knowledge-base

Name: knowledge-base
Author: inkeep

3.1kstars191forks

How to install knowledge-base?

inkeep/open-knowledge/knowledge-base

$npx -y skills add inkeep/open-knowledge --skill knowledge-base

Installs into the current project.

Summary

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/ — wired to the workflow MCP tool's ingest / research / consolidate kinds. Carries the

Files · 1

View on GitHub

SKILL.md

1	# Knowledge Base pack — how to work here
2
3	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.
4
5	> This skill is pack guidance. The platform `open-knowledge` skill (read/write/preview/grounding rules) still governs every markdown operation — this layers the KB workflow on top.
6
7	## Link at creation
8
9	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.
10
11	## The three layers
12
13	```
14	external-sources/ raw sources, saved verbatim (produced by `ingest`)
15	↓ cite
16	research/ provisional analysis (produced by `research`)
17	↓ promote
18	articles/ canonical, decided knowledge (produced by `consolidate`)
19	```
20
21	The loop is ingest → research → consolidate — each a `workflow({ kind })` guide you invoke (`workflow({ kind: 'ingest' })`, etc.). 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.
22
23	## Per-folder rules
24
25	`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 `ingest` (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/`.
26
27	`research/` — Provisional analysis synthesizing external sources. Produced by `research`. 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 `consolidate` once the team decides the findings are stable.
28
29	`articles/` — Canonical knowledge, committed after a team decision. Produced by `consolidate`. 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.
30
31	## Status flow
32
33	\| Layer \| `status` \| Set when \|
34	\|---\|---\|---\|
35	\| `research/` \| `provisional` \| created \|
36	\| `articles/` \| `canonical` \| promoted by `consolidate` after a decision \|
37
38	When a new article supersedes an older one, add the older article's path to the new one's `supersedes:` list.
39
40	## Log discipline (MUST)
41
42	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.
43
44	Log: `ingest` runs (new sources), `research` / `consolidate` runs (provisional or canonical articles), direct `write` / `edit` / `move` / `delete` outside the three loop tools, `discover` runs, folder restructures, and `.ok/config.yml` changes.
45
46	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.
47
48	Entry shape:
49
50	```markdown
51	## YYYY-MM-DD: <short title>
52
53	- <what was done>
54	- Files touched: [doc-a](./path/doc-a.md), [doc-b](./path/doc-b.md)
55	- Sources ingested: [source-slug](./external-sources/source-slug.md)
56	- Open follo

People who liked this also viewed

6 picks

Type

knowledge-base

3.1kstars191forks

View on GitHub

How to install knowledge-base?

inkeep/open-knowledge/knowledge-base

$npx -y skills add inkeep/open-knowledge --skill knowledge-base

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Knowledge Base pack — how to work here
2
3	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.
4
5	> This skill is pack guidance. The platform `open-knowledge` skill (read/write/preview/grounding rules) still governs every markdown operation — this layers the KB workflow on top.
6
7	## Link at creation
8
9	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.
10
11	## The three layers
12
13	```
14	external-sources/ raw sources, saved verbatim (produced by `ingest`)
15	↓ cite
16	research/ provisional analysis (produced by `research`)
17	↓ promote
18	articles/ canonical, decided knowledge (produced by `consolidate`)
19	```
20
21	The loop is ingest → research → consolidate — each a `workflow({ kind })` guide you invoke (`workflow({ kind: 'ingest' })`, etc.). 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.
22
23	## Per-folder rules
24
25	`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 `ingest` (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/`.
26
27	`research/` — Provisional analysis synthesizing external sources. Produced by `research`. 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 `consolidate` once the team decides the findings are stable.
28
29	`articles/` — Canonical knowledge, committed after a team decision. Produced by `consolidate`. 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.
30
31	## Status flow
32
33	\| Layer \| `status` \| Set when \|
34	\|---\|---\|---\|
35	\| `research/` \| `provisional` \| created \|
36	\| `articles/` \| `canonical` \| promoted by `consolidate` after a decision \|
37
38	When a new article supersedes an older one, add the older article's path to the new one's `supersedes:` list.
39
40	## Log discipline (MUST)
41
42	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.
43
44	Log: `ingest` runs (new sources), `research` / `consolidate` runs (provisional or canonical articles), direct `write` / `edit` / `move` / `delete` outside the three loop tools, `discover` runs, folder restructures, and `.ok/config.yml` changes.
45
46	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.
47
48	Entry shape:
49
50	```markdown
51	## YYYY-MM-DD: <short title>
52
53	- <what was done>
54	- Files touched: [doc-a](./path/doc-a.md), [doc-b](./path/doc-b.md)
55	- Sources ingested: [source-slug](./external-sources/source-slug.md)
56	- Open follo

People who liked this also viewed

6 picks

Type