agentleFS
MoizIbnYousafMoizIbnYousaf/Ai-Agent-Skills/skills/install-from-remote-library/SKILL.md

install-from-remote-library

Skill1.1k starsChanged 8 months agoMITView on GitHub

Use when installing skills from a shared ai-agent-skills library repo. Inspect with `--list` first, prefer `--collection`, and preview with `--dry-run` before installing.

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 5 are distinctive, and 7 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.

  • 7

    Very specific

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

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

    Always inspect the remote library first with install <source> --list.

    line 16
  2. Very specific:

    Prefer --collection when the library clearly exposes a starter pack or focused bundle.

    line 17
  3. Very specific:

    Always run --dry-run before the real install.

    line 18
  4. Distinctive:

    Keep the install small. Do not pull a whole library when the user only needs a narrow slice.

    line 19
  5. Very specific:

    Prefer --collection starter-pack or another named collection when it matches the user's need.

    line 31
  6. Very specific:

    Use --skill <name> only when the user needs one specific skill or the library has no useful collection.

    line 32
  7. Very specific:

    Do not combine --collection and --skill.

    line 33
  8. Distinctive:

    If the plan looks right, run the real install with the same scope.

    line 47
  9. Distinctive:

    If the library has a curated collection that already matches the user's stack, use it.

    line 55
  10. Distinctive:

    If the remote library is empty or the list output is unclear, stop and report that instead of guessing.

    line 56
  11. Very specific:

    If the install path throws an ERROR / HINT, surface that verbatim and follow the hint before retrying.

    line 57
  12. Distinctive:

    If the user is exploring a large library, keep them in browse mode first rather than installing immediately.

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Install From Remote Library

Goal

Install from a shared library repo without guessing, over-installing, or skipping the preview step.

Invariants

  • Always inspect the remote library first with install <source> --list.
  • Prefer --collection when the library clearly exposes a starter pack or focused bundle.
  • Always run --dry-run before the real install.
  • Keep the install small. Do not pull a whole library when the user only needs a narrow slice.

Workflow

  1. Inspect the source library.
npx ai-agent-skills install <owner>/<repo> --list
  1. Choose the smallest fitting target.
  • Prefer --collection starter-pack or another named collection when it matches the user's need.
  • Use --skill <name> only when the user needs one specific skill or the library has no useful collection.
  • Do not combine --collection and --skill.
  1. Preview the install plan before mutating anything.
npx ai-agent-skills install <owner>/<repo> --collection starter-pack --dry-run -p

or

npx ai-agent-skills install <owner>/<repo> --skill <skill-name> --dry-run -p
  1. If the plan looks right, run the real install with the same scope.
npx ai-agent-skills install <owner>/<repo> --collection starter-pack -p

Decision Rules

  • If the library has a curated collection that already matches the user's stack, use it.
  • If the remote library is empty or the list output is unclear, stop and report that instead of guessing.
  • If the install path throws an ERROR / HINT, surface that verbatim and follow the hint before retrying.
  • If the user is exploring a large library, keep them in browse mode first rather than installing immediately.

Done

Return:

  • what source library you inspected
  • which collection or skill you chose
  • the dry-run result
  • the exact final install command you used

Download now (ZIP)

Trending

More talk lately.thin dataabout the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 1 mentionOct 2026: 3 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the MoizIbnYousaf/Ai-Agent-Skills repository that our weekly crawl found: only 4 in all, so this is a hint, not a trend. There is no adoption data for this file yet.

Does it work?

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

Reviews can't be read right now.

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.