bingordinary/specflow/project-framing

Claude Code and agent skill by bingordinary/specflow

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when a user has a vague project, feature, or behavior idea and the goal, target user, real problem, success meaning, or non-goals are not yet clear enough to write candidate truth.

Install

npx vskill@latest install bingordinary/specflow/project-framing

SKILL.md

Project Framing

Purpose

Use this skill before writing candidate truth when the project idea is still vague.

The goal is to clarify the original problem, not to design implementation. The output remains discussion context until written into a candidate Spec through specFlow truth writeback.

Process

  1. Read only the repository context needed to understand whether an existing unit, rule, or boundary may own the idea.
  2. Translate the user's wording into ordinary-language goal, actor, desired outcome, and success meaning before naming internal specFlow owners.
  3. Ask one focused question at a time when user intent cannot be discovered from repository truth.
  • phrase the question in user-goal language
  • do not ask the user to choose unit, rule, or stable g_ rule
  1. Clarify these minimum facts:
  • target user or actor
  • problem or need
  • desired outcome
  • success criteria
  • first version non-goals
  1. When a fact becomes confirmed and affects formal behavior, mark it as candidate-writeback material.
  2. Do not continue into implementation planning.

Output Shape

Report the framing result in plain language:

  1. goal
  2. target_user_or_actor
  3. problem
  4. success_criteria
  5. first_version_non_goals
  6. candidate_writeback_items
  7. open_questions

Boundaries

  1. Do not keep confirmed behavior only in chat once it will constrain implementation.
  2. Do not create a new unit by naming alone; governance routing still decides formal ownership.
  3. Do not write implementation plans from this skill.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/bingordinary/specflow/project-framing/badge)](https://verified-skill.com/skills/bingordinary/specflow/project-framing)

Something wrong with this skill or its page? Tell us.