Install any skill in seconds. Free to start, no credit card required.
Get Started Free →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.
.claude/skills/affitor-your-skill-name/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 81% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 55% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 86% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 109% | 0% |
What this skill does in 2-3 sentences. Focus on the outcome, not the process.
This skill belongs to Stage SX: StageName
{
required_field: { # (required) Description
name: string # Example value
}
optional_field: string # (optional, default: "value") Description
}What to check first. How to handle missing inputs.
The main work the skill does.
How to structure the output.
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
}## [Skill Name]: [Context]
### Section 1
[Main content]
### Section 2
[Supporting content]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]
[skill] (SX]) — what data/output flows forward to this skill][skill] (SX]) — what data/output flows back from this skill]> Include this section for content-producing skills (S2, S3, S4, S5, S7). Remove for non-content skills.
Before delivering output, verify:
Any NO → rewrite before delivering. Do not flag this checklist to the user.
> Include this section for S2 Content skills only. Remove for other stages.
When mode: "volume":
yamlvolume_output: variants: - id: string # e.g., "v1", "v2" content: string # The variation angle: string # What makes this one different
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:
Auto-detect triggers for this skill:
Report issues: GitHub Issues | Discussions
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 systemOther measured skills in the registry, with their headline benchmark lift.