bingordinary/specflow/spec-writeback-guidance

Claude Code and agent skill by bingordinary/specflow

Trust tier 2
  • community
LLM review pending
Source check pending

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

Use when a user-approved guidance conclusion must be written into formal candidate Spec truth, and the executor must choose the legal specFlow writeback route without treating chat as durable truth.

Install

npx vskill@latest install bingordinary/specflow/spec-writeback-guidance

SKILL.md

Spec Writeback Guidance

Purpose

Use this skill to move approved guidance conclusions into formal specFlow truth.

This skill is a bridge into existing specFlow routing. It does not create a new command family.

Process

  1. Identify which approved conclusions affect behavior, boundary, acceptance, rule truth, or global rules.
  2. Restate the approved conclusion as current truth content, not as a transcript of the discussion.
  3. Write only current approved truth into the proper candidate, evidence record, Rule, or global rule proposal path.
  4. Do not copy design discussion history, rejected options, or patch-note language into candidate truth.
  5. After writeback, route to the smallest legal next step.
  6. If the approved conclusion describes a larger development chain, write only the durable truth owned by the selected target and rerun routing from current repository truth for the next step.

Output Shape

Report:

  1. writeback_target
  2. owner_reason
  3. written_truth_summary
  4. excluded_discussion_material
  5. next_legal_step
  6. why_next_step_is_legal
  7. user_visible_state_summary

Boundaries

  1. Candidate writeback is not the final review step. After the user's completion signal and explicit confirmation, route to promote@{target} as the agent-level gateway for final validation (the CLI independently validates cache freshness and format); never run promote on your own.
  2. Do not implement from chat-only design.
  3. Do not ask the user to choose internal rule-governance flow names.
  4. Do not treat a guidance conclusion as durable until it has been written into the required truth target.
  5. Do not claim the whole user goal is complete when only the first truth writeback step has landed.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

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

Source

Popularity

Repository stars
73
Repository forks
4
7-day trend score
0

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

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