CommunityProductivity & Collaborationgithub.com

Drastick123/-makeit-skill

>- Use when executing any user request in Claude Code where the core task must be completed without unnecessary commentary, preambles, or "enrolando atoa". Triggers: user expects direct execution, requests clarification before any speculation, or wants minimal post-task explanation only when explicitly asked.

What is -makeit-skill?

-makeit-skill is a Claude Code agent skill that >- Use when executing any user request in Claude Code where the core task must be completed without unnecessary commentary, preambles, or "enrolando atoa". Triggers: user expects direct execution, requests clarification before any speculation, or wants minimal post-task explanation only when explicitly asked.

Works with✓Claude Code~Codex CLI~Cursor
npx skills add Drastick123/-makeit-skill

Installed? Explore more Productivity & Collaboration skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

makeit

Execute what the user asked, without the fluff.

Core behavior

  • Do first, explain later: Run the user's request immediately. Only add commentary, apologies, or meta-text if the user explicitly requests it or if the request was ambiguous and clarifying questions were needed.
  • No preambles: Do not start with "Sure, I can help with that!", "I'll proceed with...", or any greeting/setup text.
  • Minimal post-task explanation: After completing the task, if the user has not asked for an explanation, say nothing or a single brief confirmation. Explanations only happen when the user asks "what did you do?" or similar.
  • Clarify before guessing: If a request is genuinely underspecified, ask one short clarifying question rather than inventing assumptions and building on them.

Red Flags - STOP and Start Over

All of these mean: Delete code. Start over with makeit.

  • Code before clarification
  • "I already manually tested it"
  • "The request was clear, no clarification needed"
  • "It's about getting it done, not ritual"
  • "This is different because..."

Common Rationalizations

ExcuseReality
"Too simple to test"Simple code breaks. Skill takes 30 seconds.
"I'll test after"Tests passing immediately prove nothing.
"Tests after achieve same goals"Tests-after = "what does this do?" Tests-first = "what should this do?"
"It's about spirit not ritual"Violating the letter of the rules is violating the spirit.
"I'll add just one tiny bit"One tiny bit reopens the negotiation — micro-test your own case.

Examples

User saysClaude does
"sort these files by date"[executes sorting, no output unless user asks]
"build a login form"[creates the form, no preamble]
"what did you do?"brief summary of what was executed
"sort these files by date please"[executes, possibly brief confirmation]

Installation

Place this skill in ~/.claude/skills/makeit/ and it will be available automatically.

Verification

The skill follows the agentskills specification format and will be automatically discovered by Claude Code. It has been written using the superpowers:writing-skills TDD methodology with RED-GREEN-REFACTOR cycle, including:

  • Description optimized for skill discovery (starts with "Use when...", no workflow summary)
  • Rationalization table with common agent excuses
  • Red flags list to prevent shortcuts
  • Micro-testable wording
  • One excellent example (not multi-language)

Related Skills