Skills Explorer Add Skills

idea-refine

An agent skill by addyosmani, from addyosmani/agent-skills. Tags: design, documents.

What it does

Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or "stress-test my plan".

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add addyosmani/agent-skills --skill idea-refine

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/addyosmani/agent-skills
cp -r agent-skills/skills/idea-refine ~/.claude/skills/idea-refine

Safety box score

Grade A, minimal risk: 7 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a mostly read-only ideation skill with one tiny setup script that creates `docs/ideas` inside the working tree. The main exposure is low: it can write a markdown one-pager in the repo after confirmation, but it does not download code, access secrets, or require elevated privileges.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution1 (low)The shipped script `scripts/idea-refine.sh` is executable shell and runs `mkdir -p` to initialize the ideas directory.
Network access0 (none)No file contains network access, downloads, or remote posting; the skill is offline and conversational.
Filesystem reach1 (low)The only explicit write path is `docs/ideas` in the project tree, created by `mkdir -p "$IDEAS_DIR"` and used for the final markdown one-pager.
Secrets & credentials0 (none)The skill does not read or request tokens, passwords, `.env` files, keychains, or browser sessions.
Privilege & persistence0 (none)No sudo, global installs, services, shell profile edits, or OS-level changes are present.
Instruction hijack surface0 (none)The instructions are workflow guidance for ideation; there is no text telling the agent to ignore higher-priority rules, hide behavior, or follow remote instructions.
Irreversible actions0 (none)The skill only facilitates discussion and optionally saves a file after user confirmation; it does not publish, deploy, message, or delete anything.
Transparency0 (none)All shipped files are readable markdown or a short shell script; no binaries, encoded payloads, or generated-at-runtime code are present.

Before installing

Rated 2026-10-20 by an automated review of 5 files from the skill's repository.

Source

Repository
addyosmani/agent-skills (all skills from this repository)
Path
skills/idea-refine/SKILL.md
Branch
main
Updated
2026-09-19