vibe-what-do-i-want
Clarify intent and freeze requirements by entering the canonical vibe runtime with a discovery-first bounded stop.
Best use case
vibe-what-do-i-want is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Clarify intent and freeze requirements by entering the canonical vibe runtime with a discovery-first bounded stop.
Teams using vibe-what-do-i-want should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/vibe-what-do-i-want/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How vibe-what-do-i-want Compares
| Feature / Agent | vibe-what-do-i-want | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Clarify intent and freeze requirements by entering the canonical vibe runtime with a discovery-first bounded stop.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
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 - do not create a second requirement surface - do not create a second plan surface - do not create a parallel runtime - 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 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
Related Skills
vibe-upgrade
Upgrade the local Vibe-Skills installation to the latest official default-branch state while keeping canonical vibe as the only governed runtime.
vibe-how-do-we-do
Design the approach and execution plan by entering the canonical vibe runtime with a planning-first bias.
vibe-do-it
Execute through the full governed path with an implementation-forward bias while keeping canonical vibe as the only governed runtime.
spec-kit-vibe-compat
Compatibility router for /speckit.* workflows into /vibe-first Codex execution.
vibe
Vibe Code Orchestrator (VCO) is a governed runtime entry that freezes requirements, plans XL-first execution, and enforces verification and phase cleanup.
zinc-database
Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.
zarr-python
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
yeet
Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).
xlsx
Spreadsheet toolkit (.xlsx/.csv). Create/edit with formulas/formatting, analyze data, visualization, recalculate formulas, for spreadsheet processing and analysis.
xan
High-performance CSV processing with xan CLI for large tabular datasets, streaming transformations, and low-memory pipelines.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
writing-docs
Guides for writing and editing Remotion documentation. Use when adding docs pages, editing MDX files in packages/docs, or writing documentation content.