AI Agent Task Spec: Turn Vague Requests into Executable Instructions
2026 has entered the agent era — this template turns 'I want X' into an executable spec for an agent: goal, steps, available tools, definition of done, and boundaries.
OBJECTIVE / STEPS / TOOLS / DEFINITION OF DONE / DO NOT — work step by step, stop only when done
[ Log in to see the full prompt ]Sign up free to see the full prompt, copy it, save it, and join the discussion. Free content unlocks on login; Pro content is a separate subscription.
When running multi-step tasks with Claude / ChatGPT, writing the request as a 'spec' rather than casual chat makes a dramatic difference in completion quality. A clear 'definition of done' plus 'what not to do' is the key.
一段逐步執行、每步回報、卡住給 fallback、達標才停的 agent 執行。
A description of the intended result. Check this entry's testing notes and try the prompt with your own inputs.
Suno Engineer's Mindset: 4 Steps to a Song That Doesn't Sound Like AI
A studio engineer's breakdown of Suno's fatal weaknesses (fried vocals, high-frequency artifacts), plus a 4-step DAW workflow and a Suno Studio cleanup prompt.
5 Claude Weekly Workflows That Stuck After 6 Months
Proposal generator / meeting processor / content repurposer / Friday review / shutdown reset — out of 40 I tried, only these 5 survived, each saving 30+ minutes per run.
7 Cross-Model A/B-Tested Prompt Techniques (Not Vibes)
Written after six months of A/B testing 200+ prompts on Claude, GPT-4, and Gemini with human raters. Covers persona + constraint stacking, anti-examples, role-reversal QA, cognitive scaffolds, emotional priming, uncertainty CoT, and steelman-first.
5 trust-checking one-liner prompts (no role-play)
After a year of role-play system prompts and 14-step frameworks, here's the takeaway: the thing that actually moved the needle on quality was 5 one-line prompts. No roles, no markdown, no "you are an expert."