agentleFS
clairelily2020clairelily2020/workflow-skills/skills/workflow-install-gate/SKILL.md

workflow-install-gate

Skill1 starsChanged 3 months agoMITView on GitHub

Evaluate whether to install, update, create, or skip an external AI skill, GitHub workflow, plugin, MCP server, connector, automation, or agent package. Use when the user asks about installing a skill repo, adding a plugin, adopting a workflow framework, comparing a new tool with existing local workflows, avoiding duplicate skills, checking maintenance quality, or deciding whether to fold an idea into an existing skill. Outputs an install decision with overlap, useful delta, risk, local changes, and rollback notes.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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 this skill before installing or creating any external skill, plugin, MCP server, automation, or workflow package.

    line 10
  2. Distinctive:

    Only act when the new package has a clear advantage over the current local setup.

    line 14
  3. Distinctive:

    Search existing skills, agents, automations, scripts, docs, and memory notes.

    line 19
  4. Distinctive:

    If an existing workflow covers 70% or more of the task, update that workflow instead of installing a generic package.

    line 20
  5. Distinctive:

    Prefer actively maintained packages with concrete examples.

    line 24
  6. Distinctive:

    Do not install broad packs when only one small rule is useful.

    line 37
  7. Distinctive:

    Do not overwrite local custom workflows.

    line 38
  8. Distinctive:

    Keep a rollback note for every install or update.

    line 39

≈ “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

Workflow Install Gate

Use this skill before installing or creating any external skill, plugin, MCP server, automation, or workflow package.

Decision Rule

Only act when the new package has a clear advantage over the current local setup.

Workflow

  1. Check local overlap
    • Search existing skills, agents, automations, scripts, docs, and memory notes.
    • If an existing workflow covers 70% or more of the task, update that workflow instead of installing a generic package.
  2. Check freshness
    • Review release notes, recent commits, examples, issues, and maintenance signals.
    • Prefer actively maintained packages with concrete examples.
  3. Check real delta
    • Identify what the package improves: speed, quality, reliability, repeatability, safety, or integration coverage.
    • Reject vague benefits like "looks useful" or "popular repo."
  4. Choose the smallest action
    • Skip: duplicate, stale, irrelevant, or no clear upgrade.
    • Update existing workflow: good idea, already mostly covered locally.
    • Create focused local workflow: repeated local task with stable inputs and outputs.
    • Install: actively maintained package with a meaningful advantage.
  5. Protect the workspace
    • Do not install broad packs when only one small rule is useful.
    • Do not overwrite local custom workflows.
    • Keep a rollback note for every install or update.

Output Format

Decision: Skip / Update existing workflow / Create focused workflow / Install
Reason:
Overlap with existing tools:
Useful delta:
What changes locally:
Risk:
Rollback:

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.