agentleFS
nledfordnledford/engineering-review-board/skills/suggest-lucide-icons/SKILL.md

suggest-lucide-icons

Skill11 starsChanged 14 days agoMITView on GitHub

Pick real Lucide icons for a concept, UI placement, button, section header, or note frontmatter. Use when the user asks what Lucide icon to use, requests icon candidates, or needs an icon name verified. Do not use for non-Lucide icon libraries or general icon or artwork design.

2 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

9 rules. About 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to choose existing Lucide icon names, not to invent symbolic artwork.

    line 8
  2. Very specific:

    When the project uses Lucide, inspect its manifest, lockfile-resolved version, and installed package first.

    line 13
  3. Distinctive:

    Verify candidates against installed, lockfile-resolved, or exact-version package assets.

    line 18
  4. Distinctive:

    If verification is blocked by network or tooling, say that candidates are unverified and do not present them as confirmed.

    line 28
  5. Very specific:

    Use kebab-case: arrow-up, not Arrow Up.

    line 33
  6. Very specific:

    Use Lucide's American English names: color, not colour.

    line 34
  7. Distinctive:

    Prefer icons whose visual metaphor works without explanation.

    line 43
  8. Very specific:

    Prefer action icons for commands (save, download, trash-2) and object or state icons for labels (database, shield-check, file-warning).

    line 46
  9. Distinctive:

    Avoid novelty when a conventional icon exists.

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Suggest Lucide Icons

Use this skill to choose existing Lucide icon names, not to invent symbolic artwork. Optimize for recognizable meaning in the user's context.

Workflow

  1. When the project uses Lucide, inspect its manifest, lockfile-resolved version, and installed package first. Prefer installed assets or exact-version package assets as proof; @latest is not proof of project compatibility.
  2. Identify the concept, action, object, state, and UI placement.
  3. Generate 4-6 plausible Lucide icon names in kebab-case.
  4. Verify candidates against installed, lockfile-resolved, or exact-version package assets. If no project version exists, confirm the icon through the official current package metadata or release, the current upstream package, or https://lucide.dev/icons/<icon-name>. Consult current official framework integration documentation when needed, not as sole proof of icon existence or version.
  5. Discard names that cannot be verified.
  6. Present up to 3 confirmed candidates and recommend one, stating the verification source and version.

If verification is blocked by network or tooling, say that candidates are unverified and do not present them as confirmed.

Naming Rules

  • Use kebab-case: arrow-up, not Arrow Up.
  • Use Lucide's American English names: color, not colour.
  • For grouped variants, use the icon family first: badge-plus.
  • For multiple elements, lead with the larger or containing element: circle-user, square-arrow-out-up-right.
  • For modifiers, put the base object first: circle-dashed, not dashed-circle.

Selection Rules

  • Prefer icons whose visual metaphor works without explanation.
  • Match the placement: toolbar actions need simpler shapes than navigation or section icons.
  • Prefer action icons for commands (save, download, trash-2) and object or state icons for labels (database, shield-check, file-warning).
  • Avoid novelty when a conventional icon exists.
  • For multiple requested icons, choose a visually coherent set with similar density and stroke complexity.

Output

Candidates
- icon-name: why it fits
- icon-name: why it fits
- icon-name: why it fits

Recommendation: icon-name
Reason: ...
Verification: ...

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.