Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →inkeep/open-knowledge-pack-knowledge-base
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 ow
Passed 14 of 21 test cases with the skill, and 4 of 21 without it.
and 18 more in the full report
13 fixed3 passed either way6 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are writing a tool call to create a newly ingested source clip file at `external-sources/docker-docs.md`. Which template identifier should be passed to the `write` verb?
| Checked | Without skill | With skill |
|---|---|---|
| Supplies clip as the template parameter for raw source document creation. | Missed | Passed |
| Ensures the document is stored within the external-sources/ folder. | Passed | Passed |
The instructions your model reads when the skill loads.
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.
test cases passed, vs 4 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.