📄 skillStalePromisingmedium

llm-wiki

Name: llm-wiki
Author: mduongvandinh

by mduongvandinh

Hệ thống knowledge base cá nhân hoàn toàn tự động, vận hành bởi LLM. Dựa trên pattern LLM Wiki của Andrej Karpathy.

Supported Platforms

🤖 Claude Code🧠 Codex

Stars

212

Skill Type

🏗️ Code Scaffolding & Templates

Quality Score

87/200

License

MIT

Forks

Last Updated

Jul 27, 2026

Discovered

Apr 21, 2026

Validation

Passed

github.com/mduongvandinh/llm-wiki

Quality Breakdown

87/ 200

Content Signals

○Gotchas/Edge Cases+40

✓Progressive Disclosure+30

○Trigger Description+20

○Verification/Safety+20

✓Code Examples+15

○Composability+15

Repo Health

○Recent Activity+15

✓Scripts/Automation+10

○Real Usage (Issues)+10

✓Single Responsibility+10

✓Config/Persistence+10

✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Stale

No commits in 90-365 days and no tagged releases.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

Contains CLAUDE.md files in multiple locations (root and variants/) which are Claude-specific configuration files that could modify AI behavior
Includes shell scripts (scripts/run-wiki.sh, scripts/setup-scheduler.ps1) that execute automation without apparent human approval gates
AGENTS.md file suggests multi-agent or autonomous agent orchestration capabilities
Setup instructions reference installing skills to ~/.claude/ directory, indicating persistent configuration modification of AI tool settings
Copilot instructions file (.github/copilot-instructions.md) suggests attempt to inject instructions into AI behavior
Multiple variant directories with CLAUDE.md files suggest templated AI instruction injection for different use cases

llm-wiki

Quality Breakdown

Trust & Verification

Risk Assessment

Related guides