SkillPedia Skills Encyclopedia
中文 EN

llm-wiki-skillsdyckjq-lab/llm-wiki-skill

[Core Features]: A Chinese-friendly monorepo skill based on Karpathy llm-wiki methodology that compiles fragmented infor…

No ratings yet Rate this skill
Stars2.6k
Forks302
Watchers2.5k
Open Issues29

InstallOne-line install

Installable · 88 skills

This repository follows the Agent Skills spec, so one command installs it into your AI client — works across Claude Code, Codex, Cursor, Copilot, Windsurf, and 18+ other clients.

npx skills@latest add sdyckjq-lab/llm-wiki-skill

This repository bundles 88 skills, and you can install just one:

84 more are not listed — run npx skills@latest add sdyckjq-lab/llm-wiki-skill --list to see them all.

Add -g install globally (available in every project) · add --agent claude-code to target a client · add --yes to skip the prompts. Restart your AI client afterward and it will pick it up.

OverviewOverview

[Core Features]: A Chinese-friendly monorepo skill based on Karpathy llm-wiki methodology that compiles fragmented information once and maintains it as an interlinked knowledge base instead of re-deriving from raw docs at query time, with two entries sharing one offline digital-landscape graph engine: a mature Skill form installable in one command into Claude Code, Codex, OpenClaw and Hermes and an in-development local workbench; features include zero-config init, structured wiki pages with backlinks, confidence labels, SHA256 smart caching and community legends with search filters, keeping files local while replies may send excerpts to the configured model provider. [Applicable Scenarios]: Personal knowledge-base building, structured wiki and backlinks, offline graph exploration. [Target Roles]: Knowledge Manager, Researcher, AI Engineer.

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID381
Data sourceGitHub
Repositorysdyckjq-lab/llm-wiki-skill
CategoryKnowledge & Research Skills / Local Knowledge Base and Digital Landscape Graph
Primary languageTypeScript
LicenseNot specified
Default branchmain
GitHub repository ID1201752720
Node IDR_kgDOR6FKkA
Rank#440 (position within the source ranking)
Site-wide popularity rank#507 (computed live from Stars, across all 5875 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

01k2k3k2026-09-292026-11-192026-09-29 · 2,5072026-10-11 · 2,5342026-11-19 · 2,592
  • Now2,592
  • Previous point · 10-11 2,534
  • vs previous point +58
  • 3 data points 51 days
01002003004002026-09-292026-11-192026-09-29 · 2942026-10-11 · 2982026-11-19 · 302
  • Now302
  • Previous point · 10-11 298
  • vs previous point +4
  • 3 data points 51 days

TimelineTimeline

Repository created2026-04-05 05:27:077 months ago
Data last updated2026-11-19 21:17:372 hours ago
Last commit2026-07-27 03:30:443 months ago

CommitLatest commit

Committed by sdyckjq-lab. Update Category: Testing & Quality Assurance. Commit details: test(workbench): stop racing the transient warning banner (#312) (#313). This update adds test cases for better regression coverage.

efa2294 sdyckjq-lab 2026-07-27