idea-refine

idea-refine is a skill for Claude Code from GuillemRoca/agent-skills-android. It costs 41 tokens per session (900 once invoked), scanned A, original, MIT.

A planning skill for turning a vague feature, project, or product idea into a focused one-page direction. It explores possible approaches, evaluates them, and produces a clearer basis for writing a specification.

In plain words
What is it for?
Use it before writing a specification for an unclear feature or product idea. It is meant for exploration and decision-making, not for requirements that are already specific and unambiguous.
Why use it?
It reduces confusion when people have different interpretations of what should be built or when a request is too broad. It helps identify the intended users, success measures, and constraints before implementation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agent-skills-android plugin — 29 skills, 7 commands, 3 agents, 1 hook shipped together

Good fit Use it before writing a specification for an unclear feature or product idea. It is meant for exploration and decision-making, not for requirements that are already specific and unambiguous.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/guillemroca/agent-skills-android/idea-refine
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add GuillemRoca/agent-skills-android --skill idea-refine
Clone the repo
git clone --depth 1 https://github.com/GuillemRoca/agent-skills-android

Made for: Claude Code.

Or install agent-skills-android, the plugin that ships this one along with the rest of its 29 skills, 7 commands, 3 agents, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for idea-refine

README.md
[![agentmods](https://agentmods.dev/badge/skills/guillemroca/agent-skills-android/idea-refine/github.svg)](https://agentmods.dev/skills/guillemroca/agent-skills-android/idea-refine)
Your own site
<a href="https://agentmods.dev/skills/guillemroca/agent-skills-android/idea-refine"><img src="https://agentmods.dev/badge/skills/guillemroca/agent-skills-android/idea-refine/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for idea-refine

Your own site · 80×15
<a href="https://agentmods.dev/skills/guillemroca/agent-skills-android/idea-refine"><img src="https://agentmods.dev/badge/skills/guillemroca/agent-skills-android/idea-refine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 900 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.00900
Opus 5 $0.00020 $0.00450
Sonnet 5 $0.00008 $0.00180
Haiku 4.5 $0.00004 $0.00090

Measured 8d ago against content hash abb4049e455a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

idea-refine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/idea-refine/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Idea Refinement

Overview

Turn a vague idea into a focused, actionable direction. This skill uses structured divergent-convergent thinking: first expand possibilities, then evaluate and converge on the strongest direction, then sharpen into a one-pager ready for spec writing.

Philosophy: "Simplicity is the ultimate sophistication." Say no to 1,000 things to focus on the one that matters.

When to Use

  • A feature request or product idea is unclear or overly broad
  • You need to explore multiple directions before committing
  • Stakeholders have different interpretations of "what we're building"
  • Before writing a spec (feeds into spec-driven-development)

Skip when: The requirement is already specific and unambiguous.

Core Process

Phase 1: Understand & Expand (Divergent)

  1. Restate as "How Might We" — Convert the idea into an open question

    • "Add offline support" → "How might we ensure users can accomplish core tasks without connectivity?"
  2. Ask sharpening questions (answer or surface for human input):

    • Who specifically benefits? (persona, not "users")
    • What does success look like? (measurable outcome)
    • What constraints exist? (timeline, tech debt, API limitations, minSdk)
    • What has been tried before?
  3. Generate 5–8 variations using these lenses:

    • Inversion: What if we solved the opposite problem?
    • Constraint removal: What if we had no legacy code / no backward compatibility?
    • Simplification: What is the absolute minimum version?
    • Combination: What if we merged this with another planned feature?
    • Analogy: How do other Android apps solve this? (study Play Store top apps)

Phase 2: Evaluate & Converge

  1. Cluster into 2–3 directions — group related variations
  2. Stress-test each direction:
    • Technical feasibility (existing modules, Android API levels, library support)
    • User impact (who benefits, how much)
    • Effort estimate (small / medium / large)
    • Risk profile (what could go wrong)
  3. Surface hidden assumptions — list every assumption with a validation strategy
    • "Assumption: Room migrations will handle schema changes → Validate: write migration test"

Read the full file on GitHub · 93 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 93 lines · 41 tokens per session scan A abb4049e455a

Subscribe to this mod's changes

idea-refine is a skill published in the GitHub repository GuillemRoca/agent-skills-android (2 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 900 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

spec-kitty-mission-system

Understand how Spec Kitty missions work: the 4 built-in mission types, how they define workflows via step contracts and action indices, how missions and work packages relate, how templates are resolved through the 6-tier chain, and how doctrine artifacts (procedures, tactics, directives) compose mission behavior.…

Priivacy-ai/spec-kitty · 160 tokens

spec-kitty-git-workflow

Understand how Spec Kitty manages git: what git operations Python handles automatically, what agents must do manually, worktree lifecycle, auto-commit behavior, merge execution, and the safe-commit pattern. Triggers: "how does spec-kitty use git", "worktree management", "auto-commit", "who commits what", "git…

Priivacy-ai/spec-kitty · 125 tokens

spec-kitty-spdd-reasons

Drive REASONS Canvas authoring and review for Spec Kitty missions that opted in to Structured-Prompt-Driven Development (SPDD) via charter selection. Triggers: "use SPDD", "use REASONS", "generate a REASONS canvas", "apply structured prompt driven development", "make this mission SPDD". Does NOT handle: enforcing SPDD…

Priivacy-ai/spec-kitty · 118 tokens

spec-kitty-runtime-review

Review runtime-owned outputs using the Spec Kitty review workflow surface, then direct approval or rejection with structured feedback. Triggers: "review this work package", "check runtime output", "approve this step", "review WP", "is this WP ready to approve", "check this implementation". Does NOT handle: setup-only…

Priivacy-ai/spec-kitty · 85 tokens

spk-doctrine-show-me

Explain Spec Kitty work with compact, checkable visuals. Use for specs, plans, architecture, control flow, diffs, status boards, or whenever prose obscures structure.

Priivacy-ai/spec-kitty · 42 tokens

spk-admin-dashboard

Open or report the Spec Kitty dashboard. Use for dashboard URL, localhost daemon metadata in .kittify/.dashboard, --open, --kill, or status views.

Priivacy-ai/spec-kitty · 39 tokens