CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

referrals

When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use when the user mentions 'referral,' 'affiliate,' 'ambassador,' 'word of mouth,' 'viral loop,' 'refer a friend,' 'partner program,' 'referral incentive,' 'how to get referrals,' 'customers referring customers,' or 'affiliate payout.' Use this whenever someone wants existing users or partners to bring in new customers. For launch-specific virality, see launch.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable marketing skill body with excellent progressive disclosure — real, clearly signaled reference files and no nested indirection. Its main weakness is token efficiency: several sections restate basic marketing concepts that could be cut or pushed to the reference files. Workflow sequencing and checklists are solid though not at the level of explicit validation feedback loops.

Suggestions

Trim or move the 'Referral vs. Affiliate' characteristics comparison into a reference file — the 'Best for' and 'Characteristics' bullets largely restate knowledge Claude already has.

Cut the roleplay opener ('You are an expert in viral growth...') and generic bullets like 'Ask at better moments,' replacing them with the specific tactics already present in the reference files.

Consider moving the email sequence templates and/or the full tool-integration table into a reference file so the SKILL.md body stays a lean overview, consistent with the existing split of examples and affiliate detail.

DimensionReasoningScore

Conciseness

Formatting is efficient (tables, checklists, terse bullets), but sections like 'Referral vs. Affiliate' characteristics ('Referrer is an existing customer,' 'Higher trust, lower volume') and 'High-intent moments' re-explain basic marketing concepts Claude already knows. Fits 'mostly efficient but includes some unnecessary explanation or could be tightened' — above 2 (not heavily padded) but below 4 (the conceptual comparison section is clearly trimmable).

3 / 5

Actionability

For an instruction-only skill the guidance is concrete: share mechanisms ranked by effectiveness, specific incentive structures, named A/B test variables, a problem→fix table, email templates with placeholders, and benchmark figures ('16-25% higher LTV'). Not a 5 because some directives remain directional ('Ask at better moments,' 'Improve landing experience') without the specificity of the copy-paste-ready 5 anchor.

4 / 5

Workflow Clarity

Clear end-to-end sequence: context gathering → program-type decision → design (Steps 1-3) → optimization → measurement → phased launch checklists, with checkpoint items ('Test complete referral flow,' post-launch 'Review conversion funnel,' 'Fix friction points'). Below 5 because validation is checklist-based rather than explicit validate→fix→retry feedback loops; above 3 because checkpoints are present and sequenced.

4 / 5

Progressive Disclosure

Clean overview structure with well-signaled, one-level-deep references that exist in the bundle: 'See [references/program-examples.md](references/program-examples.md)' and 'See [references/affiliate-programs.md](references/affiliate-programs.md)' — both real files with no nested references. Content split is appropriate (examples and affiliate detail out of the main file), matching the 5 anchor.

5 / 5

Total

16

/

20

Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states capabilities, exhaustively lists natural trigger phrases, and explicitly scopes both what and when. The explicit boundary pointer to the 'launch' skill is a particular strength for conflict avoidance. Only minor room to broaden the action verbs for full comprehensiveness.

DimensionReasoningScore

Specificity

Names three concrete actions ('create, optimize, or analyze') across the referral/affiliate domain, matching the 'several specific actions; minor gaps' anchor. Not a 5 because coverage is slightly thin — actions like 'design' or 'launch' are absent (launch is delegated to another skill), unlike the comprehensive multi-action 5 anchor.

4 / 5

Completeness

Explicitly answers both questions: what ('create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy') and when ('Also use when the user mentions... or... Use this whenever someone wants existing users or partners to bring in new customers') with concrete trigger phrases. Matches the 5 anchor exactly; the 4 anchor's 'when could be more explicit' criticism does not apply.

5 / 5

Trigger Term Quality

Comprehensive natural-language triggers: 'referral,' 'affiliate,' 'ambassador,' 'word of mouth,' 'viral loop,' 'refer a friend,' 'partner program,' 'referral incentive,' 'how to get referrals,' 'customers referring customers,' 'affiliate payout' — these are exactly the phrases a user would naturally say, with synonym coverage. Re-reading the 4 anchor ('a few natural terms missing') confirms nothing significant is missing.

5 / 5

Distinctiveness Conflict Risk

Clear niche (user/partner-driven acquisition) with distinct trigger vocabulary and an explicit de-confliction boundary ('For launch-specific virality, see launch'). Minor overlap potential with partner-management skills via 'partner program' is not enough to drop below the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 8 suspicious

Warning

Total

15

/

16

Passed

Repository

joshmanders/dotfiles

Path

claude/skills/referrals/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.