ready

Elicit and validate user intent into an execution-ready handoff, spec, and plan.

5|1|Updated May 8, 2026
One-click install
npx skills add https://github.com/baek-labs/hames --skill ready-baek-labs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ready
Source: https://github.com/baek-labs/hames/tree/main/packages/claude/integrations/dryforge/upstream/ready
Command: npx skills add https://github.com/baek-labs/hames --skill ready-baek-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Turning a vague goal, scattered notes, or an existing spec into something an agent can safely execute usually requires separate brainstorming and planning steps, and unspoken assumptions slip through. This Skill replaces that with one interactive dialogue that surfaces every load-bearing decision and produces a validated three-document contract before any code is touched. ## Core Features & Use Cases - Interactive intent elicitation: Decomposes any input (goal, docs, notes, or a mix) into challengeable material, then extracts domain decisions from the user and presents technical options with trade-offs instead of guessing. - Independent audits: Dispatches two fresh subagent checks — an intent-completeness guess-hunt before the spec is frozen, and a final 3-doc gate — so un-grounded assumptions are caught while the user can still decide. - Execution-ready 3-doc output: Writes handoff.md, spec.md, and plan.md (with a dependency graph) into .dryforge/, ready for the go skill to execute. - Use Case: You have a rough feature idea and a brain-dump from another tool. Invoke the ready skill, answer its targeted questions, review the generated spec and plan, then hand off to go for execution. ## Quick Start Invoke the ready skill with a description of what you want to build or change, then answer its questions and approve the resulting three-document plan.

Frequently Asked Questions about ready

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

FAQPage Schema
How do I turn a rough feature idea into an executable spec and plan?▼

Invoke the ready skill with your goal, notes, or existing documents as input. It interactively elicits the decisions only you can make, presents technical options with trade-offs, and writes a handoff, spec, and plan into .dryforge/ for the go skill to execute.

What inputs does the ready skill accept?▼

It accepts a natural-language goal, file paths to specs or brain-dumps, scattered notes, a mix of these, or nothing at all. Input is treated as challengeable material, not ground truth, and becomes settled only through dialogue and your approval.

Does the ready skill require git?▼

Yes, git is required for both greenfield and existing projects. If the project is not a git repo, the skill offers to run git init with an initial commit; if git is not installed, it stops and tells you.

How does the ready skill avoid making assumptions about my intent?▼

Every load-bearing decision must be grounded in what you said or explicitly asked. An independent intent-completeness subagent audits the dialogue for un-grounded guesses before the spec is frozen, and a final 3-doc gate reviews the finished documents.

What is the difference between first cycle and delta mode?▼

The skill branches on whether .dryforge/status.json exists. First cycle runs a forced foundation design covering domain and technical decisions; delta mode loads the existing harness as context and applies full rigor only to the current task.

When should I not use the ready skill?▼

Skip it for trivial one-line changes where a full spec is overhead, though it still downshifts to a thinner valid 3-doc for low-blast goals. It also cannot run without git installed, and it never executes code — execution belongs to the go skill.