Karpathy LLM Wiki
Astro-Han/karpathy-llm-wiki
A skill your agent uses when building or maintaining a personal LLM-powered knowledge base.
Create the project wiki skeleton (schema, index, source registry) — the three-layer LLM Wiki structure
$ npx skills add haru/redmine_ai_helper --skill speckit-wiki-init -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install haru/redmine_ai_helper speckit-wiki-init --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/haru/redmine_ai_helper.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/speckit-wiki-init .claude/skills/speckit-wiki-init && rm -rf skills-srcUse ~/.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/
Install the "speckit-wiki-init" agent skill from https://github.com/haru/redmine_ai_helper/tree/main/.claude/skills/speckit-wiki-init into .claude/skills/speckit-wiki-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speckit-wiki-init", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/haru/redmine_ai_helper/tree/main/.claude/skills/speckit-wiki-initType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add haru/redmine_ai_helper --skill speckit-wiki-init -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install haru/redmine_ai_helper speckit-wiki-init --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/haru/redmine_ai_helper.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/speckit-wiki-init .agents/skills/speckit-wiki-init && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "speckit-wiki-init" agent skill from https://github.com/haru/redmine_ai_helper/tree/main/.claude/skills/speckit-wiki-init into .agents/skills/speckit-wiki-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speckit-wiki-init", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add haru/redmine_ai_helper --skill speckit-wiki-init -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install haru/redmine_ai_helper speckit-wiki-init --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/haru/redmine_ai_helper.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/speckit-wiki-init .cursor/skills/speckit-wiki-init && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "speckit-wiki-init" agent skill from https://github.com/haru/redmine_ai_helper/tree/main/.claude/skills/speckit-wiki-init into .cursor/skills/speckit-wiki-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speckit-wiki-init", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/haru/redmine_ai_helper.git --path .claude/skills/speckit-wiki-init--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add haru/redmine_ai_helper --skill speckit-wiki-init -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install haru/redmine_ai_helper speckit-wiki-init --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/haru/redmine_ai_helper.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/speckit-wiki-init .gemini/skills/speckit-wiki-init && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "speckit-wiki-init" agent skill from https://github.com/haru/redmine_ai_helper/tree/main/.claude/skills/speckit-wiki-init into .gemini/skills/speckit-wiki-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speckit-wiki-init", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install haru/redmine_ai_helper speckit-wiki-initInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add haru/redmine_ai_helper --skill speckit-wiki-init -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/haru/redmine_ai_helper.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/speckit-wiki-init .github/skills/speckit-wiki-init && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "speckit-wiki-init" agent skill from https://github.com/haru/redmine_ai_helper/tree/main/.claude/skills/speckit-wiki-init into .github/skills/speckit-wiki-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speckit-wiki-init", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add haru/redmine_ai_helper --skill speckit-wiki-init -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install haru/redmine_ai_helper speckit-wiki-init --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/haru/redmine_ai_helper.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/speckit-wiki-init .opencode/skills/speckit-wiki-init && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "speckit-wiki-init" agent skill from https://github.com/haru/redmine_ai_helper/tree/main/.claude/skills/speckit-wiki-init into .opencode/skills/speckit-wiki-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speckit-wiki-init", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
speckit-wiki-initCreate the project wiki skeleton (schema, index, source registry) — the three-layer LLM Wiki structure
Speckit Wiki Init is an agent skill from haru/redmine_ai_helper. Create the project wiki skeleton (schema, index, source registry) — the three-layer LLM Wiki structure
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires spec-kit project structure with .specify/ directory
It sits in Knowledge Management, covering LLM wikis and Spec-driven development. The repository describes itself as: A Redmine plugin that adds AI agents, MCP Server, smart completion, and vector search. The licence is MIT.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 3cd87d6. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Requires spec-kit project structure with .specify/ directory
From compatibility in the SKILL.md frontmatter.
Speckit Wiki Init loads about 1.4k tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 400 words of instructions outside code blocks.
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.
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.
The full file from haru/redmine_ai_helper at commit 3cd87d6, republished under its MIT licence (© haru). 400 words, ~1,378 tokens.
.claude/skills/speckit-wiki-init/SKILL.md (or your agent's skills folder).Set up the persistent, LLM-maintained project wiki. After this command, the
project has a compounding knowledge layer — ordinary markdown, committed with
the repo — that ingest grows, query answers from, and lint keeps honest.
This implements the three-layer structure of Karpathy's LLM Wiki pattern: raw sources (immutable — your repo, spec artifacts, external documents) → the wiki (LLM-written, cross-referenced pages) → the schema (a configuration document defining the wiki's structure and maintenance rules).
$ARGUMENTSIf provided, treat $ARGUMENTS as the wiki scope — one or two sentences
describing what this wiki exists to accumulate (e.g. "Everything we learn
about the payments domain and our integration constraints"). key=value
tokens (e.g. directory=docs/wiki) are configuration overrides.
.specify/extensions/wiki/wiki-config.yml if it exists; otherwise use
the extension defaults (wiki/ directory, 12 pages max per ingest, 600
words per page, citations required, 8-page query slice, 90-day staleness,
index-and-links auto-fix).SPECKIT_WIKI_* environment variable overrides, then any
key=value overrides from $ARGUMENTS (highest precedence).WIKI_DIR = the configured state.directory, relative to the repo root.If WIKI_DIR/SCHEMA.md already exists, do not overwrite anything. Report
that the wiki is already initialized, then behave exactly like
/speckit.wiki.status and stop. If the user supplied a new scope sentence in
$ARGUMENTS, append it to the ## Scope section of SCHEMA.md as an
additional numbered item instead.
Create WIKI_DIR/ and write each file below exactly once.
SCHEMA.md — the schema layer (user-editable; every command obeys it):
# Wiki Schema
This file defines how this wiki is structured and maintained. Edit it to
change the rules; `/speckit.wiki.*` commands read it before writing anything.
## Scope
1. <scope from $ARGUMENTS, or "(not set — pass a sentence to /speckit.wiki.init)">
## Page types
| Type | Holds | Example title |
|------|-------|---------------|
| concept | domain ideas and definitions that outlive any feature | "Idempotency keys" |
| decision | choices made, alternatives rejected, and why | "Why SQLite over Postgres" |
| component | how a part of the system actually works | "Auth middleware" |
| reference | distilled external facts (APIs, papers, vendor limits) | "Stripe rate limits" |
| howto | procedures that took effort to figure out | "Local TLS setup" |
## Rules
- Pages live in `pages/`, one topic per page, kebab-case filenames.
- Every synthesized claim cites a source ID from `sources.md` (e.g. `(S003)`).
- Pages cross-reference with relative links: `[title](./other-page.md)`.
- A page that outgrows <ingest.page_max_words> words is split, and both halves
link to each other.
- Conflicting claims are kept side by side under a `> ⚠ conflict:` marker
until resolved — never silently overwritten.
- Frontmatter per page: `title`, `type`, `sources`, `updated` (ISO date).
## Maintenance workflows
- Grow: `/speckit.wiki.ingest <source>` — the only way knowledge enters.
- Use: `/speckit.wiki.query <question>` — answers come from pages, cited.
- Check: `/speckit.wiki.lint` — drift, orphans, contradictions, staleness.
- Resume: `/speckit.wiki.status` — the session-resume entry point.INDEX.md — the page directory (maintained by ingest and lint):
# Wiki Index
One line per page, grouped by type. Maintained by `/speckit.wiki.ingest` and
regenerated by `/speckit.wiki.lint` — hand edits will be preserved only in
page files, not here.
_No pages yet. Run `/speckit.wiki.ingest` to add the first source._sources.md — the source registry (raw sources are never copied, only pointed to):
# Source Registry
Append-only IDs (S001, S002…). Dedup key: normalized path or URL.
Sources are immutable inputs — the wiki never edits them.
| ID | Source | Type | First ingested | Last ingested | Pages touched |
|----|--------|------|----------------|---------------|---------------|Replace every <...> placeholder with the resolved configuration value.
Do not create pages/ yet — the first ingest creates it.
Output a short confirmation:
WIKI_DIR and the three files created./speckit.wiki.ingest to compound the first source — a feature's
research.md, a file, or a URL; /speckit.wiki.status at any time —
including from a brand-new session — to resume from the files.ingest reads what it needs when it needs it.© haru, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .claude/skills/speckit-wiki-init of haru/redmine_ai_helper.
Open the folder on GitHubat commit 3cd87d6
Speckit Wiki Init 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Speckit Wiki Init this skillharu/redmine_ai_helper | 106 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Karpathy LLM WikiAstro-Han/karpathy-llm-wiki | 2.4k | — | ~3.6k | Automated safety check: Pass | MIT | |
| LLM Wikilewislulu/llm-wiki-skill | 655 | — | ~3.7k | Automated safety check: Pass | None | |
| Wiki Builderrohitg00/pro-workflow | 2.9k | — | ~1k | Automated safety check: Pass | None | |
| Codex History IngestAr9av/obsidian-wiki | 3.5k | — | ~2.2k | Automated safety check: Notes | MIT | |
| Arkon Editnduckmink/arkon | 1.5k | — | ~1.6k | Automated safety check: Pass | Custom licence |
Astro-Han/karpathy-llm-wiki
A skill your agent uses when building or maintaining a personal LLM-powered knowledge base.
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…
rohitg00/pro-workflow
Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base.
Ar9av/obsidian-wiki
Ingest Codex CLI conversation/session history into Obsidian as distilled knowledge.
nduckmink/arkon
Propose or directly apply edits to Arkon wiki pages, including proposing brand new pages.
dair-ai/dair-academy-plugins
Creates and maintains configurable research wikis: scaffold a folder, add sources, compile pages and indexes, and file query answers back.
haru/redmine_ai_helper
Stage the current changes and create a git commit with a properly formatted English message.
haru/redmine_ai_helper
Create a pull request from the current branch. An agent skill from haru/redmine_ai_helper.
haru/redmine_ai_helper
Create a release branch for a given version. An agent skill from haru/redmine_ai_helper.
haru/redmine_ai_helper
Code quality checks, formatting, and metrics via qlty CLI. An agent skill from haru/redmine_ai_helper.
haru/redmine_ai_helper
Connect to the running Redmine instance and log in via the Playwright MCP browser, using REDMINEPLAYRIGHTURL/REDMINEPLAYRIGHTUSER/REDMINEPLAYRIGHTPASSWORD environment variables.
haru/redmine_ai_helper
Recreate the Redmine test database from scratch (delete db/schema.rb and db/redmine.sqlite3test, then run core and plugin migrations with RAILSENV=test).
Categories
Create the project wiki skeleton (schema, index, source registry) — the three-layer LLM Wiki structure. Speckit Wiki Init is an agent skill from haru/redmine_ai_helper.
Speckit Wiki Init fits situations like: tasks that involve LLM wikis; tasks that involve Spec-driven development.
Run `npx skills add haru/redmine_ai_helper --skill speckit-wiki-init -a claude-code`. Or copy the skill folder (.claude/skills/speckit-wiki-init in haru/redmine_ai_helper) into .claude/skills/speckit-wiki-init in your project. Claude Code loads it when a task matches its description.
Run `npx skills add haru/redmine_ai_helper --skill speckit-wiki-init -a codex`. Or copy the skill folder (.claude/skills/speckit-wiki-init in haru/redmine_ai_helper) into .agents/skills/speckit-wiki-init in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add haru/redmine_ai_helper --skill speckit-wiki-init -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/speckit-wiki-init, .gemini/skills/speckit-wiki-init, .github/skills/speckit-wiki-init and .opencode/skills/speckit-wiki-init in your project.
SKILL.md names no scripts, command-line tools or credentials: Speckit Wiki Init is instructions for the agent only. Compatibility (from SKILL.md): Requires spec-kit project structure with .specify/ directory.
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.
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.
Speckit Wiki Init is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Speckit Wiki Init: Karpathy LLM Wiki (Astro-Han/karpathy-llm-wiki, 2.4k stars), LLM Wiki (lewislulu/llm-wiki-skill, 655 stars), Wiki Builder (rohitg00/pro-workflow, 2.9k stars) and Codex History Ingest (Ar9av/obsidian-wiki, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
haru (a GitHub user) maintains it in haru/redmine_ai_helper, which has 106 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 9, 2026.
Source: haru/redmine_ai_helper on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.