ask-agents
Send a task or question to Claude Code and/or Gemini as external subagents and report back what they said. Use when the user asks…
Turn a rough, dictated, or ambiguous request into a clear, structured task, then carry it out. Use when a request is conversational, messy, underspecified, or high-stakes enough to deserve careful framing before work begins.
$ npx -y skills add chrisblattman/claudeblattman --skill prompt --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/promptContext preview
The summary Claude sees to decide when to auto-load this skill.
Turn a rough, dictated, or ambiguous request into a clear, structured task, then carry it out. Use when a request is conversational, messy, underspecified, or high-stakes enough to deserve careful framing before work begins.
name: prompt description: Turn a rough, dictated, or ambiguous request into a clear, structured task, then carry it out. Use when a request is conversational, messy, underspecified, or high-stakes enough to deserve careful framing before work begins.
Turn rough intent into an instruction another session could execute without repeated clarification — then execute it.
1. Identify the objective, the artifact to produce, the audience, sources, constraints, and success criteria. 2. Ask only questions that change scope, risk, source access, or irreversible action. If none qualify, do not ask any. 3. Convert the vague ask into concrete task instructions. 4. Include guardrails about what not to touch, when relevant. 5. Show the structured task briefly, then execute it, starting with the first bounded step.
Refined task: Inputs to provide: Constraints: Success criteria: First step:
A professor's guide to building AI workflows — from chatbots to self-improving systems. Website: claudeblattman.com
Send a task or question to Claude Code and/or Gemini as external subagents and report back what they said. Use when the user asks…
Wrap up the current session by writing a short HANDOFF.md in the project folder, so the next session can resume quickly. Use when…
Review a proposed plan with a single-pass structured critique and a clear verdict. Use when the user asks to review a plan,…
Dispatch a small panel of critic agents in parallel on a plan, draft, or decision, then synthesize their raw critiques in a…
Smoke-test skill for the starter kit. Confirms the plugin installed and skills load. Use when the user runs /kit-hello or asks to…
One-time starter-kit setup: detects optional AI engines (Codex, Gemini), confirms each with you, writes the engines config, and…