wiki
Skill0 starsChanged 7 months agoMITView on GitHub
Persistent wiki store for long-lived project knowledge, with query, graph, and CLI validation surfaces.
We split this skill into the rules it gives an agent
7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 34 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Use the MCP tools for writes and structured reads.
- Very specific: line 17
Use wiki_ingest when you want SHA-256 de-duplication by body.
- Very specific: line 23
Use wiki_write for direct upserts when de-duplication is not the point.
- Distinctive: line 32
Search across wiki pages by title, body, and tags.
- Very specific: line 55
Use the main CLI for read-only navigation with human-readable output by default and --json when you need machine-readable output.
- Very specific: line 69
Use [[slug]], [[Title|slug]], or local markdown links like docs to create wiki graph edges.
- Distinctive: line 79
NO vector embeddings — query is keyword/tag matching over stored rows
“Common” is measured: kept by at least 6 in 10 of the 34 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Wiki
Persistent project knowledge base stored in the Omni SQLite state store.
Use the MCP tools for writes and structured reads. Use the omni wiki ... CLI for human-readable inspection and validation.
Operations
Ingest / write
Use wiki_ingest when you want SHA-256 de-duplication by body. Re-ingesting the same body is a no-op (deduped: true).
wiki_ingest({ title: "Auth Architecture", body: "...", tags: ["auth", "architecture"] })Use wiki_write for direct upserts when de-duplication is not the point.
wiki_write({ slug: "auth-architecture", title: "Auth Architecture", body: "...", tags: ["auth"] })The canonical content field is body.
Query
Search across wiki pages by title, body, and tags.
wiki_query({ query: "authentication" })List / read
wiki_list()
wiki_read({ slug: "auth-architecture" })Graph
The MCP server exposes wiki_graph, which returns {nodes, edges, dangling} derived from wiki-link and local markdown-link references.
wiki_graph({})CLI inspection
Use the main CLI for read-only navigation with human-readable output by default and --json when you need machine-readable output.
omni wiki list
omni wiki show auth-architecture
omni wiki search authentication
omni wiki graph
omni wiki validateomni wiki validate exits non-zero when dangling links are present, so it can be used as a lightweight integrity check.
Cross-references
Use [[slug]], [[Title|slug]], or local markdown links like [docs](./other-page.md) to create wiki graph edges.
For repository-level file/import/refactor analysis, use codebase_graph / codebase_impact or the CLI surface omni codebase graph|impact instead of wiki_graph.
Storage
- Backing store:
$OMNI_HOME/omni.db - Table:
wiki - Graph source: stored page bodies parsed for wiki/local markdown links
Hard Constraints
- NO vector embeddings — query is keyword/tag matching over stored rows
- Validation today is bounded to graph integrity (dangling-link detection), not a full semantic linter
Other versions39 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 39
- Yeachan-Heo/oh-my-claudecode★ 40ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 40ksame name
- Yeachan-Heo/oh-my-codex★ 34ksame name
- AgriciDaniel/claude-obsidian★ 16ksame name
- SethGammon/Citadel★ 927same name
- saltmd/salt.md★ 166same name
- ekadetov/llm-wiki★ 108same name
- skillberry-ai/cap-evolve★ 65same name
- 6eanut/llm-wiki★ 43same name
- alxyrgin/health-os★ 38same name
29 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use ultragoal, hud and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Yeachan-HeoSkillultragoal
Create and execute durable repo-native multi-goal plans over Codex goal mode artifacts.
Also in 3 projects that use this
ibahgatSkillhud
Control omi visual HUD profile and keep status output readable in normal, compact, or hidden mode.
Also in 3 projects that use this
MicrosoftSkillwiki-lint
Use when an operation issue is a lint or health-check (`operationType: "lint"`) — typically the nightly lint routine or a manual "Run lint" from the UI. Audit the wiki for contradictions, orphans, weak provenance, broken links, and missing concept pages, and return a triage list — do not auto-fix.
Also in 4 projects that use this
MicrosoftSkillwiki-ingest
Use when an operation issue asks you to ingest a captured source from `raw/` into the LLM Wiki, or when the user explicitly says "ingest <slug>". The issue body will name a file under `raw/` (e.g. `raw/karpathy-llm-wiki.md`) and ask for durable wiki pages. Do not invoke this skill for Paperclip activity bundles — those use `paperclip-distill` instead.
Also in 4 projects that use this
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- ai-slop-cleanerSkill
- autopilotSkill
- cancelSkill
- configure-notificationsSkill
- debugSkill
- deep-diveSkill
- deepinitSkill
- deep-interviewSkill
- external-contextSkill
- mcp-setupSkill
- omni-doctorSkill
- omni-referenceSkill
- omni-setupSkill
- omni-planSkill
- ralphSkill
- ralplanSkill
- releaseSkill
- rememberSkill
- setupSkill
- skillifySkill
- skillSkill
- teamSkill
- traceSkill
- ultraqaSkill
- ultraworkSkill
- verifySkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

