agentleFS
TheArchitectitTheArchitectit/awesome-cline-skills/template/SKILL.md

your-skill-name

Skill8 starsChanged 3 months agoApache-2.0View on GitHub

Clear description of what this skill does and when Cline should use it. This skill should be used when [specific trigger conditions] for [key capabilities]. Max 1024 characters.

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 26 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When [specific trigger condition 1]

    line 12
  2. Distinctive:

    When you need [key capability]

    line 15
  3. Distinctive:

    Before executing, evaluate the request:

    line 21
  4. Distinctive:

    After execution, verify the output:

    line 38
  5. Distinctive:

    If something goes wrong:

    line 85
  6. Very specific:

    Progressive loading: Only metadata loads initially.

    line 96

“Common” is measured: kept by at least 6 in 10 of the 26 edited versions of this file we could read. “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

Your Skill Name

Brief overview of the skill's purpose and capabilities. Explain what Cline can accomplish with this skill and why it exists.

When to Use This Skill

  • When [specific trigger condition 1]
  • When [specific trigger condition 2]
  • When [specific trigger condition 3]
  • When you need [key capability]

Instructions

Step 1: Initial Assessment

Before executing, evaluate the request:

  • Confirm the task matches this skill's scope
  • Check for prerequisites (tools, packages, access)
  • Identify any constraints or special requirements

Step 2: Execution

[Detailed instructions for Cline on how to execute the skill. Be specific about: ]

  • What tools or commands to use
  • What order to follow
  • What output format to produce
  • How to handle variations in the request

Step 3: Validation

After execution, verify the output:

  • Output matches the expected format
  • Content is accurate and complete
  • No errors or warnings remain
  • User's original request is fully addressed

Best Practices

  • Best practice 1: [Specific, actionable guidance]
  • Best practice 2: [Specific, actionable guidance]
  • Best practice 3: [Specific, actionable guidance]

Common Pitfalls

  • Pitfall 1: [Description] → [How to avoid or fix]
  • Pitfall 2: [Description] → [How to avoid or fix]
  • Pitfall 3: [Description] → [How to avoid or fix]

Examples

Example 1: [Descriptive Title]

Input:

User asks: "[example user request]"

Output:

[What Cline should produce]

Example 2: [Descriptive Title]

Input:

User asks: "[example user request]"

Output:

[What Cline should produce]

Error Handling

If something goes wrong:

  1. Missing prerequisites: Inform the user what needs to be installed and provide the installation command
  2. Invalid input: Explain what valid input looks like and provide an example
  3. Partial failure: Complete what's possible and clearly document what failed and why
  4. Unexpected output: Describe the discrepancy and suggest next steps

Cline Workflow Notes

  1. Install location: Copy this skill directory to .cline/skills/your-skill-name/ (project-level) or ~/.cline/skills/your-skill-name/ (global)
  2. Activation: Cline will suggest this skill when you [describe trigger conditions]
  3. Progressive loading: Only metadata loads initially; full instructions activate via use_skill when needed

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.