define-goal

Converts vague user intentions into concrete, measurable goals with verification criteria.

3|Updated Nov 8, 2014
One-click install
npx skills add https://github.com/mintuz/.dotfiles --skill define-goal-mintuz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: define-goal
Source: https://github.com/mintuz/.dotfiles/tree/main/agents/.agents/skills/define-goal
Command: npx skills add https://github.com/mintuz/.dotfiles --skill define-goal-mintuz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Vague requests like "make it faster" or "keep investigating" give an agent no way to know when work is done. This Skill turns fuzzy intentions into concrete, measurable objectives with explicit success criteria, scope boundaries, and verification evidence before any work begins. ## Core Features & Use Cases - Goal Shaping: Restates user intent as a specific outcome naming the artifact, verification method, scope, and stop conditions. - Quantification Heuristics: Applies domain-specific guidance for bugs, tests, performance, research, and operations to define numeric or binary success thresholds. - Goal State Management: Checks for an active goal via get_goal before calling create_goal, avoiding duplicates or conflicting objectives. - Use Case: A user says "make checkout faster." The Skill rewrites this into "Reduce checkout API p95 latency below 250 ms, verified by the local latency benchmark across 3 consecutive runs," then creates the goal. ## Quick Start Use $define-goal to turn my intention of improving the signup flow into a concrete, measurable goal before starting work.

Frequently Asked Questions about define-goal

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

FAQPage Schema
How do I create a measurable goal for an AI agent?

State the concrete outcome that will be true when done, the evidence that proves it, and a quantitative or binary success threshold. This Skill rewrites vague requests into that format and creates the goal with create_goal once it passes the quality bar.

What makes a good goal versus a weak goal?

A good goal names the outcome, verification method, scope bounds, and stop condition, such as a latency target verified by a benchmark. Weak goals like "make it faster" or "keep investigating" lack measurable success criteria and are rejected or rewritten.

When should I use the define-goal skill?

Use it when you explicitly ask to create or set a goal, invoke $define-goal, or want help turning an intention into a clear objective. Ordinary implementation requests should be done directly without forcing goal creation.

Does define-goal handle duplicate or conflicting goals?

Yes. It calls get_goal first; if an active goal matches the intent it continues using it, and if a conflicting goal exists it asks whether to finish, complete, or start a separate goal-backed thread.

What are the limitations of the define-goal skill?

It covers goal definition and creation only. It does not manage durable snapshots, decision logs, planning artifacts, ledgers, or long-running execution state, and it adds a token budget only when explicitly requested.