brainstorm
Explores requirements and approaches through collaborative dialogue before planning implementation.
Reviews and refines brainstorm or planning documents before implementation. Identifies gaps, clarifies assumptions, and ensures the approach is sound.
$ npx -y skills add VeryGoodOpenSource/vgv-wingspan --skill refine-approach --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/refine-approachContext preview
The summary Claude sees to decide when to auto-load this skill.
Reviews and refines brainstorm or planning documents before implementation. Identifies gaps, clarifies assumptions, and ensures the approach is sound.
name: refine-approach user-invocable: true description: Reviews and refines brainstorm or planning documents before implementation. Identifies gaps, clarifies assumptions, and ensures the approach is sound. when_to_use: Use when user says "refine this", "review my approach", or "is this ready". argument-hint: path to document to refine compatibility: Designed for Claude Code (or similar products with agent support)
Improve brainstorm and/or planning documents through structured review.
**Document path:** `$ARGUMENTS`
**If `$ARGUMENTS` is non-empty**, treat it as the document path and proceed to `Step 2. Assess`.
**If `$ARGUMENTS` is empty**, ask the user which document to review. Check `docs/brainstorm/` and `docs/plan/` for recent documents to suggest.
Read the document, then ask and clarify:
Do not fix yet anything. Simply take notes about what you find to inform what you do in `Step 3. Evaluate and score`.
Apply the following criteria to evaluate the document:
| Criteria | What to evaluate | |-----------|---------------| | **Clarity** | Problem statement is clear, no vague language ("probably," "consider," "try to") | | **Completeness** | Required sections present, constraints stated, open questions flagged | | **Specificity** | Concrete enough for next step (brainstorm → can plan, plan → can implement) | | **YAGNI** | No hypothetical features, simplest approach chosen | | **Scope** | Scope is well defined and constrained, not overly ambitious |
If invoked during a brainstorm phase (after `/brainstorm`), validate that the document reflects with fidelity the user intent.
Among everything found in Steps 2-3, does one issue stand out? If something would significantly improve the document's quality, this is the **must address** item. Highlight it prominently.
Present your findings, then:
1. **Auto-fix** minor issues (vague language, formatting) without asking 2. **Ask approval** before substantive changes (restructuring, removing sections, changing meaning) 3. **Update** the document inline—no separate files, no metadata sections
Simplification is purposeful removal of unnecessary complexity, not shortening for its own sake.
**Simplify when:**
**Don't simplify:**
After changes are complete, ask:
1. **Refine again** — another review pass 2. **Review complete** — document is ready
**When invoked directly by the user** (not as part of another skill), also determine the document type and offer clear context handoff as the first option:
**If the document is a brainstorm** (from `docs/brainstorm/`):
1. **Clear context and plan (Recommended)**: clear context for a fresh start, then plan 2. **Refine again** — another review pass 3. **Done for now** — document is ready
**If the document is a plan** (from `docs/plan/`):
1. **Clear context and build (Recommended)**: clear context for a fresh start, then build 2. **Refine again** — another review pass 3. **Done for now** — document is ready
**If the user selects "Clear context and plan"** → Follow the [clear context handoff](references/clear-context-handoff.md) for `/plan` with the actual brainstorm doc path. Then stop.
**If the user selects "Clear context and build"** → Follow the [clear context handoff](references/clear-context-handoff.md) for `/build` with the actual plan file path. Then stop.
**When invoked by another skill** (e.g., from `/brainstorm` or `/plan`), only offer "Refine again" and "Review complete", then return control to the caller.
After 2 refinement passes, recommend completion—diminishing returns are likely. But if the user wants to continue, allow it.
🦋 AI-assisted workflows that follow Very Good Ventures best practices and standards. Developed with 💙 by Very Good Ventures 🦄
Explores requirements and approaches through collaborative dialogue before planning implementation.
Executes an implementation plan — writes code and tests, runs quality review, and ships a pull request.
Stage, commit, push, and open a pull request following project conventions and the Conventional Commits spec. Accepts optional…
Scaffolds a new project by routing to the right companion plugin's create skill.
Produces a structured post-incident analysis — timeline, root cause, and actionable follow-ups — while context is fresh.
Applies Strunk's Elements of Style principles when writing or editing prose.