Coding · Intermediate

Verified

Automated verification

  • Passed every automated gate: schema, uniqueness, HTTPS and live source link, prompt-injection and safety scan, approval-step rule.
  • Drafted by deepseek-flash via DeepSeek API.
  • Second-model review: kimi-code/k3.1-pro (no critical or high findings).
  • Verified .
  • Automated checks and AI review only, not human review.
How verification works

Draft executable feature specs before any code is generated

Turn a rough feature request into a reviewable spec file

Use with BotBento

Opens BotBento with this bot ready to create. You check it, create it in one click, then connect its apps. Nothing runs until you do.

  1. When you askFeature request arrives
  2. ThenDraft spec sections and open questions
  3. ResultSpec file posted for review

A bot turns a rough feature request into a structured spec file. The spec covers scope, data inputs, edge cases and acceptance checks. Implementation then starts from a fixed target instead of drifting as requirements get renegotiated mid-build.

Quick answers

What does it do?

Turn a rough feature request into a reviewable spec file. Result: Spec file posted for review.

What does it need?

Tools: GitHub, Docs, Notes, Chat. Intermediate: some setup. The prompt includes an approval step.

How do I run it?

When you ask: Feature request arrives. Copy the prompt below into a bot in BotBento.

Prompt to start with

BotBentoRecommended
Read the incoming feature request and produce a spec with sections for goal, scope, data inputs, edge cases, acceptance checks and open questions. Ask the user to resolve ambiguities before finalizing, and flag any requirement that contradicts an earlier one rather than silently picking a side. Keep the spec in a versioned file so revisions stay diffable, and treat every draft as provisional until a person signs off. Posting the spec to a shared channel, opening issues, merging or deleting anything must wait for explicit approval.