goal-prompt

Converts agreed implementation discussions into structured goal prompts for execution agents.

Updated Jul 7, 2026
One-click install
npx skills add https://github.com/bbenefield89/skills --skill goal-prompt-bbenefield89
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: goal-prompt
Source: https://github.com/bbenefield89/skills/tree/main/skills/goal-prompt
Command: npx skills add https://github.com/bbenefield89/skills --skill goal-prompt-bbenefield89

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After a team converges on what to build, the decisions and constraints often stay scattered across chat history. This Skill compresses that settled discussion into a single durable Goal Prompt that another agent can execute without re-reading the entire conversation. ## Core Features & Use Cases - Objective Compression: Distills a feature, refactor, migration, or bug-fix discussion into one objective with a verifiable stopping condition. - Constraint Preservation: Captures non-goals, out-of-bounds files, compatibility requirements, and validation commands so nothing is lost in handoff. - Checkpoint Guidance: Instructs the receiving agent to work in checkpoints, keep progress logs, and stop and report on blocking conditions. - Use Case: After agreeing on a database migration approach in chat, generate a Goal Prompt naming the exact files to read, the migration commands to run, and the rollback expectations, then hand it to an implementation agent. ## Quick Start Turn our agreed discussion about the authentication refactor into a goal prompt for the implementation agent.

Frequently Asked Questions about goal-prompt

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write a goal prompt for an AI coding agent?

State one objective with a verifiable stopping condition, list the files and docs to read first, define constraints and non-goals, and specify validation commands. This Skill generates that structure automatically from an agreed discussion.

How to hand off implementation work between AI agents?

Compress the settled scope into a durable prompt containing the objective, starting context, constraints, validation steps, and checkpoint guidance. The receiving agent can then start immediately without re-reading the full conversation.

What should a goal prompt include for long-running tasks?

Include checkpoint instructions, a short progress log requirement, re-validation after each checkpoint, and explicit conditions where the agent should stop and report instead of guessing.

When should I not use a goal prompt generator?

Avoid it when key decisions are still unresolved. The Skill will ask targeted follow-up questions or return a list of missing information rather than inventing certainty about unsettled scope.

Does the goal-prompt skill work with any repository?

Yes, it reads project language from CONTEXT.md, ADRs, issues, and existing code when available. If those sources are missing, it instructs the agent to use standard project commands instead of inventing them.