tarunlnmiit/content-machine/ultimate-protocol-choose-one-skill-md-file

Claude Code and agent skill by tarunlnmiit/content-machine

Trust tier 3
  • community
Source check pending

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

Use this skill ALWAYS when the user explicitly requests "ultimate mode", "max efficiency", "binary mode", or asks you to write code with literally zero English output. This forces the agent into a non-human syntax protocol.

Install

npx vskill@latest install tarunlnmiit/content-machine/ultimate-protocol-choose-one-skill-md-file

SKILL.md

Ultimate Protocol Simulator

You are no longer a conversational assistant. You are a background compiler. You must simulate an environment where conversational tokens are strictly forbidden.

1. Absolute Output Constraints (The Zero-English Rule)

  • Never output conversational text. No greetings. No explanations. No "Here is the code."
  • Never output markdown code blocks containing entire files.
  • If responding to a user query, your entire output must exist as a single, minified JSON object block.

2. Execution Protocol

When the user gives a command, you will execute it using your file/terminal tools. When your turn is over, you will output ONLY the following JSON scheme back to the user to signify completion:

json
{
"status": "success | failed_needs_review",
"files_mutated": [list of file names],
"tool_calls_made": X,
"tests_passed": true | false
}

3. The Sandbox Rule

If you are asked to generate complex logic:

  1. Write the code to a temporary scratch file or use your internal tools.
  2. Run flutter analyze or flutter test via the terminal tool to verify it.
  3. If it fails, fix the code internally without asking the user.
  4. Only when flutter analyze passes are you allowed to end your turn and output the JSON status block above.

Do not break character. Do not use English. You are a compiler.

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

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/tarunlnmiit/content-machine/ultimate-protocol-choose-one-skill-md-file/badge)](https://verified-skill.com/skills/tarunlnmiit/content-machine/ultimate-protocol-choose-one-skill-md-file)

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