Skip to content
alyn
tudoumashu

LLM Wiki skill

Query and maintain the user's local LLM Wiki from any Codex or Claude Code conversation or project. Use when the user asks to search personal knowledge, recall prior research or decisions, answer from the wiki, create durable notes, ingest a source into the wiki, update topic/concept/entity/question pages, write back useful answers, or run wiki lint/reindex workflows.

$npx skills add tudoumashu/ai-memory-skillpack --skill llm-wiki
View this skill on GitHubtudoumashu/ai-memory-skillpack/skills/llm-wiki/SKILL.md
Pack stars
492
Pack installs
3
Alyn Score
38/99
Updated
2 months ago
License
MIT
– views – installs via Alyn

Install LLM Wiki

Pick your agent. Every command is ready to paste.

$npx skills add tudoumashu/ai-memory-skillpack --skill llm-wiki

The open skills CLI detects your agents (Claude Code, Cursor, Codex and 70+ more) and installs to the right folder. Add -g to install globally.

01

Install it

Run the command above, or upload the folder in Claude.

02

Ask naturally

Describe the task. Your agent loads llm-wiki when the request matches its description.

03

Name it if needed

If it does not trigger, say “use the llm-wiki skill”. In Codex, type $llm-wiki.

The skill itself

SKILL.md

FolderGitHub

LLM Wiki

Core Rule

Use the local LLM Wiki as the durable knowledge source. Do not copy the wiki into this skill.

Paths on this machine:

VAULT_ROOT=/home/shiyi/Apps/Obsidian/vault
WIKI_ROOT=/home/shiyi/Apps/Obsidian/vault/60-Wiki
INDEX=/home/shiyi/Apps/Obsidian/vault/60-Wiki/index.md
LOG=/home/shiyi/Apps/Obsidian/vault/60-Wiki/log.md
QUERY=/home/shiyi/Apps/Obsidian/vault/70-System/scripts/query_wiki.sh
LINT=/home/shiyi/Apps/Obsidian/vault/70-System/scripts/lint_wiki.sh
REINDEX=/home/shiyi/Apps/Obsidian/vault/70-System/scripts/reindex_qmd.sh
EMBED_SAFE=/home/shiyi/Apps/Obsidian/vault/70-System/scripts/embed_qmd_safe.sh

Default wiki prose to Chinese. Keep commands, paths, filenames, config keys, API fields, code, package names, versions, URLs, and fixed English terms unchanged.

Obsidian Markdown Rules

Apply when creating or editing Markdown inside VAULT_ROOT, especially WIKI_ROOT.

  • Preserve existing YAML frontmatter. New wiki pages use the local schema keys: title, created, updated, kind, status, source_paths, tags, summary.
  • Every agent edit sets frontmatter updated_by: to the fixed actor string claude-code/fable-5 or codex/gpt-5.6-sol-pro, and refreshes updated.
  • Do not translate or rewrite frontmatter keys, wikilink targets, block IDs, embed targets, file paths, URLs, code blocks, JSON, or shell commands.
  • Use [[wikilinks]] for internal vault notes ([[path|display]] for Chinese labels); normal Markdown links for external URLs.
  • Prefer linking related source / topic / concept / entity / question pages over leaving isolated notes.
  • Embeds ![[...]], callouts, %% comments %%, Mermaid, math, footnotes: only when they add durable structure or evidence. Tags live in frontmatter tags, not inline.
  • After editing wiki Markdown, run lint_wiki.sh.

Query Workflow

  1. Start from 60-Wiki/index.md.
  2. If the query mentions a local project name or repo path, read the central project entity in 60-Wiki/entities/ first. Do not assume the entity file name matches the project name — locate it first with rg -ilF "<project-name-or-repo-path>" /home/shiyi/Apps/Obsidian/vault/60-Wiki/entities/; on multiple hits pick the page whose frontmatter source_paths contains the repo root (a body mention does not count, same criterion as $ai-project-memory), then read that page.
  3. If the entity points to a repo docs/ai/, follow project read discipline — full read only project-card.md and handoff.md; targeted rg for architecture.md, runbook.md, gotchas.md, diagrams/README.md, current ADRs in decisions/; do not read history/, reports/, screenshots/, learning/, superseded ADRs (Status: superseded/deprecated), or deprecated ledger files by default(change-log 已停用 2026-07-28,git 提交即账本); on explicit user recall, targeted reads are allowed with cross-checking against current code.
  4. Query the compiled wiki:
/home/shiyi/Apps/Obsidian/vault/70-System/scripts/query_wiki.sh "<query>" --scope wiki
  1. If insufficient, widen scope:
/home/shiyi/Apps/Obsidian/vault/70-System/scripts/query_wiki.sh "<query>"
/home/shiyi/Apps/Obsidian/vault/70-System/scripts/query_wiki.sh "<query>" --scope raw
  1. Read cited wiki pages directly before making important claims.
  2. If wiki evidence is stale or insufficient, say so and use source pages, raw sources, project-local docs/ai/, or current web search when required.

Writeback Workflow

Write back only when the answer or change has durable value. Choose the smallest correct destination:

  • 60-Wiki/questions/: reusable answer. 60-Wiki/topics/: cross-source synthesis. 60-Wiki/concepts/: reusable method, pattern, term. 60-Wiki/entities/: person, company, tool, project, system. 60-Wiki/sources/: single-source summary.

When writing back:

  1. Prefer updating an existing page over creating a duplicate.
  2. Preserve frontmatter and wikilinks; set updated_by per the rule above.
  3. Add or update source_paths; link related pages.
  4. Update 60-Wiki/index.md when navigation changes.
  5. log.md is newest-first: agents log content changes only(ingest、writeback、页面重构)by inserting a ## [YYYY-MM-DD] <kind> | <slug> entry above the first existing ## heading. Never hand-write query or lint entries; lint_wiki.sh itself inserts a daily lint | wiki-health entry and writes a report under 70-System/reports/ — tool behavior, not a violation; do not remove those entries.
  6. Keep uncertainty explicit with inferred, unknown, or open questions.
  7. Never write secret values into any wiki page.
  8. The vault is a git repository — after content writebacks, commit with an explicit file list including lint by-products(the updated log.md and the new 70-System/reports/wiki-lint-<date>.md)(git 即账本,不积压未提交改动).

For a user-owned project with repo-local docs/ai/, the central project entity stays lightweight and points to the repo pack: repo path, docs/ai/ path, key file links, short summary, important gaps. Never copy full docs/ai/ content into the wiki; sync only on entity-level changes.

Ingest Workflow

  1. Read the source.
  2. Create or update a source page in 60-Wiki/sources/.
  3. Extract durable points; update relevant topic / concept / entity / question pages — do not stop after only a source page when clear updates exist.
  4. Update 60-Wiki/index.md; add a content entry to 60-Wiki/log.md per Writeback rule 5(newest-first, same header format).
  5. Run lint and reindex.

Validation

/home/shiyi/Apps/Obsidian/vault/70-System/scripts/lint_wiki.sh
/home/shiyi/Apps/Obsidian/vault/70-System/scripts/reindex_qmd.sh llm-wiki

Lint is required after any wiki edit. Reindex only when future search should find new or changed Markdown. Do not run qmd embed by default; run embedding only for immediate vector-search freshness or batch maintenance:

/home/shiyi/Apps/Obsidian/vault/70-System/scripts/embed_qmd_safe.sh llm-wiki

Avoid npx --yes @tobilu/qmd ... embed(version drift, startup cost). Large high-churn files(central log.md, project handoff.md, generated reports)cause repeated expensive embedding — keep entities lightweight and avoid embedding large dumps when a link is enough. Status check: QMD_LLAMA_GPU=false qmd --index llm-wiki status.

Final Response

Mention: wiki pages read; wiki pages changed; validation commands run; any source gaps, uncertainty, or stale information.

Tips for LLM Wiki

  • • Start a fresh session after installing so your agent picks up the new skill.
  • • It is part of a pack with 3 skills. Install only the ones you need with --skill to keep triggers precise.
  • • If two skills overlap, mention the one you want by name.

Questions about LLM Wiki

What does the LLM Wiki skill do?

Query and maintain the user's local LLM Wiki from any Codex or Claude Code conversation or project. Use when the user asks to search personal knowledge, recall prior research or decisions, answer from the wiki, create durable notes, ingest a source into the wiki, update topic/concept/entity/question pages, write back useful answers, or run wiki lint/reindex workflows.

How do I install LLM Wiki?

Run "npx skills add tudoumashu/ai-memory-skillpack --skill llm-wiki" in your project. The skills CLI installs it for Claude Code, Cursor, Codex and 70+ other agents. In Claude on the web, upload the skill folder as a ZIP under Customize > Skills.

Does LLM Wiki work in Cursor and Codex?

Yes. LLM Wiki uses the open SKILL.md format, so it works in Claude Code, Claude, Cursor, OpenAI Codex, Gemini CLI, GitHub Copilot and other agents that support agent skills.

Is LLM Wiki free?

LLM Wiki is open source on GitHub under the MIT license. It is free to install; check the license before commercial use.

Who made LLM Wiki?

LLM Wiki is published by tudoumashu in the tudoumashu/ai-memory-skillpack repository, together with 2 other skills.

Similar skills. From other creators.