OpenParable
Skip to content
← Back to skills

Vibe What Do I Want

Productivity
vibe-what-do-i-want

Vibe What Do I Want is an Agent Skill for productivity published in the foryourhealth111-pixel/Vibe-Skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Clarify intent and freeze requirements by entering the canonical vibe runtime with a discovery-first bounded stop.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/foryourhealth111-pixel/Vibe-Skills/blob/HEAD/bundled/skills/vibe-what-do-i-want/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/vibe-what-do-i-want, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Use canonical vibe as the only governed runtime authority for this request.

Entry bias:

  • clarify what the user actually wants
  • shape scope before solutioning
  • strengthen requirement-first discovery
  • stop after canonical requirement_doc

Execution rules:

  • delegate to canonical vibe
  • keep vibe as the only runtime authority
  • let canonical vibe keep router selection and confirm_required ownership
  • do not create a second requirement surface
  • do not create a second plan surface
  • do not create a parallel runtime
  • do not preflight-scan the current workspace or repository for canonical proof files before launch
  • Launch canonical-entry first; validate receipts only after it returns a session root
  • do not continue into xl_plan, plan_execute, or phase_cleanup unless the user explicitly re-enters through canonical vibe or another approved wrapper
  • when a later wrapper intentionally continues from this bounded stop, forward --continue-from-run-id <source_run_id> and --bounded-reentry-token <reentry_token> from the latest runtime-summary.json bounded_return_control block

When this wrapper is chosen, enter canonical vibe with:

  • stronger deep_interview
  • stronger requirement clarification before planning
  • a bounded terminal stage of requirement_doc

Request: $ARGUMENTS