agentsclimarketplace

Skill template

Skill easyzoom/aix-skills/template/skill-template

Use when an agent needs to perform a specific repeatable task in a specific contextFrom its SKILL.md

Install
npx -y skills add easyzoom/aix-skills --skill skill-template

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 24 stars24 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.2 KB, 428 tokens by cl100k_base, as published. Nobody here has run it

Skill Name

Overview

State the core purpose in one or two sentences. Explain what this skill helps an agent do, without turning the overview into a long tutorial.

When To Use

Use this skill when:

  • The task matches a repeatable workflow.
  • The agent needs domain-specific constraints, tool order, or verification rules.
  • The expected output has a recognizable quality bar.

Do not use this skill when:

  • The task is a one-off note.
  • The behavior is better enforced by code, linting, or a script.
  • General documentation already covers the need clearly.

First Questions

Ask for the minimum inputs the workflow depends on, for example:

  • The target library, tool, chip, or protocol version in play.
  • The runtime context (bare-metal or RTOS) and relevant config files.
  • The exact command, error code, or symptom being investigated.

Workflow

Name this section for the task shape: Integration Checklist for library integration skills, Debug Workflow for debugging skills, or keep Workflow for anything else.

  1. Gather the minimum context needed for the task.
  2. Follow the domain-specific steps in order.
  3. Stop and ask for clarification if required inputs are missing.
  4. Verify the result with the checks below.

Common Failures

  • Writing a broad essay instead of operational guidance.
  • Making the description summarize the workflow instead of trigger conditions.
  • Adding too many examples instead of one strong example.
  • Forgetting verification, which makes the skill hard to trust.

Verification

Before claiming completion:

  • Confirm the expected artifact exists.
  • Confirm the output matches the user's request.
  • Run the relevant command, checklist, or manual inspection step.
  • Report any limitation or skipped check.

Example

User: "Create a release note from these commits."

Agent:

  1. Loads the release-note skill because the task is a repeatable writing workflow.
  2. Collects commit messages and user-facing changes.
  3. Drafts the release note in the required format.
  4. Checks that the note avoids internal-only implementation details.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.