vibeknowvibeknow/cli/skills/vibeknow-core/SKILL.md

vibeknow-core

Skill10 starsChanged 3 months agoMITView on GitHub

vibeknow CLI setup, authentication, profile management, and diagnostics. Use when: first-time setup, auth errors, switching environments, diagnosing connection issues.

In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- vibeknow-createSkill
- vibeknow-docSkill

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Document upload or status → use vibeknow-doc
line 42
Very specific:
All core commands support --output text|json|ndjson:
line 121

≈ “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-core

TRIGGER

First-time vibeknow setup or onboarding
Authentication errors or credential issues
Switching between environments (dev/staging/prod)
Diagnosing connection or endpoint problems
Managing profiles or config values

SKIP

Video generation, status, download → use vibeknow-create
Document upload or status → use vibeknow-doc

Core Concepts

Profile: A named environment config (endpoints + credential). Supports dev/staging/prod switching via vibeknow profile use <name>.
Credential priority: VIBEKNOW_TOKEN env var > OS keychain > encrypted file. The env var overrides everything and cannot be cleared by logout.
Endpoint trust boundary: Profiles pointing to localhost or non-official domains must set --trust dev --is-production=false, or the CLI refuses to start.
Doctor: Runs endpoint reachability checks and token validation. Use it first when anything seems wrong.

Quick Reference

Command	Description
`vibeknow auth status`	Show credential source and active profile
`vibeknow auth whoami`	Print current authenticated user
`vibeknow auth logout`	Clear stored credential for current profile
`vibeknow profile add NAME`	Add a new profile
`vibeknow profile use NAME`	Switch active profile
`vibeknow profile list`	List all profiles
`vibeknow profile show [NAME]`	Show profile details (default: current)
`vibeknow profile remove NAME`	Delete a profile
`vibeknow config get KEY`	Read a config value
`vibeknow config set KEY VALUE`	Write a config value
`vibeknow config list`	List all config keys
`vibeknow doctor`	Diagnose local setup and endpoint reachability

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

Common Tasks

Check if vibeknow is working

vibeknow doctor
vibeknow auth status

Set up a new dev environment

vibeknow profile add dev \
  --endpoint-figlens http://localhost:20067 \
  --trust dev \
  --is-production=false \
  --credential-ref vibeknow.dev
vibeknow profile use dev
vibeknow doctor

Switch between environments

vibeknow profile list              # see available profiles
vibeknow profile use prod          # switch to prod
vibeknow auth status               # verify credentials

Diagnose auth failure

vibeknow auth status               # check credential source
vibeknow auth whoami               # verify identity
vibeknow doctor                    # check endpoint reachability

Exit Code Handling

Exit	Meaning	Action
0	Success	—
1	General error	Check stderr message
2	Invalid arguments	Fix command syntax
3	Auth error	Run `vibeknow auth status`, check credential source
130	User interrupt (SIGINT)	—

For full exit code and error code reference, see errors.md.

Output Formats

All core commands support --output text|json|ndjson:

vibeknow auth status --output json    # structured output
vibeknow profile list --output json   # machine-readable profile list

References

commands.md — Full flag reference for all 12 subcommands
errors.md — Exit codes, error codes, and Error Object schema

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.

Check your setup, free