How to work in a Knowledge Base project (the knowledge-base starter pack).
$ npx skills add inkeep/open-knowledge --skill knowledge-base -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install inkeep/open-knowledge knowledge-base --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/inkeep/open-knowledge.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/server/assets/skills/packs/knowledge-base .claude/skills/knowledge-base && 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 "knowledge-base" agent skill from https://github.com/inkeep/open-knowledge/tree/main/packages/server/assets/skills/packs/knowledge-base into .claude/skills/knowledge-base/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-base", 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/inkeep/open-knowledge/tree/main/packages/server/assets/skills/packs/knowledge-baseType 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 inkeep/open-knowledge --skill knowledge-base -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install inkeep/open-knowledge knowledge-base --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/inkeep/open-knowledge.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/server/assets/skills/packs/knowledge-base .agents/skills/knowledge-base && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "knowledge-base" agent skill from https://github.com/inkeep/open-knowledge/tree/main/packages/server/assets/skills/packs/knowledge-base into .agents/skills/knowledge-base/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-base", 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 inkeep/open-knowledge --skill knowledge-base -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install inkeep/open-knowledge knowledge-base --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/inkeep/open-knowledge.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/server/assets/skills/packs/knowledge-base .cursor/skills/knowledge-base && 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 "knowledge-base" agent skill from https://github.com/inkeep/open-knowledge/tree/main/packages/server/assets/skills/packs/knowledge-base into .cursor/skills/knowledge-base/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-base", 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/inkeep/open-knowledge.git --path packages/server/assets/skills/packs/knowledge-base--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 inkeep/open-knowledge --skill knowledge-base -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install inkeep/open-knowledge knowledge-base --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/inkeep/open-knowledge.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/server/assets/skills/packs/knowledge-base .gemini/skills/knowledge-base && 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 "knowledge-base" agent skill from https://github.com/inkeep/open-knowledge/tree/main/packages/server/assets/skills/packs/knowledge-base into .gemini/skills/knowledge-base/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-base", 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 inkeep/open-knowledge knowledge-baseInstalls 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 inkeep/open-knowledge --skill knowledge-base -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/inkeep/open-knowledge.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/server/assets/skills/packs/knowledge-base .github/skills/knowledge-base && 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 "knowledge-base" agent skill from https://github.com/inkeep/open-knowledge/tree/main/packages/server/assets/skills/packs/knowledge-base into .github/skills/knowledge-base/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-base", 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 inkeep/open-knowledge --skill knowledge-base -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install inkeep/open-knowledge knowledge-base --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/inkeep/open-knowledge.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/server/assets/skills/packs/knowledge-base .opencode/skills/knowledge-base && 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 "knowledge-base" agent skill from https://github.com/inkeep/open-knowledge/tree/main/packages/server/assets/skills/packs/knowledge-base into .opencode/skills/knowledge-base/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-base", 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.
knowledge-baseHow to work in a Knowledge Base project (the knowledge-base starter pack).
Knowledge Base is an agent skill from inkeep/open-knowledge. How to work in a Knowledge Base project (the knowledge-base starter pack). Read when the project has the three-layer source-grounded layout — external-sources/ → research/ → articles/ — or when asked how this project is organized. Carries the layer model, per-folder rules, status flows, and log discipline so this guidance does NOT live inside template bodies or log.md. The three procedures live elsewhere: ingest in the platform open-knowledge skill, research and consolidate as their own sibling skills in this…
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `plugin.json`). Compatibility notes: Any agent host with the OpenKnowledge MCP server configured. Installed project-local by ok seed --pack knowledge-base.
It sits in Knowledge Management, covering Knowledge bases and Source-grounded notebooks. The repository describes itself as: Beautiful, AI-native markdown IDE and LLM wiki. The licence is GPL-3.0.
Read from SKILL.md and the folder at commit cf9b84c. 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.
Links to these hosts (documentation or services it may open):
gist.github.comFrom 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.
Any agent host with the OpenKnowledge MCP server configured. Installed project-local by `ok seed --pack knowledge-base`.
From compatibility in the SKILL.md frontmatter.
Knowledge Base loads about 2.1k tokens when it runs. Until then it costs about 154 tokens; SKILL.md has 988 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 inkeep/open-knowledge at commit cf9b84c, republished under its GPL-3.0 licence (© inkeep). 988 words, ~2,133 tokens.
.claude/skills/knowledge-base/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.This project uses the source-grounded knowledge-base layout. The whole point is a closed evidence loop: nothing canonical exists without a traceable chain back to a preserved source. This skill holds the workflow so the templates and log.md can stay clean — when you create a doc from a template you get structure, and the how lives here.
This skill is pack guidance. The platform
/open-knowledgeskill (read/write/preview/linking/grounding rules) still governs every markdown operation — this layers the KB workflow on top.
The user watches your build live — the editor follows the file you're writing, and the knowledge graph assembles on screen as pages get linked. No view management on your part; just author well: every page carries its links from the moment it's written (at minimum the hub/index page and its most related siblings — an unlinked page is invisible in the graph), and related pages share a cluster: frontmatter value (e.g. cluster: architecture) so the graph's cluster coloring makes the map read at a glance.
external-sources/ raw sources, saved verbatim (produced by `ingest`)
↓ cite
research/ provisional analysis (produced by `research`)
↓ promote
articles/ canonical, decided knowledge (produced by `consolidate`)The loop is ingest → research → consolidate, mapped to Karpathy's three-layer knowledge-base pattern. Every downstream claim traces upstream to a preserved source. Cite local paths in external-sources/, never bare web URLs — the KB must survive link rot.
Karpathy's insight: "The tedious part of maintaining a knowledge base is not the reading or the thinking — it's the bookkeeping." Humans abandon wikis because maintenance costs exceed perceived value. These procedures exist so an agent can do the bookkeeping (fetching, summarizing, cross-linking, superseding) without fatigue. Skipping the cross-linking, supersedes chains, or raw-source preservation is what turns a useful wiki back into an abandoned one.
Each layer has a full, STOP-gated procedure, and each ships as its own skill so it loads only when the work calls for it. Execute the procedure yourself with the OK verbs — these are your default move over a bare write when the work fits a layer.
| Procedure | Where it lives | When |
|---|---|---|
| ingest | Platform /open-knowledge skill (references/ingest-and-sources.md) — its Grounding rule depends on it everywhere, so it ships with every project, not just this pack. | Preserve a shared URL / PDF / file verbatim, OR you fetched a URL to ground a KB claim (binary sources preserved, not scraped). |
| research | Sibling skill /research-with-sources | Investigate / compare / synthesize multiple sources → provisional article with status: draft + sources:. |
| consolidate | Sibling skill /consolidate-notes | A decision was actually made → commit canonical source-of-truth with status: stable + a supersedes: chain. |
Typical day-2 flow: user shares a URL → ingest (preserve) → user asks "now research this" → research (provisional article, ingesting more sources as needed) → decision lands → consolidate (canonical article, supersedes the research).
Don't chain silently. After ingest, ask whether to proceed to research. After research, let the user decide whether the findings are ready to consolidate. Each procedure completes on its own terms — the user drives the transitions.
Autonomy gates vs session-level autonomy. A procedure's STOP gates (research's scoping gate, consolidate's decision-confirmation gate) are NOT overridden by session-level "work without stopping for clarifying questions" hints. Those hints cover trivial back-and-forth ("which file did you mean?"); the gates exist for one-way-door decisions. When in doubt, the gate is authoritative.
external-sources/ — Raw sources saved verbatim, not just cited: the actual fetched text of URLs, extracted text of PDFs, copies of referenced files. Each file's frontmatter carries the original URL, access date, and any author/publisher metadata. Produced by the ingest procedure (applies whether the user shared the URL or you fetched it yourself to ground a claim). Immutable after capture — update only to refresh a stale fetch. No analysis here; that belongs in research/.
research/ — Provisional analysis synthesizing external sources, stored as OKF status: draft. Produced by the /research-with-sources skill. Every factual claim cites a specific doc in external-sources/ (or an inline URL if ingest was skipped); no unsourced assertions. Keep the sources: frontmatter list aligned with the docs actually linked in the body. Promote to articles/ via the /consolidate-notes skill once the team decides the findings are stable.
articles/ — Canonical knowledge, committed after a team decision and stored as OKF status: stable. Produced by the /consolidate-notes skill. Carries a supersedes: chain tying back to the research/ docs it replaces (which in turn cite external-sources/) so the full evidence chain is traceable without leaving the repo. Source-of-truth for the domain; update only when a new decision supersedes it.
| Layer | status | Set when |
|---|---|---|
research/ | draft | created |
articles/ | stable | promoted by consolidate after a decision |
When a new article supersedes research, set that research to status: deprecated, add its path to the article's supersedes: list, and point it back with superseded_by:.
Older projects may use status: provisional / canonical and string entries under sources:. Read those forms as draft / stable and source resources. Do not rewrite untouched documents; use the OKF forms above for new writes and files you are already updating.
There is a log.md at the project root. Append one dated entry after any turn that creates, edits, or restructures content — one entry per turn, not per file. Silent edits break the audit trail.
Log: ingest runs (new sources), research / consolidate runs (provisional or canonical articles), direct write / edit / move / delete outside the three procedures, project-onboarding runs, folder restructures, and .ok/config.yml changes.
Reference docs as markdown links, not bare paths — [path/to/doc](./path/to/doc.md), so the entry shows up in links({ kind: "backlinks" }) for those docs. A bare path string does not register in the graph.
Because this append-only log.md is a reserved log, its broken links may be withheld from audit. When a clean result carries brokenLinkSuppression, it is filtered rather than proof that every raw link resolves; do not rewrite log history to clear those links.
Entry shape:
## YYYY-MM-DD: <short title>
- <what was done>
- Files touched: [doc-a](./path/doc-a.md), [doc-b](./path/doc-b.md)
- Sources ingested: [source-slug](./external-sources/source-slug.md)
- Open follow-ups: <topic-1>, <topic-2>Each folder has a starter template (clip, research-log, article). Create with write({ document: { path, template: "<name>" } }). Templates carry only structure (headings + frontmatter scaffold) — the meaning of each field and section is described above, not repeated inside the document body.
© inkeep, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in packages/server/assets/skills/packs/knowledge-base of inkeep/open-knowledge.
Open the folder on GitHubat commit cf9b84c
Knowledge Base 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 |
|---|---|---|---|---|---|---|
| Knowledge Base this skillinkeep/open-knowledge | 4.4k | — | ~2.1k | Automated safety check: Pass | GPL-3.0 | |
| Learn From Materialsdmoshehun-prog/learn-from-materials | 902 | — | ~7.9k | Automated safety check: Pass | MIT | |
| Paper LensYSQ-boop/paper-lens | 101 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Zlibrary To Notebooklmzstmfhy/zlibrary-to-notebooklm | 1.7k | 1 repos | ~968 | Automated safety check: Pass | MIT | |
| Multi-Source to NotebookLM Processorjoeseesun/qiaomu-anything-to-notebooklm | 6.2k | — | ~3.6k | Automated safety check: Pass | MIT | |
| LLM Wiki Knowledge GraphEgonex-AI/Understand-Anything | 85k | 1 repos | ~1.5k | Automated safety check: Pass | MIT |
dmoshehun-prog/learn-from-materials
Turns books, PDFs, slides and web pages into a source-grounded knowledge base and an interactive learning page in English or Chinese, with quizzes, relationship maps and reusable methodology notes.
YSQ-boop/paper-lens
Read and critically analyze one academic paper from an arXiv URL/ID or a local PDF, producing a source-grounded Markdown report that can grow from a quick read into a reviewer-level deep review.
zstmfhy/zlibrary-to-notebooklm
自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式，自动转换，一键创建知识库。
joeseesun/qiaomu-anything-to-notebooklm
Collects content from WeChat articles, web pages, YouTube, podcasts, documents and more, uploads it to NotebookLM and generates podcasts, slides or mind maps.
Egonex-AI/Understand-Anything
Detects a Karpathy-pattern LLM wiki and builds an interactive knowledge graph with entities, implicit relationships and topic clusters.
chenjin-cmd/xhs-virtual-product
This skill helps plan, select, produce, and market Xiaohongshu (RED) virtual/digital products — templates, knowledge bases, test tools, study materials.
inkeep/open-knowledge
A skill your agent uses when the user wants to create, author, write, or design a new Agent Skill (a SKILL.md) — for OpenKnowledge or for their editors — including requests like 'help me write a…
inkeep/open-knowledge
Read when the user asks what OpenKnowledge is, wants to install it on a repository, wants to open or preview a single markdown file that is not part of an OpenKnowledge project, wants to share an…
inkeep/open-knowledge
Write a blameless incident postmortem under postmortems/ following the Google SRE shape — evidence-based timeline, trigger vs root cause vs symptom, contributing factors, what went well, and…
inkeep/open-knowledge
How to work in a Codebase Wiki project (the codebase-wiki starter pack): an agent-authored, source-grounded wiki of the surrounding codebase.
inkeep/open-knowledge
Authoritative agent-runtime contract for working inside an OpenKnowledge project — a markdown-CRDT knowledge base exposed over MCP.
inkeep/open-knowledge
Promote existing research into a stable-status canonical article under articles/ in a Knowledge Base project (the knowledge-base starter pack).
Categories
How to work in a Knowledge Base project (the knowledge-base starter pack). Knowledge Base is an agent skill from inkeep/open-knowledge. How to work in a Knowledge Base project (the knowledge-base starter pack).
Knowledge Base fits situations like: tasks that involve Knowledge bases; tasks that involve Source-grounded notebooks.
Run `npx skills add inkeep/open-knowledge --skill knowledge-base -a claude-code`. Or copy the skill folder (packages/server/assets/skills/packs/knowledge-base in inkeep/open-knowledge) into .claude/skills/knowledge-base in your project. Claude Code loads it when a task matches its description.
Run `npx skills add inkeep/open-knowledge --skill knowledge-base -a codex`. Or copy the skill folder (packages/server/assets/skills/packs/knowledge-base in inkeep/open-knowledge) into .agents/skills/knowledge-base 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 inkeep/open-knowledge --skill knowledge-base -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/knowledge-base, .gemini/skills/knowledge-base, .github/skills/knowledge-base and .opencode/skills/knowledge-base in your project.
SKILL.md names no scripts, command-line tools or credentials: Knowledge Base is instructions for the agent only. Compatibility (from SKILL.md): Any agent host with the OpenKnowledge MCP server configured. Installed project-local by `ok seed --pack knowledge-base`..
SKILL.md names 1 domain. As links in the text: gist.github.com. 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.
Knowledge Base is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.1k tokens (SKILL.md is roughly 8.5k 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 Knowledge Base: Learn From Materials (dmoshehun-prog/learn-from-materials, 902 stars), Paper Lens (YSQ-boop/paper-lens, 101 stars), Zlibrary To Notebooklm (zstmfhy/zlibrary-to-notebooklm, 1.7k stars) and Multi-Source to NotebookLM Processor (joeseesun/qiaomu-anything-to-notebooklm, 6.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
inkeep (a GitHub organization) maintains it in inkeep/open-knowledge, which has 4,407 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 7, 2026.
Source: inkeep/open-knowledge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
