agentleFS
IamK77IamK77/Skill/skills/atelier/pilot/SKILL.md

pilot

Skill2 starsChanged 31 days agoApache-2.0View on GitHub

Route atelier work to an execution SOP, a creative heuristic, or a direct answer. Use when the needed kind of help is unclear; do not impose a suite-wide pipeline.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Ask a short clarifying question only if the distinction changes the work.

    line 24

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Copyright 2026 IamK77 — Licensed under the Apache License, Version 2.0. See ./LICENSE and ./NOTICE · https://www.apache.org/licenses/LICENSE-2.0 -->

pilot

Route atelier work to an execution SOP, a creative heuristic, or a direct answer. Use when the needed kind of help is unclear; do not impose a suite-wide pipeline.

Choose the kind of help

  • A chosen outcome needing steps, artifacts, and verification: suggest the smallest relevant SOP.
  • An open question, stuck framing, or desire for possibilities: suggest a heuristic. Explore rather than inspect every dimension.
  • A small factual, syntax, or local implementation question: answer directly; no skill is a valid choice.

Ask a short clarifying question only if the distinction changes the work. A router is an auxiliary entrypoint, not a third substantive skill category. It starts no run and requires no CLI to offer directions.

Map

SkillKindUse
canonheuristicGenerate visual points of view and unexpected design languages from a product’s tensions and meaning.
colorheuristicExplore palette ideas through perception, material associations, temperature, and semantic relationships.
formheuristicExplore shape, depth, light, texture, and material metaphors for an interface.
graphicsheuristicInvent imagery, iconography, illustration, and generative visual languages.
layoutheuristicInvent spatial compositions through attention, rhythm, and alternative information metaphors.
motionheuristicExplore motion as rhythm, continuity, character, and narrative.
systemssopTurn a selected visual direction into versioned tokens, reusable components, and an inspectable handoff.
typeheuristicExplore typographic voices, rhythm, and multilingual expression.

Handoff

Name the selected skill, why it fits, and the concrete input it needs. Suggest a chain only when a real artifact connects its steps. Heuristics have no completion gates and need not converge; begin an SOP only after its target is selected. Check runtime availability only when executing an SOP, not before creative exploration. Never silently install tools or reset an existing run.

The seven visual lenses are peers: begin with the interesting dimension, not necessarily canon. Only systems is an execution SOP. For ordinary CSS mechanics, answer directly; for a chosen end-to-end product journey, consider surface keel.

Suite map.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.