain-skills/wiki-self-heal ~/.claude/skills/wiki-self-heal

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# wiki-self-heal

Audit → research → fill → commit. An autonomous pass over a Karpathy-style LLM wiki that finds what's weak or missing, researches high-quality answers, writes them into the wiki, and commits to a dedicated branch for human review.

Inspired by Karpathy's `autoresearch` loop: isolated branch per run, explicit CAN/CANNOT rules, numbered steps, structured logging, simplicity criterion, and a NEVER STOP autonomy directive once the loop begins.

## When to use

User says: "lint my wiki", "self-heal", "find gaps", "auto-research my wiki", "update my second brain", "health check my wiki", "audit my wiki" or "dry run" (audit-only mode), or has scheduled this skill via cron / GitHub Actions / Claude Code triggers.

## Two modes

- **Full mode** (default) — audit → research → apply → commit. Changes the wiki on a heal branch.
- **Audit-only mode** — audit → report. No research, no changes to wiki pages. The audit report itself is still committed to the branch.

Infer the mode from phrasing. If the user says "dry run", "just audit", "audit only", "don't make changes", or "show me the gaps first" → audit-only. If the user just says "lint" or "self-heal" → full mode. If unsure, ask once.

## Preconditions

Before doing anything:

1. The vault has Karpathy wiki structure: `raw/`, `wiki/`, `CLAUDE.md`, `wiki/index.md`, `wiki/log.md`. If any are missing → stop and suggest running the `llm-wiki-setup` skill first.
Read the full skill on GitHub

Details

Skill name
wiki-self-heal
Path
wiki-self-heal/SKILL.md
License
MIT
Repo updated
12 April 2026

FAQ

What does the Wiki Self Heal skill do?

Autonomously audit an LLM wiki (Karpathy pattern) for gaps, contradictions, orphans, and stale data, then research and fill high-priority gaps using quality-gated web research. Supports audit-only dry-run mode. Operates on a dedicated branch and commits changes for human review — never auto-merges. Use when the user asks to "lint my wiki", "self-heal my knowledge base", "find gaps in my wiki", "update my second brain", "auto-research my wiki", "run a health check on my LLM wiki", "audit my wiki without making changes", "dry run the lint", or wants to schedule periodic wiki maintenance.

How do I install the Wiki Self Heal skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add NulightJens/ai-second-brain-skills --skill wiki-self-heal. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Wiki Self Heal popular?

It lives in NulightJens/ai-second-brain-skills, which has 103 GitHub stars and 17 forks.

Related skills

LLM Wiki Setup

103

NulightJens/ai-second-brain-skills

Initialize a Karpathy-style LLM wiki (personal knowledge base / AI second brain) in a folder. Creates a CLAUDE.md schema with routing table and naming conventions, AGENTS.md mirror, raw/wiki directory structure, and index.md/log.md scaffolding — a complete working vault in one pass. Use when the user asks to "set up an LLM wiki", "create a second brain", "build a personal knowledge base", "install the Karpathy wiki pattern", "initialize a knowledge vault", or points at an empty folder and wants to turn it into an AI-maintained wiki.

AI, LLMs & Agents17

2026 Legal Research Agent

272

curiositech/some_claude_skills

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape. Activate on "find expungement data", "scrape state laws", "legal research", "court URLs", "statute sources", "Clean Slate laws", "automatic expungement research". NOT for interpreting laws (use national-expungement-expert), building UI, or legal advice.

Research & Science46

Research Expert Team

188

jaccen/Awesome-Gaussian-Skills

Evidence-led research assistance for 3DGS, spatial intelligence and agent papers: evaluate an idea, locate related work, plan experiments, interpret results, review a draft, improve prose and check venue requirements. Use for 科研专家团、选题评估、创新点分析、实验设计、结果分析、模拟审稿、论文润色和投稿检查。

Research & Science13

Clinical Diagnostic Reasoning

272

curiositech/some_claude_skills

Identify and counteract cognitive biases in medical decision-making through systematic error analysis and contextual algorithm application. For diagnostic reasoning, treatment decisions, and clinical judgment improvement. NOT for basic medical knowledge, technical procedures, or non-clinical healthcare domains.

Research & Science46

Cg Paper Writing

188

jaccen/Awesome-Gaussian-Skills

Academic paper writing for 3D vision, computer graphics, CAD, and 3D understanding. Covers NeRF, 3DGS, SLAM, point cloud, 3D shape, CAD modeling. Supports CVPR/ICCV/ECCV/SIGGRAPH venues and Chinese core journals (17 journal-specific format specs). Multi-agent adversarial review, citation integrity gates, style calibration, paper novelty/industry-value evaluation, pre-submission format audit, experiment claim verification. Use when: writing or revising a CG/3D vision paper, drafting abstract/intro/method/experiments, running adversarial review or citation integrity check, calibrating writing st

Research & Science13

Jungian Psychologist

272

curiositech/some_claude_skills

Expert in Jungian analytical psychology, depth psychology, shadow work, archetypal analysis, dream interpretation, active imagination, addiction/recovery through Jungian lens, and the individuation process - grounded in primary sources and clinical frameworks. Activate on 'Jung', 'Jungian', 'shadow work', 'archetypes', 'dream interpretation', 'active imagination', 'individuation', 'anima', 'animus', 'collective unconscious', 'addiction', 'recovery', 'spiritus contra spiritum'. NOT for therapy or diagnosis (only licensed analysts diagnose), active psychosis, severe dissociation, or replacing th

Research & Science46

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.