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

pilot

Skill2 starsChanged 31 days agoApache-2.0View on GitHub

Route surface 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

2 rules. 0 are common, 0 are distinctive, and 2 are 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.

  • 2

    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
  2. Very specific:

    Use livery for a coherent visual direction and atelier lenses for a specific visual dimension.

    line 43

“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 surface 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
bearingsheuristicExplore frontend architecture by reframing journeys, ownership, and the experience of time.
bulwarksopMaintain frontend module boundaries and reusable design artifacts with demonstrable checks.
keelsopBuild a walking skeleton for one selected frontend journey across real integration seams.
liveryheuristicExplore coherent visual directions across colour, type, space, form, imagery, and motion.
lookoutsopEstablish delivery observation and decision-linked frontend telemetry for a chosen release.
seaworthysopHarden a selected frontend journey across async states, recovery, accessibility, and performance constraints.
trialssopBuild frontend regression tests that observe real user behaviour and survive implementation refactors.
wellspringheuristicGenerate alternatives for frontend state and interaction models using ownership, time, and representation shifts.

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.

Use livery for a coherent visual direction and atelier lenses for a specific visual dimension. keel is a walking skeleton across integration seams, not a destination for routine CSS questions. bearings and wellspring explore alternatives; neither is an obligatory prerequisite.

Suite map.

Optional handoffs, not a pipeline.

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.