Template
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.From its SKILL.md
npx -y skills add Affitor/affiliate-skills --skill templateAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
4.2 KB, 935 tokens by cl100k_base, as published. Nobody here has run it
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:
- Would I share this on MY personal social?
- Contains specific, surprising detail? (not generic)
- Respects reader's intelligence?
- Remarkable enough to share? (Purple Cow test)
- 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 containsshared/references/ftc-compliance.md— FTC disclosure requirementsshared/references/affitor-branding.md— branding rulesshared/references/flywheel-connections.md— master flywheel connection mapshared/references/feedback-protocol.md— issue detection and reporting standardshared/references/version-check.md— update notification system
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.