xiduzo/wtf/wtf-steer-vision
- community
Checking that the SKILL.md file is still in the repository.
This skill should be used when a team wants to create or refine the project vision document — for example "create the vision document", "write our product constitution", "who are our users", or "the vision doc is outdated" — and as the entry point for "set up the steering docs". Generates docs/steering/VISION.md as a living document capturing product purpose, target users, principles, strategic goals, and bounded contexts. Generated once and refined — not regenerated from scratch.
Install
npx vskill@latest install xiduzo/wtf/wtf-steer-visionSKILL.md
Steer Vision
Generate or refine docs/steering/VISION.md — the product constitution. This document is the highest-level steering artifact. It captures why the product exists, who it serves, and what principles govern every decision.
The shared steering-doc flow (exists-check → research → interview → draft → review → write → wiki sync → continue) lives in ../references/steering-doc-process.md. Follow that process with the skill-specific inputs below.
- Doc path:
docs/steering/VISION.md - Template:
references/vision-template.md - Display name / wiki page:
WTF-Vision.md - Commit message:
docs: add project vision steering document
Step 2 — Research checklist
Run in parallel with the Agent tool:
Codebase signals:
- README for product description and stated goals
- Any existing
docs/files, ADRs, or architectural notes - Domain language in file names, module names, and type definitions
- Existing wiki pages or glossary files
GitHub signals (optional — skip if unavailable):
- Open and closed Epics for strategic intent — list per the List issues of a kind query (kind
Epic) in../references/issue-classification.md - Any issues or discussions that reference product goals or principles
Synthesize internally. Do not dump raw research at the user.
Step 3 — Gap-topic list
Ask only about items research could not determine, in priority order. For each unanswered item, call AskUserQuestion (per ../references/questioning-style.md):
- Product purpose — question: "What problem does this product solve, and for whom?" / header: "Product purpose" / options: pre-fill with purpose statements inferred from README or codebase.
- Target users — question: "Who are the primary users? Use their domain role names." / header: "Target users" / options: pre-fill with named roles inferred from the codebase.
- Core principles — question: "What 3–5 principles guide every product decision?" / header: "Core principles" / options: pre-fill with principles inferred from
CLAUDE.mdor READMEs. - Strategic goals — question: "What does success look like in 12–18 months?" / header: "Strategic goals" / options: pre-fill with goals inferred from open Epics or README.
- Bounded contexts — question: "Which domain contexts does this product span?" / header: "Bounded contexts" / options: pre-fill with contexts inferred from module structure or Epic vocabulary.
- Out of scope — question: "What is explicitly out of scope?" / header: "Out of scope" / options: pre-fill with exclusions found in existing docs or issue discussions.
Step 4 — Writing rules
- Apply strict STE per
../references/ste-writing.mdbefore you write any durable body (shared process Step 4 also requires this). - Every sentence uses domain language — the words domain experts and stakeholders use.
- Target users are named domain actors. Never write "users" or "admins".
- Strategic goals are business outcomes. They are not features or technical work items.
- Bounded context names stay consistent with vocabulary found in the codebase.
Step 8 — Continue options
{label: "Create TECH.md", description: "Run wtf.steer-tech to document the technical guidelines"}{label: "Create DESIGN.md", description: "Run wtf.steer-design to document the design guidelines"}{label: "Create QA.md", description: "Run wtf.steer-qa to document the QA standards"}{label: "Stop here", description: "Exit — no further action"}
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/wtf.steer-vision/SKILL.md
Popularity
- Repository stars
- 7
- Repository forks
- 2
- 7-day trend score
- 10
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/xiduzo/wtf/wtf-steer-vision)