From vgv-wingspan
Generates structured markdown implementation plans from high-level feature ideas, bug reports, or improvements, using brainstorm docs, targeted codebase searches, and VGV conventions.
npx claudepluginhub verygoodopensource/very_good_claude_code_marketplace --plugin vgv-wingspanThis skill uses the workspace's default tool permissions.
Transform feature descriptions, bug reports, or improvement ideas into well-structured markdown files that follow VGV conventions and best practices. This command provides flexible detail levels to match your needs.
Generates structured implementation plans from feature descriptions or requirements, grounded in repo patterns and research. Deepens existing plans via interactive sub-agent review.
Creates structured plans for multi-step tasks including software features, implementations, research, or projects. Deepens plans via interactive sub-agent reviews.
Creates detailed implementation plans interactively for features, refactoring, or tasks by reading work items, spawning codebase analysis agents, and collaborating with users.
Share bugs, ideas, or general feedback.
Transform feature descriptions, bug reports, or improvement ideas into well-structured markdown files that follow VGV conventions and best practices. This command provides flexible detail levels to match your needs.
<feature_description>$ARGUMENTS</feature_description>
Check for brainstorm output first — before asking the user anything.
ls docs/brainstorm/
A brainstorm is relevant if created within the last 7 days and its topic semantically matches the feature description (if provided).
| Brainstorms found | Feature description provided? | Action |
|---|---|---|
| One relevant | Yes | Read it, announce "Found brainstorm from [date]: [topic]", extract key decisions, proceed |
| One relevant | No | AskUserQuestion: "Plan this brainstorm?" — (Recommended) use it, or describe something different |
| Multiple relevant | Either | AskUserQuestion: list candidates, ask which to use |
| None / not relevant | No | Ask: "What would you like to plan?" |
| None / not relevant | Yes | Run /brainstorm to clarify the idea first |
Do not proceed until you have a clear feature description — from arguments, a brainstorm, or the user.
Skip option: if the description is already detailed enough, ask the user if they want to skip idea refinement and proceed directly to planning.
Do not re-run codebase-review-agent here. Codebase context was already captured in the brainstorm from /brainstorm.
Instead, extract what's needed from the brainstorm and run targeted searches:
Based on the findings from 0. Idea Refinement and 1.1 Local research, decide whether external research is needed:
| Signal | Decision |
|---|---|
| High-risk topic (security, payments, external APIs, personal data) | Always research — cost of missing something is too high |
| Strong local context (good patterns, CLAUDE.md guidance, clear user intent) | Skip external research |
| Uncertainty or unfamiliar territory (no codebase examples, new technology) | Research |
Announce the decision briefly and proceed. User can redirect if needed.
Only run this step if 1.1.1 Research decision determines that external research is needed.
Run these agents in parallel to gather external information:
After all research steps complete, consolidate findings:
src/authentication/forms/authentication_form:42)Optional validation: Briefly summarize findings and ask if anything looks off or missing before proceeding to planning.
Think like a product manager — what would make this issue clear and actionable?
Title & Categorization:
feat: add user authentication, fix: cart total calculation)-plan suffix
feat: add user authentication → 2026-01-21-feat-add-user-authentication-plan.mdStakeholder Analysis:
Content Planning:
After planning the issue structure, run the user-flow-analysis-agent to analyze the plan for flow completeness and gap identification:
Flow Analysis Output:
Default to Standard. Use a different level only when the task clearly warrants it.
| Level | When to use | Template |
|---|---|---|
| Minimal | Simple bugs, small enhancements, straightforward implementation | minimal |
| Standard (default) | Most features and bug fixes needing moderate detail | standard |
| Extensive | Major features, architectural changes, significant risk or uncertainty | extensive |
Before writing the plan file, ensure the session is on a feature branch:
Formatting checklist:
- [ ]) for trackable items; collapsible <details> for lengthy content#number), commits (SHA), and code (GitHub permalinks)Pre-submission Checklist:
Filename: Use the date and kebab-case filename from Step 2 Title & Categorization: docs/plan/YYYY-MM-DD-<type>-<descriptive-name>-plan.md
Examples:
docs/plan/2026-01-15-feat-user-authentication-flow-plan.mddocs/plan/2026-01-15-feat-thing-plan.md (not descriptive)docs/plan/feat-user-auth-plan.md (missing date prefix)After writing the plan file, use the AskUserQuestion tool and present the following options:
Options:
/build/plan-technical-review on this plan: run the technical review skill to validate the planBased on selection:
/build with the actual plan file path. Then stop./build skill with the plan file pathopen docs/plan/<plan_filename>.md to open the file in the user's default editor/plan-technical-review → Call the /plan-technical-review skill with the plan file path/refine-approach skill.NEVER CODE at this stage. Only focus on producing a plan.