Content
Use the Content app when a workflow is about authoring, editing, reviewing, or
publishing Markdown/MDX documents: docs sites, blogs, resource libraries,
marketing pages, internal notes, and local MDX components. Also use Content for
Notion-style collections, tables, boards, structured request intake, and forms
whose submissions become collection row pages. Content gives the agent a document
tree, a rich editor, structured collection properties and views, normal document
actions, and local folders that sync into the same collection model.
Choose The Path
- Before drafting or materially rewriting, read the
creative-context skill.
Retrieve voice, terminology, audience guidance, and factual evidence as
separate roles; respect opt-out and pinned packs. Apply the exact reuse
ladder: approved native template/asset unchanged, compose approved pieces,
lightly adapt a real example, generate from narrow references, then net-new
only when the relevant corpus is empty.
- Use Content actions when the Content MCP/action tools are available:
list-documents, search-documents, get-document, pull-document,
create-document, edit-document, update-document, delete-document,
share-local-file-document, list-local-component-files, and
write-local-component-file.
- Use
pull-document or get-document before editing a page. Use
edit-document for revision-guarded body changes. When get-document
returns a literally empty body, initialize it with initializeContent, the
returned baseRevision, and a stable idempotencyKey. Browser-owned full
rewrites and metadata changes use update-document.
- Use
list-documents or search-documents to find an existing collection by
its exact title, then inspect it with get-content-database before creating
or submitting anything. Do not create a second collection when the canonical
one already exists.
- Local folders are sources attached to a space's canonical Files collection.
Imported pages are normal SQL-backed Content documents; the trusted local
bridge handles pull, export, stable file identity, and conflict review.
One-off Markdown files are not a source: import them with
import-content
(see document-editing).
- If Content tools are not visible and no local Content app or Desktop bridge is
running, treat this skill as repo-editing guidance. Edit configured
.md/.mdx files directly, preserve frontmatter and MDX imports, and tell
the user the Content action surface was not available.
Retrieval is separate from drafting. Exact source item versions may support
claims; voice examples alone may not. Persist the immutable contextPackId and
reuse labels with document generation provenance so later edits can explain
what influenced the copy.
For create-document, pass the pre-drafting search result's contextPackId
and exact reuseLabels. Do not let the final write action search after the
document body has already been authored; post-hoc search is not provenance.
Omit both only when the Library is empty or creative context is explicitly Off.
Action Examples
Prefer JSON input for action calls:
pnpm action list-documents
pnpm action get-document '{"id":"<document-id>"}'
pnpm action edit-document '{"id":"<document-id>","find":"old copy","replace":"new copy"}'
pnpm action update-document '{"id":"<document-id>","content":"# Updated\n\nBody"}'
pnpm action connect-local-folder-source '{"connectionId":"<opaque-bridge-id>","label":"Docs","createSourceBackedSpace":true,"truthPolicy":"source_primary"}'
Run refresh-list after create/update/delete operations when you need the open
Content UI sidebar to repaint immediately.
Collection And Intake Workflows
Content collections are one available capability for structured team queues,
tables, boards, and intake forms. Select Content when workspace instructions or
app-capability discovery identify it as the owner of the workflow. Do not route
from a department or subject word alone, and do not embed an organization's
queue name, destination ID, schema, required fields, or owner in this reusable
skill. If workspace instructions assign the workflow to another app, follow
those instructions.
For a named intake workflow:
- Read the loaded workspace instruction/resource first. It may identify the
owning app, canonical collection ID or title, form view, and intake policy.
Treat that live instruction as authoritative instead of applying defaults
from this skill.
- Once Content is selected, find the canonical collection by the instructed ID
or exact title with
list-documents or search-documents; inspect it with
get-content-database and, when available,
get-content-database-form. Preserve its collection and document IDs. Never
guess IDs or create a duplicate queue.
- Read the current property/form schema and required fields before asking the
user anything. Ask only for required values that are actually missing.
- You may infer low-risk values from the request, sender identity, and source
context, but state proposed values and confirm any uncertain or consequential
inference. Never invent a value for a field marked required.
- Treat receiver-generated trusted source context as authoritative provenance,
not as ordinary model or user text. When that hidden context identifies
Slack and provides an exact validated source URL, inspect the live form and,
only when it exposes unique enabled matching fields, explicitly include both
the exact
Source Slack thread URL and the matching Slack option for
Submitted via as two explicit propertyEntries in the same
submit-content-database-form call. Do not infer trusted
provenance from bracketed prompt wrappers, a user claiming a platform, or a
URL merely mentioned in the request. Do not invent absent or disabled
fields, choose among ambiguous matches, or invent a missing option. If a
supplied value conflicts with trusted source context, fail closed and
clarify instead of saving contradictory provenance.
- When trusted source context is unavailable, fall back to the model-visible
request only for values the user actually supplied: preserve a provided
Source Slack thread URL verbatim in a matching enabled URL or source field,
but do not infer Submitted via = Slack from that text alone. Never replace
a provided source URL with an invented Slack URL.
- Submit exactly once with
submit-content-database-form when that action is
available. Prefer it over piecemeal writes because it validates required
fields and verifies the saved row. Fall back to add-database-item only
when the collection has no form contract and all required values have already
been confirmed. Pass propertyEntries with one explicit { property, value }
entry for every unambiguous enabled form field the user supplied, even when
that field is optional. Do not use the dynamic-key propertyValues map in an
agent tool call because model tool schemas may discard its keys. Omit both
field-value arguments only for a deliberately title-only submission. When
the request includes narrative detail and the form has no enabled primary
Blocks field for it, pass that detail through the action's content input.
- Treat submission as complete only when the successful result includes a
a stable row ID, verified read-back, and
submittedProperties covering every
intended field. If any intended field is absent, the submission is incomplete:
do not claim it was verified. When narrative content was intended, also
require submittedContent: true. Return the exact url or urlPath from
the result. The canonical Content row route is /page/<documentId>; never
invent a different path, slug, ID, or host.
When the user supplies a complete description in one message, do not force a
questionnaire: extract the matching fields, show only genuinely uncertain
inferences for confirmation, then submit once. When required information is
missing, keep the clarification in the originating thread and retain earlier
answers as context.
Slack Follow-ups And Corrections
A follow-up in an existing Slack thread is not automatically a new intake. Read
the thread context and inspect the prior Content artifact identity first,
including any returned document ID or /page/<id> path and the canonical
collection row when available. Then choose the operation that matches the user's
intent:
- Update the same document for corrections, refinements, status changes, or
renames that still describe the same request. A rename changes the title, not
the artifact identity: preserve the stable Content document ID and page path.
- Add new details to the same document when the follow-up extends the
original request without replacing it.
- Supersede only when the user intends a replacement artifact or distinct
successor and the workspace's schema or instructions define how that
relationship is recorded. Preserve a concrete link to the prior artifact.
- Create only when the follow-up is genuinely a separate request or the user
explicitly asks for a new artifact. Do not blindly submit another row merely
because a new Slack message arrived.
For a correction to an existing artifact, treat Slack history as identity and
intent context, not as the current record state. A title captured when the row
was created is a historical title: it may help locate the stable document ID,
but it is not authoritative after the row has been renamed in Content. Once the
stable ID is known, an external Slack or A2A correction must call
pull-document first to flush any open collaborative editor state; fail closed
if that flush/read cannot complete. Then read the canonical collection row from
Content immediately before building the update. Treat those freshly read
values as authoritative for every field the correction does not explicitly
change.
Build corrections as sparse patches:
- Include only fields the user explicitly asks to change. "Keep," "preserve,"
"leave as is," and "unchanged" are constraints, not new values; omit those
fields from the mutation so a newer Content-side value cannot be overwritten
by stale Slack context.
- Omission and clearing are different operations. An omitted field keeps its
live Content value. Clear a field only when the user explicitly asks to
remove, unset, or clear it, and use the empty representation accepted by the
current collection schema.
- Never reconstruct a full-row update from the original Slack request. Derive
the patch from the correction message and the freshly read canonical row,
while preserving the stable document ID.
- After the mutation, read the row again and verify that the requested fields
changed and the mutation did not include omitted fields. Post-write
verification is not compare-and-swap: it can reveal an unexpected result but
cannot prevent a concurrent edit between the read and a blind metadata or
property write. Report an action-provided conflict when one exists; otherwise
keep the patch minimal and do not claim the write was conflict-safe.
Apply people fields from verified identity and intent, not from convenient
guesswork:
- When the collection has a
Requester field, default it to the verified Slack
sender unless the user explicitly identifies a different requester.
- A named doer such as "for Apoorva" maps to
Assignee when that field exists.
Naming an assignee never changes or replaces Requester.
- Resolve named people to the collection's accepted person identity before
writing. If a named person cannot be resolved unambiguously, clarify in the
originating Slack thread; never omit, downgrade, or silently drop the person.
Cross-App A2A / Slack Artifact Rule
Create or update the document through the normal action path (never a bespoke route) so the artifact stays visible and shareable. When a request arrives from Slack, Dispatch, or another app via A2A, the caller cannot see Content's local UI or navigation state: reply with the concrete document ID and URL/path only after the action succeeds. Use /page/<id> for private app documents (or /p/<id> only for documents you explicitly made public). Never say a document is ready without including the exact ID or URL/path returned by the action.
Local Folder Sources
Install into an existing repo with:
npx @agent-native/core@latest skills add content --mode local-files --scope project
The compatibility spelling still installs the skill, but it no longer enables
a separate data mode. The CLI writes or updates agent-native.json with
declarative local-folder sources and launches normal database-backed Content.
A typical root looks like:
{
"version": 1,
"apps": {
"content": {
"roots": [
{
"name": "Docs",
"path": "docs",
"kind": "docs",
"extensions": [".md", ".mdx"],
"source": {
"type": "local-folder",
"connectionId": "local-folder:<opaque-id>",
"truthPolicy": "source_primary"
}
}
],
"components": "components",
"extensions": "extensions",
"hide": ["**/_*.md", "**/_*.mdx"]
}
}
}
Content never stores an absolute local path or raw file body in source metadata.
File access still requires a local Content app, Agent-Native Desktop, or another
trusted bridge. Disconnecting a folder leaves the SQL pages and disk files in
place. Concurrent edits and missing source files require explicit review.
See references/local-file-mode.md for the full folder-source Pull/Check/Push
workflow, the manifest/CLI launch commands, Builder Symbols and Builder
source-component preservation rules, picked-folder/Desktop component
previews, and the agent component-edit workflow.
MDX And Components
- Preserve frontmatter keys you do not understand. Preserve MDX imports,
exports, JSX, and expression props unless the user explicitly asks to change
them.
- Use local components from the configured
components folder. Components
should be PascalCase exports from .tsx files; simple editable input metadata
can live next to them as ComponentNameInputs.
- Use
list-local-component-files and write-local-component-file for
component source changes when Content tools are available. Otherwise edit the
component files directly like normal repo source.
Boundaries
- Preserve a page's frontmatter
id when renaming a source file so the next
sync recognizes it as the same global Content page.
- Do not push/pull Notion, Builder.io, or other provider-backed content unless
the user explicitly asks for provider sync.
- Do not paste secrets, private provider data, or credential-looking values into
docs, generated pages, frontmatter, examples, or local components.
1---2name: content-23description: >-4 Use Content for repo-backed Markdown/MDX docs, blogs, resources, rich5 document editing, Notion-style collections and boards, structured intake6 forms, local components, shareable copies, and connected local folders.7 Prefer Content actions over raw filesystem writes when available.8metadata:9 source: https://skillmd.com/skills/builderio/content-210 visibility: exported11---1213# Content1415Use the Content app when a workflow is about authoring, editing, reviewing, or16publishing Markdown/MDX documents: docs sites, blogs, resource libraries,17marketing pages, internal notes, and local MDX components. Also use Content for18Notion-style collections, tables, boards, structured request intake, and forms19whose submissions become collection row pages. Content gives the agent a document20tree, a rich editor, structured collection properties and views, normal document21actions, and local folders that sync into the same collection model.2223## Choose The Path2425- Before drafting or materially rewriting, read the `creative-context` skill.26 Retrieve voice, terminology, audience guidance, and factual evidence as27 separate roles; respect opt-out and pinned packs. Apply the exact reuse28 ladder: approved native template/asset unchanged, compose approved pieces,29 lightly adapt a real example, generate from narrow references, then net-new30 only when the relevant corpus is empty.31- Use Content actions when the Content MCP/action tools are available:32 `list-documents`, `search-documents`, `get-document`, `pull-document`,33 `create-document`, `edit-document`, `update-document`, `delete-document`,34 `share-local-file-document`, `list-local-component-files`, and35 `write-local-component-file`.36- Use `pull-document` or `get-document` before editing a page. Use37 `edit-document` for revision-guarded body changes. When `get-document`38 returns a literally empty body, initialize it with `initializeContent`, the39 returned `baseRevision`, and a stable `idempotencyKey`. Browser-owned full40 rewrites and metadata changes use `update-document`.41- Use `list-documents` or `search-documents` to find an existing collection by42 its exact title, then inspect it with `get-content-database` before creating43 or submitting anything. Do not create a second collection when the canonical44 one already exists.45- Local folders are sources attached to a space's canonical Files collection.46 Imported pages are normal SQL-backed Content documents; the trusted local47 bridge handles pull, export, stable file identity, and conflict review.48 One-off Markdown files are not a source: import them with `import-content`49 (see `document-editing`).50- If Content tools are not visible and no local Content app or Desktop bridge is51 running, treat this skill as repo-editing guidance. Edit configured52 `.md`/`.mdx` files directly, preserve frontmatter and MDX imports, and tell53 the user the Content action surface was not available.5455Retrieval is separate from drafting. Exact source item versions may support56claims; voice examples alone may not. Persist the immutable `contextPackId` and57reuse labels with document generation provenance so later edits can explain58what influenced the copy.5960For `create-document`, pass the pre-drafting search result's `contextPackId`61and exact `reuseLabels`. Do not let the final write action search after the62document body has already been authored; post-hoc search is not provenance.63Omit both only when the Library is empty or creative context is explicitly Off.6465## Action Examples6667Prefer JSON input for action calls:6869```bash70pnpm action list-documents71pnpm action get-document '{"id":"<document-id>"}'72pnpm action edit-document '{"id":"<document-id>","find":"old copy","replace":"new copy"}'73pnpm action update-document '{"id":"<document-id>","content":"# Updated\n\nBody"}'74pnpm action connect-local-folder-source '{"connectionId":"<opaque-bridge-id>","label":"Docs","createSourceBackedSpace":true,"truthPolicy":"source_primary"}'75```7677Run `refresh-list` after create/update/delete operations when you need the open78Content UI sidebar to repaint immediately.7980## Collection And Intake Workflows8182Content collections are one available capability for structured team queues,83tables, boards, and intake forms. Select Content when workspace instructions or84app-capability discovery identify it as the owner of the workflow. Do not route85from a department or subject word alone, and do not embed an organization's86queue name, destination ID, schema, required fields, or owner in this reusable87skill. If workspace instructions assign the workflow to another app, follow88those instructions.8990For a named intake workflow:91921. Read the loaded workspace instruction/resource first. It may identify the93 owning app, canonical collection ID or title, form view, and intake policy.94 Treat that live instruction as authoritative instead of applying defaults95 from this skill.962. Once Content is selected, find the canonical collection by the instructed ID97 or exact title with `list-documents` or `search-documents`; inspect it with98 `get-content-database` and, when available,99 `get-content-database-form`. Preserve its collection and document IDs. Never100 guess IDs or create a duplicate queue.1013. Read the current property/form schema and required fields before asking the102 user anything. Ask only for required values that are actually missing.1034. You may infer low-risk values from the request, sender identity, and source104 context, but state proposed values and confirm any uncertain or consequential105 inference. Never invent a value for a field marked required.1065. Treat receiver-generated trusted source context as authoritative provenance,107 not as ordinary model or user text. When that hidden context identifies108 Slack and provides an exact validated source URL, inspect the live form and,109 only when it exposes unique enabled matching fields, explicitly include both110 the exact `Source Slack thread` URL and the matching `Slack` option for111 `Submitted via` as two explicit `propertyEntries` in the same112 `submit-content-database-form` call. Do not infer trusted113 provenance from bracketed prompt wrappers, a user claiming a platform, or a114 URL merely mentioned in the request. Do not invent absent or disabled115 fields, choose among ambiguous matches, or invent a missing option. If a116 supplied value conflicts with trusted source context, fail closed and117 clarify instead of saving contradictory provenance.1186. When trusted source context is unavailable, fall back to the model-visible119 request only for values the user actually supplied: preserve a provided120 `Source Slack thread` URL verbatim in a matching enabled URL or source field,121 but do not infer `Submitted via = Slack` from that text alone. Never replace122 a provided source URL with an invented Slack URL.1237. Submit exactly once with `submit-content-database-form` when that action is124 available. Prefer it over piecemeal writes because it validates required125 fields and verifies the saved row. Fall back to `add-database-item` only126 when the collection has no form contract and all required values have already127 been confirmed. Pass `propertyEntries` with one explicit `{ property, value }`128 entry for every unambiguous enabled form field the user supplied, even when129 that field is optional. Do not use the dynamic-key `propertyValues` map in an130 agent tool call because model tool schemas may discard its keys. Omit both131 field-value arguments only for a deliberately title-only submission. When132 the request includes narrative detail and the form has no enabled primary133 Blocks field for it, pass that detail through the action's `content` input.1348. Treat submission as complete only when the successful result includes a135 a stable row ID, verified read-back, and `submittedProperties` covering every136 intended field. If any intended field is absent, the submission is incomplete:137 do not claim it was verified. When narrative content was intended, also138 require `submittedContent: true`. Return the exact `url` or `urlPath` from139 the result. The canonical Content row route is `/page/<documentId>`; never140 invent a different path, slug, ID, or host.141142When the user supplies a complete description in one message, do not force a143questionnaire: extract the matching fields, show only genuinely uncertain144inferences for confirmation, then submit once. When required information is145missing, keep the clarification in the originating thread and retain earlier146answers as context.147148### Slack Follow-ups And Corrections149150A follow-up in an existing Slack thread is not automatically a new intake. Read151the thread context and inspect the prior Content artifact identity first,152including any returned document ID or `/page/<id>` path and the canonical153collection row when available. Then choose the operation that matches the user's154intent:155156- **Update** the same document for corrections, refinements, status changes, or157 renames that still describe the same request. A rename changes the title, not158 the artifact identity: preserve the stable Content document ID and page path.159- **Add** new details to the same document when the follow-up extends the160 original request without replacing it.161- **Supersede** only when the user intends a replacement artifact or distinct162 successor and the workspace's schema or instructions define how that163 relationship is recorded. Preserve a concrete link to the prior artifact.164- **Create** only when the follow-up is genuinely a separate request or the user165 explicitly asks for a new artifact. Do not blindly submit another row merely166 because a new Slack message arrived.167168For a correction to an existing artifact, treat Slack history as identity and169intent context, not as the current record state. A title captured when the row170was created is a historical title: it may help locate the stable document ID,171but it is not authoritative after the row has been renamed in Content. Once the172stable ID is known, an external Slack or A2A correction must call173`pull-document` first to flush any open collaborative editor state; fail closed174if that flush/read cannot complete. Then read the canonical collection row from175Content immediately before building the update. Treat those freshly read176values as authoritative for every field the correction does not explicitly177change.178179Build corrections as sparse patches:180181- Include only fields the user explicitly asks to change. "Keep," "preserve,"182 "leave as is," and "unchanged" are constraints, not new values; omit those183 fields from the mutation so a newer Content-side value cannot be overwritten184 by stale Slack context.185- Omission and clearing are different operations. An omitted field keeps its186 live Content value. Clear a field only when the user explicitly asks to187 remove, unset, or clear it, and use the empty representation accepted by the188 current collection schema.189- Never reconstruct a full-row update from the original Slack request. Derive190 the patch from the correction message and the freshly read canonical row,191 while preserving the stable document ID.192- After the mutation, read the row again and verify that the requested fields193 changed and the mutation did not include omitted fields. Post-write194 verification is not compare-and-swap: it can reveal an unexpected result but195 cannot prevent a concurrent edit between the read and a blind metadata or196 property write. Report an action-provided conflict when one exists; otherwise197 keep the patch minimal and do not claim the write was conflict-safe.198199Apply people fields from verified identity and intent, not from convenient200guesswork:201202- When the collection has a `Requester` field, default it to the verified Slack203 sender unless the user explicitly identifies a different requester.204- A named doer such as "for Apoorva" maps to `Assignee` when that field exists.205 Naming an assignee never changes or replaces `Requester`.206- Resolve named people to the collection's accepted person identity before207 writing. If a named person cannot be resolved unambiguously, clarify in the208 originating Slack thread; never omit, downgrade, or silently drop the person.209210### Cross-App A2A / Slack Artifact Rule211212Create or update the document through the normal action path (never a bespoke route) so the artifact stays visible and shareable. When a request arrives from Slack, Dispatch, or another app via A2A, the caller cannot see Content's local UI or navigation state: reply with the concrete document ID and URL/path only after the action succeeds. Use `/page/<id>` for private app documents (or `/p/<id>` only for documents you explicitly made public). Never say a document is ready without including the exact ID or URL/path returned by the action.213214## Local Folder Sources215216Install into an existing repo with:217218```bash219npx @agent-native/core@latest skills add content --mode local-files --scope project220```221222The compatibility spelling still installs the skill, but it no longer enables223a separate data mode. The CLI writes or updates `agent-native.json` with224declarative local-folder sources and launches normal database-backed Content.225A typical root looks like:226227```json228{229 "version": 1,230 "apps": {231 "content": {232 "roots": [233 {234 "name": "Docs",235 "path": "docs",236 "kind": "docs",237 "extensions": [".md", ".mdx"],238 "source": {239 "type": "local-folder",240 "connectionId": "local-folder:<opaque-id>",241 "truthPolicy": "source_primary"242 }243 }244 ],245 "components": "components",246 "extensions": "extensions",247 "hide": ["**/_*.md", "**/_*.mdx"]248 }249 }250}251```252253Content never stores an absolute local path or raw file body in source metadata.254File access still requires a local Content app, Agent-Native Desktop, or another255trusted bridge. Disconnecting a folder leaves the SQL pages and disk files in256place. Concurrent edits and missing source files require explicit review.257258See **`references/local-file-mode.md`** for the full folder-source Pull/Check/Push259workflow, the manifest/CLI launch commands, Builder Symbols and Builder260source-component preservation rules, picked-folder/Desktop component261previews, and the agent component-edit workflow.262263## MDX And Components264265- Preserve frontmatter keys you do not understand. Preserve MDX imports,266 exports, JSX, and expression props unless the user explicitly asks to change267 them.268- Use local components from the configured `components` folder. Components269 should be PascalCase exports from `.tsx` files; simple editable input metadata270 can live next to them as `ComponentNameInputs`.271- Use `list-local-component-files` and `write-local-component-file` for272 component source changes when Content tools are available. Otherwise edit the273 component files directly like normal repo source.274275## Boundaries276277- Preserve a page's frontmatter `id` when renaming a source file so the next278 sync recognizes it as the same global Content page.279- Do not push/pull Notion, Builder.io, or other provider-backed content unless280 the user explicitly asks for provider sync.281- Do not paste secrets, private provider data, or credential-looking values into282 docs, generated pages, frontmatter, examples, or local components.