agentleFS
Sign inStart free
fabioc-alohafabioc-aloha/Alex_ACT_ONE/skills/install-visual-companions/SKILL.md

install-visual-companions

Skill0 starsChanged 9 days agoMITView on GitHub

Offer to install marketplace plugins that extend visual-authoring workflows: chart rendering, screenshot verification, whiteboard iteration, and PR annotation. Consent-gated, one plugin at a time, never bundled without explicit approval. Use when the user asks to enable visual-workflow tooling, or when chart, figure, or print-SVG authoring produces artifacts that need runtime verification.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use native capability discovery first.

    line 9
  2. Distinctive:

    Use supported native marketplace/plugin commands for discovery and lifecycle.

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Visual Companion Setup

Use native capability discovery first. A visual task does not itself justify installing a browser, screenshot auditor, renderer, or plugin. If the active host covers the requested scenario, use it; retain registered fallbacks for unavailable or unverified cases.

For a real remaining gap, load the relevant catalog entry and consent procedure in execution details. Catalog verification dates are historical evidence: verify the current plugin name, publisher, marketplace, dependencies, and scope before offering installation.

Offer only applicable choices. Require explicit consent for each integration and its installation scope; no answer means no action. Never install a bundle silently or treat missing optional companions as a broken Core installation.

Use supported native marketplace/plugin commands for discovery and lifecycle. Do not modify global settings or registration without their own consent. Confirm actual tool/resource availability after installation; a successful install does not prove a rendered result is correct.

Return what was available, the concrete gap, approved actions, observed readiness, and any remaining setup. Existing framing, chart interpretation, and render verification require no extra companion when their native prerequisites are already satisfied.

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.

Check your setup, free