Tooluck logoTooluck
SKILL.md

aim

Agent skill fromLilMGenius/paperthin

When data lands with a thin ask (files, a repo, a paste, a chat scrollback), read it and propose what the user is trying to do with it for them to confirm. Use the moment material arrives without a fully-formed ask, or when the ask reads thinner than the data suggests.

How to install aim

install aim
# install the paperthin pack with the skills CLI
npx skills add LilMGenius/paperthin

# or add only this skill to Claude Code: copy the folder

skills/depth/aim/

# into

~/.claude/skills/aim/ (all projects)

.claude/skills/aim/ (one project)

skills/depth/aim/SKILL.md

MITFull file
1Read the data and propose the intent behind it, for the user to confirm.
2
3## Goal
4
5Give the user a proposal to confirm, revise, or reject. Never make them compose an answer from scratch: proposing lets them answer yes to an intent they had not yet put into words. If they still have to write that intent themselves, the skill missed.
6
7## Workflow
8
91. Read every piece of the handed-over data end to end before proposing anything.
102. State the intent you read in one line grounded in what the data shows.
113. Briefly state what you would do next on that intent.
124. Ask only for confirmation: right, wrong, or adjust.
13
14## Rules
15
16- Read before proposing. A proposal without reading is a guess.
17- Ground it in the data. Point at what you read, not what you assumed.
18- One intent per turn. If two are plausible, propose the likelier and name the other in a clause.
19- Confirm, don't compose. If the turn ends with the user assembling a sentence, redo the proposal.
20- If the data is too thin to propose from, say so and stop. Do not fall back to asking.
21
22## Verification
23
24The user's next reply is short: a yes, a correction, or a small adjustment. If they had to explain what they wanted from scratch, the proposal was wrong or was a question in disguise.

Excerpt shown under the repository's MIT license.

More skills in paperthin

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

nexu-io /

open-design
107k

The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create motion, prototypes, websites, apps, dashboards, presentations, images, and videos with your team and AI agents. Share work, exchange feedback, and iterate together in one workspace.

40 skills

tt-a1i /

archify
95k

Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.

CCCXOC1 skill

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates