agentleFS
AffitorAffitor/affiliate-skills/template/SKILL.md

your-skill-name

Skill757 starsChanged 8 months agoMITView on GitHub

Replace with when the AI should activate this skill. Be pushy — cover multiple phrasings so the AI activates for a wide range of user prompts.

49 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

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

  • 0

    Common

    Most of the 26 edited versions we read keep these.

  • 1

    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:

    Before delivering output, verify:

    line 113
  2. Very specific:

    When this skill produces unexpected, incomplete, or incorrect output, generate a skill_feedback block (see …

    line 143

“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

What this skill does in 2-3 sentences. Focus on the outcome, not the process.

Stage

This skill belongs to Stage SX: StageName

When to Use

  • Scenario 1
  • Scenario 2
  • Scenario 3

Input Schema

{
  required_field: {          # (required) Description
    name: string             # Example value
  }
  optional_field: string     # (optional, default: "value") Description
}

Workflow

Step 1: Gather Context

What to check first. How to handle missing inputs.

Step 2: Execute Core Task

The main work the skill does.

Step 3: Format and Deliver

How to structure the output.

Output Schema

Other skills can consume these fields from conversation context:

{
  primary_output: string     # Main result for downstream chaining
  secondary_output: string   # Additional data for downstream skills
}

Output Format

## [Skill Name]: [Context]

### Section 1
[Main content]

### Section 2
[Supporting content]

Error Handling

  • Missing required input: How to recover gracefully.
  • External data unavailable: Fallback strategy.
  • Edge case: How to handle unexpected scenarios.

Examples

Example 1: [realistic user prompt] → [step-by-step what the skill does] → [expected output summary]

Example 2: [different scenario] → [step-by-step] → [expected output summary]

Example 3: [edge case or beginner scenario] → [step-by-step] → [expected output summary]

Flywheel Connections

Feeds Into

  • [skill] (S[X]) — [what data/output flows forward to this skill]

Fed By

  • [skill] (S[X]) — [what data/output flows back from this skill]

Feedback Loop

  • [analytics metric or data point that improves this skill's next run]

Quality Gate

Include this section for content-producing skills (S2, S3, S4, S5, S7). Remove for non-content skills.

Before delivering output, verify:

  1. Would I share this on MY personal social?
  2. Contains specific, surprising detail? (not generic)
  3. Respects reader's intelligence?
  4. Remarkable enough to share? (Purple Cow test)
  5. Irresistible offer framing? (if S4 offer skills ran)

Any NO → rewrite before delivering. Do not flag this checklist to the user.

Volume Mode

Include this section for S2 Content skills only. Remove for other stages.

When mode: "volume":

  • Generate 5-10 variations instead of 1
  • Prioritize speed + variety over perfection
  • Tag each with variant ID for A/B tracking
  • Let data pick the winner (GaryVee philosophy)
volume_output:
  variants:
    - id: string           # e.g., "v1", "v2"
      content: string      # The variation
      angle: string        # What makes this one different

Feedback & Issue Reporting

When this skill produces unexpected, incomplete, or incorrect output, generate a skill_feedback block (see shared/references/feedback-protocol.md for full schema).

Skill-specific failure modes:

  • [Failure mode 1]: [What triggers it, what to report]
  • [Failure mode 2]: [What triggers it, what to report]

Auto-detect triggers for this skill:

  • [Specific condition that means this skill underperformed]
  • [Another condition]

Report issues: GitHub Issues | Discussions

References

  • references/your-reference.md — description of what it contains
  • shared/references/ftc-compliance.md — FTC disclosure requirements
  • shared/references/affitor-branding.md — branding rules
  • shared/references/flywheel-connections.md — master flywheel connection map
  • shared/references/feedback-protocol.md — issue detection and reporting standard
  • shared/references/version-check.md — update notification system

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.