yunzeforbetter/castflow/module-mark-skill

Claude Code and agent skill by yunzeforbetter/castflow

Trust tier 3
  • community
Source check pending

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

Mark candidate packages before a module cut. Use when cold-start must separate a feature, a shared method, an independent system, and a framework mechanism. NOT a programmer skill for one module.

Install

npx vskill@latest install yunzeforbetter/castflow/module-mark-skill

SKILL.md

Module marks

Mark packages so the module cut follows how this repo is built. The mark is a weight on an engineering stance. It is not a directory rule and not a skill.

Yield

  • One module's API how-to -> that programmer-*-skill
  • Drawing the package graph or printing the first cut -> coldstart
  • Designing a Jev question for some other job -> the jev skill, if installed
  • Writing scan ledgers (GRAPH.md, knowledge-graph.json, .ua/) -> never

Responsibilities

  1. Build one evidence card per candidate package from the scanner. Do not

invent packages by reading files one by one.

  1. Score four stances: feature, shared method, independent system, framework

mechanism. Use a structural prior always. When TYPESAFE_API_KEY is set, unresolved cards go to official TypeSafe System One (jev-latest unless TYPESAFE_DEFAULT_MODEL is set). When it is not set, say so and keep the prior. Do not invent a probability.

  1. Turn the winning stance into attach, split, keep, or review.

Show the revised cut. Do not hide unmarked rows.

  1. Persist a mark only after the user accepts it. The next scan applies

accepted marks before the prior and before Jev.

Navigate

  • EXAMPLES.md — evidence card, Jev questions, cut actions
  • SKILL_MEMORY.md — what a mark is not allowed to do
  • ITERATION_GUIDE.md — when this skill changes
  • marks.schema.json — card and decision fields; read it when emitting marks

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
5

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/yunzeforbetter/castflow/module-mark-skill/badge)](https://verified-skill.com/skills/yunzeforbetter/castflow/module-mark-skill)

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