inkeep/open-knowledge

"description": "CRDT knowledge base with real-time collaboration and AI agent tools",   "author": { "name": "Inkeep" },   "repository": "https://github.com/inkeep/open-knowledge"

"author": { "name": "Inkeep" },   "repository": "https://github.com/inkeep/open-knowledge" }

"repository": "https://github.com/inkeep/open-knowledge"

metadata:   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

- **Docs** — <https://openknowledge.ai/docs>

- **Source** — <https://github.com/inkeep/open-knowledge>

pack: "codebase-wiki"   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

{   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"name": "Inkeep"   },   "repository": "https://github.com/inkeep/open-knowledge-skills",

},   "repository": "https://github.com/inkeep/open-knowledge-skills",   "keywords": ["openknowledge", "starter-pack"]

"repository": "https://github.com/inkeep/open-knowledge-skills",

**Prerequisite.** This procedure assumes the `codebase-wiki` pack is seeded (`ok seed --pack codebase-wiki`, or `ok-beta` for Beta, → `wiki/` with `architecture/ modules/ flows/ concepts/ guides/`, each carrying folder frontmatter + a page 

- **Intra-wiki navigation** → OK doc links (`[Auth flow](../flows/auth.md)`). These build the full backlink / hub / orphan graph. Link liberally — density is how the wiki stays navigable. - **Code references, `internal`** → a relative markd

- **Code references, `public`** → GitHub blob URLs (`https://github.com/<org>/<repo>/blob/<branch>/path/to/file.ts`) so a reader without the repo can follow them. Detect the remote with `git remote get-url origin`; if there is none, fall ba

`exec("cat <content-dir>/wiki/OVERVIEW.md")` and read its frontmatter:

pack: "entity-vault"   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

{   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"name": "Inkeep"   },   "repository": "https://github.com/inkeep/open-knowledge-skills",

},   "repository": "https://github.com/inkeep/open-knowledge-skills",   "keywords": ["openknowledge", "starter-pack"]

"repository": "https://github.com/inkeep/open-knowledge-skills",

pack: "knowledge-base"   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

The loop is **ingest → research → consolidate**, mapped to [Karpathy's three-layer knowledge-base pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f). Every downstream claim traces upstream to a preserved source. Cit

pack: "knowledge-base"   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

- Use `exec("grep -rn <topic-keyword> <content-dir>")` to find prior research, or `exec("ls -A research")` if the project groups research in a known location

- Read each research article fully via `exec("cat <path>")` (rich enrichment gives frontmatter + shadow-repo activity + project git history + backlinks)

- **Update neighbors.** After writing, find 2-3 closely-related existing pages (via `exec("grep -rn <topic> <content-dir>")`) and add a link to the new article from each — usually under a "See also" section or inline where the new article i

- `exec("ls -A <target-dir>")` shows the new file

{   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"name": "Inkeep"   },   "repository": "https://github.com/inkeep/open-knowledge-skills",

},   "repository": "https://github.com/inkeep/open-knowledge-skills",   "keywords": ["openknowledge", "starter-pack"]

"repository": "https://github.com/inkeep/open-knowledge-skills",

pack: "knowledge-base"   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

1. `exec("grep -rln <topic-keyword> <content-dir>")` — returns matching files with frontmatter enrichment so you can judge relevance without opening each.

2. `exec("ls -A <content-dir>")` — surfaces folder layout and most-recent-updated doc per subdir.

3. For the **1-3 most promising candidates**, `exec("cat <path>")` — returns full doc + frontmatter + backlinks + recent shadow-repo activity.

- **Don't skip ingest.** Raw preservation separates capture from interpretation and makes research reproducible. An article without preserved sources is just opinion; an article with preserved sources is a trail someone else can follow. - I

- If a fetch returns an obvious *summary* instead of the raw bytes (some LLM-backed fetch tools do this), note it and try a raw alternative (`curl -sL <url>`, or ask the user to paste).

- **Existing canonical articles** on the topic — `exec("cat <path>")` (returns frontmatter + backlinks + shadow-repo activity).

- **Prior research** on adjacent topics — same: `exec("cat <path>")` for OpenKnowledge markdown.

If you followed *Persist as you go*, the article already exists and is substantially filled from Step 4 — this step **finalizes** it (fill any remaining sections, tighten the recommendation, run the structure + validation checks below) rath

- `exec("ls -A <dir>")` lists the new file with frontmatter enrichment

plugin: "okf"   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

[OKF v0.2](https://github.com/GoogleCloudPlatform/open-knowledge-format/blob/main/SPEC.md) is a portable format for agent-readable knowledge: Markdown files, YAML frontmatter, and standard links. The `/open-knowledge` skill governs tool use

{   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"name": "Inkeep"   },   "repository": "https://github.com/inkeep/open-knowledge-skills",

},   "repository": "https://github.com/inkeep/open-knowledge-skills",   "keywords": ["openknowledge", "starter-pack"]

"repository": "https://github.com/inkeep/open-knowledge-skills",

pack: "plain-notes"   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

{   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"name": "Inkeep"   },   "repository": "https://github.com/inkeep/open-knowledge-skills",

},   "repository": "https://github.com/inkeep/open-knowledge-skills",   "keywords": ["openknowledge", "starter-pack"]

"repository": "https://github.com/inkeep/open-knowledge-skills",

pack: "software-lifecycle"   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

pack: "software-lifecycle"   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

- `exec("ls -A proposals/")` and `exec("ls -A decisions/")` — see the sequence space and what has landed.

- `exec("grep -rln <keyword> proposals/ decisions/")` — pinpoint files that name the same subsystem.

- For the 1–3 most relevant hits, `exec("cat proposals/0003-x.md")` to read the full doc plus its backlinks.

**List, don't guess, the sequence.** `exec("ls -A proposals/")`, take the highest existing `NNNN`, add one, zero-pad to four digits. Guessing collides the moment two proposals are drafted the same week.

{   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"name": "Inkeep"   },   "repository": "https://github.com/inkeep/open-knowledge-skills",

},   "repository": "https://github.com/inkeep/open-knowledge-skills",   "keywords": ["openknowledge", "starter-pack"]

"repository": "https://github.com/inkeep/open-knowledge-skills",

pack: "software-lifecycle"   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

2. `exec("ls -A decisions/")` — see the existing sequence and titles.

3. `exec("grep -rln <subsystem-keyword> decisions/")` — find records touching the same subsystem, interface, or constraint.

4. For each promising hit, `exec("cat decisions/NNNN-x.md")` — read its Decision and Status.

If the decision graduated from an accepted proposal in `proposals/`, locate that proposal now (`exec("grep -rln <topic> proposals/")`) — you'll link it as the parent in Step 4.

1. `exec("ls -A decisions/")` — read the highest existing `NNNN`.

pack: "software-lifecycle"   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

2. Read it whole: `exec("cat proposals/0003-feature.md")`.

- the **decisions it assumes** — `exec("grep -rln <subsystem-keyword> decisions/")`, then `cat` the relevant ones. A design that contradicts an accepted ADR without noting it is a finding by itself.

- the **prior postmortems in the same subsystem** — `exec("ls -A postmortems/")` and `search({ query: "<subsystem> failure" })`. A postmortem names a failure mode; a design that reintroduces it is your highest-value catch.

pack: "software-lifecycle"   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

The knowledge base is markdown owned by OpenKnowledge MCP. Read and list in-scope markdown with `exec` (`exec("ls -A postmortems/")`, `exec("cat postmortems/2024-03-02-auth-outage.md")`, `exec("grep -rln failover .")`) and `search({ query: 

1. `exec("ls -A postmortems/")` — see every prior incident at a glance.

3. `exec("grep -rln <subsystem-keyword> postmortems/")` — exact-term sweep for the service, the error, the mechanism.

4. `exec("cat postmortems/<candidate>.md")` on the 1–3 closest matches — read their Root cause and Action items.

pack: "software-lifecycle"   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

1. `exec("ls -A proposals/")` — surface the proposal set with frontmatter enrichment.

2. `exec("ls -A decisions/")` — an accepted proposal often has a matching frozen record here.

4. For the 1-2 strongest candidates, `exec("cat proposals/0004-x.md")` — read the accepted design and its unresolved questions in full; those unresolved questions become your Open Questions seed.

- `exec("ls -A specs/")` — see what's been specced before; a sibling spec may already map the same subsystem.

- `exec("cat specs/003-x/spec.md")` — read the closest prior spec's Design + Migration for the shape and the pointers.

- `exec("ls -A guides/")` then `exec("cat guides/<runbook>.md")` — runbooks describe operational reality the code alone won't tell you.

1. `exec("ls -A specs/")` — read the existing `NNN-name/` folders. Take the highest `NNN`, add one, zero-pad to the existing width (`003` → `004`).

pack: "worldbuilding"   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

{   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"name": "Inkeep"   },   "repository": "https://github.com/inkeep/open-knowledge-skills",

},   "repository": "https://github.com/inkeep/open-knowledge-skills",   "keywords": ["openknowledge", "starter-pack"]

"repository": "https://github.com/inkeep/open-knowledge-skills",

pack: "writing-pipeline"   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

{   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",

"name": "Inkeep"   },   "repository": "https://github.com/inkeep/open-knowledge-skills",

},   "repository": "https://github.com/inkeep/open-knowledge-skills",   "keywords": ["openknowledge", "starter-pack"]

"repository": "https://github.com/inkeep/open-knowledge-skills",

metadata:   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

1. **Reads:** `exec("cat …")` for one doc, `exec("ls -A …")` for a directory (folder defaults + template menu), `exec("grep …")` for literal, `search` for ranked retrieval. Native `Read` / `Grep` only on source code (`.ts` / `.py` / …), nev

- **`Bash ls` / `Bash find` / `Bash cat` on dirs containing in-scope markdown** — use `exec("ls -A …")` / `exec("find … -name '*.md'")` / `exec("cat …")`. Native returns bare names; `exec` adds frontmatter, backlinks, and recent activity. `

- **Closed loop.** External sources are pulled in by the ingest procedure, then cited locally. A bare `[source](https://...)` inside a KB doc is **not** a citation — it is a TODO meaning "still needs ingesting". The chain only works if ever

- **Read the folder before writing (MUST).** Before creating/editing docs in a folder, call `exec("ls -A <folder>")` once per folder per session — it returns the folder's `title`/`description`/`tags` + `templates_available`. Skipping it lan

| List / find / read markdown | `Bash: ls`/`Glob: **/*.md`/`Read: foo.md` | `exec("ls -A …")` / `exec("find …")` / `exec("cat …")` |

| Reference another doc | `` `[text](./p.md)` `` (backticked) or HTML `<a>` | `[text](./p.md)` | | Embed an image | `<img>`, a `localhost`/`preview_url` URL, hot-link | save locally + `![meaningful alt](./path)` | | Factual claim in a KB do

| Embed an image | `<img>`, a `localhost`/`preview_url` URL, hot-link | save locally + `![meaningful alt](./path)` | | Factual claim in a KB doc | prose with no citation, OR inline `[src](https://…)` | ingest the source (`references/ingest-

| Factual claim in a KB doc | prose with no citation, OR inline `[src](https://…)` | ingest the source (`references/ingest-and-sources.md`), cite the local path |

| Write in an unfamiliar folder | straight to `write` | `exec("ls -A <folder>")` first |

- **Docs** — <https://openknowledge.ai/docs>

- **Source** — <https://github.com/inkeep/open-knowledge>

| List a markdown-heavy dir                       | `Bash: ls specs/`                                                                  | `exec("ls -A specs/")`                                                            |

| Find all SPEC.md files                          | `Glob: **/SPEC.md`                                                                 | `exec("find specs -name SPEC.md")`                                                |

| Find every literal occurrence of a phrase       | `Grep: "pattern" *.md`                                                             | `exec("grep -rn pattern <dir>")` (literal, grouped by file, with frontmatter)     |

| Read an individual doc                          | `Read: specs/foo/SPEC.md`                                                          | `exec("cat specs/foo/SPEC.md")`                                                   |

| Reference another doc                           | `` `[text](./page.md)` `` (backticked) or HTML `<a>`                               | `[text](./page.md)` (raw markdown)                                                | | Embed an image   

| Embed an image                                  | `<img src="...">` (HTML), a `localhost:<port>` / `preview_url` server URL, or hot-linked external URL | Fetch + save locally + doc-relative `![meaningful alt](./assets/images/path)`     | 

| Write a factual claim in a KB doc               | plausible prose without citation, OR inline `[source](https://URL)`                | `ingest` the source first, then cite the local path per Grounding                  | | Cite a web sourc

| Cite a web source you just fetched              | inline `[source](https://...)` because YOU did the fetch (not the user)            | `ingest` it — agent-initiated fetches are not exempt from the closed-loop rule    |

| Write a doc in an unfamiliar folder             | go straight to `write` with hand-authored markdown                        | `exec("ls -A <folder>")` first — read the folder description + `templates_available` before writing |

**Hub docs.** Don't *create* `INDEX.md` / `README.md` hub files solely to catalog children — `exec("ls -A <folder>")` returns the same view live, with per-file frontmatter + backlink counts. But if a hub doc *already exists* from prior work

| `merged-first` | An outside change to the file was handled before your write was saved: merged in, or saved to the doc's history when it could not be merged. Your write landed. | `true` | Re-read before the next edit (`exec("cat <path>")`

- **no existing doc already answers it** — scan first (`search`, `exec("grep …")`); if one does, point the user to it instead of writing a near-duplicate;

**Stale-session symptom.** If `edit` returns "Text not found" on text you can verify exists on disk (via `exec("cat …")`), or `No document at` a path you can `cat` from the content root, the MCP session is likely stale (e.g., after a folder

**Advisory warnings on writes.** `write` and `edit` responses may include `structuredContent.document.warnings` (batch: per-doc `structuredContent.documents[].warnings`) — advisory entries discriminated by `kind`, each also summarized as a 

Before creating or editing docs in a folder, **always** call `exec("ls -A <folder>")` once. The response carries the folder's own `title`/`description`/`tags` + `templates_available` (the template menu for `write({ document: { template } })

0. **First-contact check.** If the folder has no frontmatter of its own AND `templates_available` is empty AND `exec("ls -A")` shows substantial content elsewhere, the project hasn't been onboarded — STOP and run `onboard-existing-repo.md`.

- **Is it in scope?** If the source is unrelated to what this knowledge base is accumulating, ingest is pollution. Check the existing layout: `exec("ls -A <content-dir>")`.

- **Is it already ingested?** `exec("grep -rln <source-url-or-title-slug> <content-dir>")` — if the same source is already present with current content, stop and reuse. Re-ingest is appropriate when the source changed materially — see Step 

- **URL with a clear HTML/text extension** (`.html`, `.htm`, none, `.txt`, `.md`) → treat as **text**. Skip to Step 1c. The executable hard-block does NOT apply here because Step 1c never writes the source extension to disk — it writes a `.

- **Local file path** → use your native file read tool. If the local file is text (HTML, plain, markdown), skip to **Step 2b** (text wrapper). If it is a binary you want preserved verbatim, you already have the bytes on disk — skip Step 1b'

- **Ambiguous URL** (no extension, query-string download URL, redirect-y link) → run `curl -IL --proto =http,=https --proto-redir =http,=https --max-redirs 5 -A 'Mozilla/5.0' <url>` to read response headers, then classify by `Content-Type`:

2. **URL scheme — HARD BLOCK.** If the URL scheme is not `http://` or `https://` (i.e., `file://`, `gopher://`, `ftp://`, etc.) → **HARD STOP**. Tell the user: "Ingest only fetches `http(s)` URLs. Other schemes (local-file paths, intranet p

2. **Size pre-check.** Run `curl -IL --max-redirs 5 -A 'Mozilla/5.0' '<SOURCE_URL>'` (if not already done in Step 1a's ambiguous-URL branch) and read `Content-Length`:

- greater than 100 MB → **HARD STOP**. Tell the user the source exceeds GitHub's 100 MB file-size cap and offer the manual-`curl` + Git-LFS escape path.    - greater than 50 MB → STOP and ask explicitly: "Source is X MB (above the 50 MB Git

- greater than 50 MB → STOP and ask explicitly: "Source is X MB (above the 50 MB GitHub warn threshold). Proceed?"    - absent → proceed; the `curl --max-filesize` flag is the enforced backstop. Note in chat that the size could not be pre-v

- absent → proceed; the `curl --max-filesize` flag is the enforced backstop. Note in chat that the size could not be pre-verified.

mkdir -p "<content-dir>/external-sources" curl -L --fail \

curl -L --fail \

**Shell-escape any special characters in the URL (single quotes, backticks, dollar signs). Do NOT paste a URL containing a literal single quote directly into the single-quoted curl argument — break it into a shell-safe form first.**

- `--max-redirs 5` caps redirect chains (exit 47 on excess). - `--max-time 60` caps total request time (exit 28). - `--max-filesize 104857600` enforces the 100 MB hard cap as defense-in-depth in case the server omits or lies about `Content-

- `--max-filesize 104857600` enforces the 100 MB hard cap as defense-in-depth in case the server omits or lies about `Content-Length` (exit 63). The option has shipped since curl 7.10.8 (2003) — every modern install has it.

If curl exits non-zero:

- 63 (`--max-filesize` triggered) → `rm -f` the truncated output. STOP and tell the user the server's `Content-Length` was missing or wrong.

- 63 (`--max-filesize` triggered) → `rm -f` the truncated output. STOP and tell the user the server's `Content-Length` was missing or wrong. - 22 (HTTP error returned by `--fail`) → STOP. Auth wall, anti-scraping, or vanished URL. Ask the u

- Other (e.g., 1 = unsupported protocol from `--proto`) → STOP and report the curl exit code to the user.

## Step 1c: Text fetch (HTML / article sources, or shell-less host fallback)

Use your available web fetch tool (`WebFetch` or your host's equivalent). If the fetcher returns an obvious *summary* of the page instead of the raw content (some LLM-backed fetch tools do this), note it and try a raw alternative (`curl -sL

description: One-line summary from the source (their words, not yours) type: source source_url: https://example.com/path/to/file.pdf

type: source source_url: https://example.com/path/to/file.pdf source_path: ./<slug>.<ext>    # relative to this wrapper

source_url: https://example.com/path/to/file.pdf

description: One-line summary from the source (their words, not yours) type: source source_url: https://example.com/article

type: source source_url: https://example.com/article media_type: text/html

source_url: https://example.com/article

- `exec("ls -A <content-dir>/external-sources/")` lists the new file(s) with enrichment.

- **Every noun-phrase that names another document should be linked** using standard markdown link syntax. Two forms are valid: **relative** (`[text](./sibling.md)`, `[text](../folder/doc.md)`) — the recommended default, native in GitHub / O

- **Never glue `./` onto a content-root path.** `./wiki/modules/tasks`, written from a doc already inside `wiki/`, resolves to the doubled garbage `wiki/wiki/modules/tasks` — correct resolution of a malformed path, i.e. a silently broken li

- **External web sources are NOT inline body links.** Per the Grounding rule, web URLs live in the `source_url:` frontmatter of an ingested doc under `external-sources/` (or the project's equivalent raw-sources folder); the body cites the l

- **Markdown syntax only:** `![alt text](./path/to/image.png)`. Do NOT emit HTML `<img>` tags — they don't participate in OK's content graph and don't render consistently across Fumadocs / preview surfaces. Paths resolve relative to the doc

- **Always a doc-relative path — never a server URL.** Reference an asset by its path relative to the doc (`./image.png`, `../assets/foo.png`), never an absolute `http://localhost:<port>/…`, `127.0.0.1`, or other server URL. `preview_url`'s

- **Always a doc-relative path — never a server URL.** Reference an asset by its path relative to the doc (`./image.png`, `../assets/foo.png`), never an absolute `http://localhost:<port>/…`, `127.0.0.1`, or other server URL. `preview_url`'s

- **Placement model.** Free-form image embeds → co-located alongside the referencing doc (sha256 same-directory dedup): give `write({ asset })` a `path` in that doc's folder, because a bare file name goes to the attachment folder (`content.

1. `exec("ls -A <content-dir>")` — list every top-level entry.

2. For each top-level **directory**: `exec("ls -A <dir>")` — the enriched listing surfaces the `.md` count, per-child frontmatter samples, recursive count, and the folder's own descriptive `title`/`description`/`tags` + `templates_available

6. **Confirm-then-extend detection.** For each substantial folder, check the `exec("ls -A <folder>")` listing:

1. **Pick representative siblings.** From `exec("ls -A <folder>")`:

2. **Read the siblings.** `exec("cat <doc>")` on each. Extract:

7. **Apply confirmed proposals** via the `edit({ folder })` + `write({ template })` calls above. Re-run `exec("ls -A <folder>")` to confirm `templates_available` + the folder's descriptive `title`/`description`/`tags` are populated.

3. Apply via `edit` on each affected doc, resolving page titles to file paths via `exec("ls -A")` / `search`.

1. Re-run `exec("ls -A <folder>")` on every `[KB]` folder. Verify:

- **Don't create INDEX.md / README.md hub files** — folder frontmatter + `exec("ls -A")` give the same view live.

**Re-point at the end of a multi-doc workflow; don't claim a doc is on screen unless you put it there.** The one-shot attach (signal 3) opens the preview *once* — later writes do NOT move the pane; it stays on the doc you last navigated to.

**Canonical, always-current instructions:** <https://openknowledge.ai/docs/get-started/quickstart>. The rungs below are a quick orientation; the docs are authoritative (release channels and download links move, so this file deliberately poi

Three of the layers correspond to [Karpathy's three-layer knowledge-base pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f): **ingest** (raw sources, immutable) → **research** (wiki, provisional) → **consolidate** (

**Keep starter content clean (MUST).** A template body is a reusable skeleton, not a meta-prompt: section headings, real frontmatter, and SHORT `{Stub}` placeholders (e.g. `# {Meeting Title}`). Do NOT bake a workflow's verbose `{...}` promp

exec("ls -A meetings/")

metadata:   author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills"

author: "Inkeep"   repository: "https://github.com/inkeep/open-knowledge-skills" ---

repository: "https://github.com/inkeep/open-knowledge-skills"

`skills({ query })` path is unavailable. If the user already has a skills.sh page open, pass the full skill-page URL as `source`, e.g. `import({ source: "https://www.skills.sh/<owner>/<repo>/<skill>", add: [...] })` — the

open, pass the full skill-page URL as `source`, e.g. `import({ source: "https://www.skills.sh/<owner>/<repo>/<skill>", add: [...] })` — the middle segment is the REPO, not a literal `skills`. Do not

`import({ source: "https://www.skills.sh/<owner>/<repo>/<skill>", add: [...] })` — the