Agent skill
brainstorm
Help the user develop a vague idea into a "plan seed" — a scoped, handoff-ready statement of intent
Install this agent skill to your Project
npx add-skill https://github.com/rstacruz/agentic-toolkit/tree/main/skill/atk/brainstorm
SKILL.md
The user shares a rough idea. Guide them to a plan seed through targeted questioning — ask about intent, scope, and success criteria; point out blind spots; suggest alternative framings.
Rate readiness after each exchange:
NEEDS_REFINEMENT— critical gaps remain. State which gaps and ask 1-2 follow-up questions.READY_FOR_PLANNING— all planning criteria met. Produce the plan seed immediately.READY_FOR_EXECUTION— all planning + execution criteria met. Produce the plan seed immediately.
READY_FOR_PLANNING criteria:
- What problem is being solved (for whom)
- What success looks like (measurable or demonstrable outcomes)
- What is in/out of scope (explicit boundaries)
- Why this problem is important — always ask the user via the
questiontool; suggest reasons to pick from; never infer it yourself
READY_FOR_EXECUTION criteria: All planning criteria, plus the ones below:
- Implementation path is obvious — no design decisions remain; a competent engineer could start immediately
- Scope is narrow — touches a single file or tightly bounded area; no cross-cutting concerns
- Single deliverable — one concrete task, not a breakdown of sub-tasks
When done: Write the plan seed to artefacts/seed-<title>.md. Reply with the filename, then use the question tool to ask what's next:
- create a spec (
$spec-mode) or - refine the seed (
$refine-spec) or - add code blocks to explain changes (
$spec-tech-design) or - implement now (
$implement-spec)
Important: do NOT modify files other than Markdown files until the user specifically asks to start implementing. The goal is to assist the user in building a seed and a spec.
Plan seed: A concise document communicating intent clearly enough to hand off to a planner — not a plan itself.
Always use the question tool whenever you need user input.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
refine-implementation
Use after implementation to simplify and review code. Provide: git range (eg, main...HEAD). Runs simplify + peer review loop until change set is clean.
implement-spec
Implements a spec on a ticket-by-ticket basis.
spec-product-requirements
Gives important guidelines to define product requirements sections (functional requirements, technical requirements, constraints, design considerations, diagrams). Companion to $spec-mode.
coding-practices
Contains important guidelines for software engineering, coding, programming. Includes (but not limited to): - CP1: Functional core, imperative shell - CP2: Operational vs unexpected errors - CP3: Result-oriented interface pattern - CP4: Presentational vs container components - CP5: Log context builder pattern Use this when writing, editing, debugging, planning, or otherwise working with: - Any programming work - UI components in React, Vue, or similar - JavaScript, TypeScript, Rust, or any programming language
spec-tech-design
Gives important guidelines to define technical design sections (call graphs, data models, pseudocode, files, CSS classes, testing strategy). Companion to $spec-mode skill.
review-changes
Use when reviewing code changes against a plan. Provide: plan/spec doc; git range or changed files (eg, branch...HEAD). Returns P1/P2/P3 on alignment, quality, bugs, security.
Didn't find tool you were looking for?