Skip to content
Agentmart
Submit a tool

ideas

Offer evidence-backed improvement options without changing code or inventing a backlog.

Skill by ItsLucky23

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/itslucky23-ideas

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Offer evidence-backed improvement options without changing code or inventing a backlog.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/ideas

What's inside

Skill name
ideas
Description
Offer evidence-backed improvement options without changing code or inventing a backlog.
License
MIT
Instructions
12 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Improvement options

This is a proposal session, not implementation. Keep it write-free unless the user explicitly requests a scan artifact or chooses an action.

1. Query relevant capabilities/routes/decisions and inspect recent history for the requested area. Do not load every index or assume an unlisted package exists.
2. Inspect promising gaps directly: missing business tests, duplicate capabilities, weak access policy, user friction or measured performance trouble. Names, missing exports and TODOs are leads, not defects by themselves.
3. Present a short finite list with source/evidence pointers, benefit, rough effort, risk and recommended priority. Separate confirmed problems from hypotheses.
4. Change nothing until the user selects scope. Do not turn discussed alternatives into accepted decisions, findings or new skills.

Use `AGENTS.md` capture and package-recommendation policy. Effort estimates are uncertainty-bearing advice, not commitments.

From ItsLucky23/LuckyStack-v2, MIT.

More from ItsLucky23/LuckyStack-v2

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Oct 13, 2026 (15 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ItsLucky23

Cite this page

ideas skill. Agent Mart. https://agentmart.dev/skills/itslucky23-ideas (last updated 2026-10-24)