agentleFS
vibeknowvibeknow/cli/skills/vibeknow-doc/SKILL.md

vibeknow-doc

Skill10 starsChanged 3 months agoMITView on GitHub

Upload documents to vectoria and check processing status. Use when: user wants to upload a document, check if a document is ready, or get a doc_id for use with vibeknow create.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check document processing status

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

vibeknow-doc

TRIGGER

  • Upload a document to vectoria for processing
  • Check document processing status
  • Get a doc_id for later use with vibeknow create --from <doc_id>

SKIP

  • Video generation or task management → use vibeknow-create
  • Auth, profile, environment setup → use vibeknow-core
  • RAG queries → not yet available

Core Concepts

  • doc upload: Uploads a local file to vectoria. Creates a knowledge base, polls until processing completes, and returns the doc_id + kb_id.
  • doc get: Fetches document status from vectoria. Requires both <doc_id> and --kb-id.
  • Document states: processing → completed or failed.
  • Relationship to create: vibeknow create --from <doc_id> uses an already-uploaded document. If you pass a file path or URL to create --from, it uploads automatically — you don't need doc upload first.

Quick Reference

CommandDescription
vibeknow doc upload <file>Upload a document to vectoria
vibeknow doc get <doc_id> --kb-id <kb_id>Fetch document status

For full flags and output examples, see commands.md.

Common Tasks

Upload a document and get its doc_id

vibeknow doc upload ./report.pdf
# Output includes doc_id and kb_id
vibeknow doc upload ./report.pdf --output json
# {"doc_id":"doc_abc123","kb_id":"kb_xyz789","status":"completed"}

Check if a document is ready

vibeknow doc get doc_abc123 --kb-id kb_xyz789

Upload then create video (two-step)

# Step 1: upload (useful if you want to reuse the doc_id)
result=$(vibeknow doc upload ./slides.pdf --output json)
doc_id=$(echo "$result" | jq -r '.doc_id')

# Step 2: create video from the uploaded doc
vibeknow create --from "$doc_id"

Note: For one-shot workflows, vibeknow create --from ./slides.pdf does both steps automatically.

Exit Code Handling

ExitMeaningAction
0Success—
1General errorRead stderr
2Invalid argumentsCheck file path exists, doc_id format
3Auth errorRun vibeknow auth status to inspect credential source. Re-login with vibeknow auth login (interactive) or set VIBEKNOW_TOKEN. See vibeknow-core for profile/diagnostics if installed.
130User interrupt—

For full error reference, see errors.md.

Output Formats

vibeknow doc upload ./report.pdf                   # text (human-readable)
vibeknow doc upload ./report.pdf --output json      # structured JSON
vibeknow doc get doc_abc --kb-id kb_xyz --output json

References

  • commands.md — Full flag reference
  • errors.md — Exit codes and error codes

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.