partner-affiliate
When the user wants to build a partner program, launch an affiliate program, design integration partnerships, or create distribution partnerships. Also use when the user mentions 'partnerships,' 'affiliate program,' 'referral program,' 'partner ecosystem,' 'integration partner,' 'reseller,' 'co-marketing,' 'PartnerStack,' or 'revenue share.' This skill covers partner and affiliate program design from recruitment through performance optimization. Do NOT use for technical implementation, code review, or software architecture.
81
76%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./packages/skills-catalog/skills/(gtm)/partner-affiliate/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description with excellent trigger term coverage and clear 'when to use' guidance, including helpful negative boundaries. The main weakness is that the 'what it does' portion could be more specific about concrete actions (e.g., 'design commission structures, create partner onboarding flows, optimize partner performance metrics') rather than summarizing broadly as 'from recruitment through performance optimization.'
Suggestions
Replace the broad summary 'partner and affiliate program design from recruitment through performance optimization' with a list of specific concrete actions, e.g., 'design commission structures, create partner tiers, build onboarding workflows, define referral tracking, optimize partner performance metrics.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (partner/affiliate programs) and mentions some actions like 'build,' 'launch,' 'design,' and 'create,' but the core capability statement ('covers partner and affiliate program design from recruitment through performance optimization') is fairly broad rather than listing multiple specific concrete actions. | 2 / 3 |
Completeness | Clearly answers both 'what' (partner and affiliate program design from recruitment through performance optimization) and 'when' (explicit trigger terms and use-case scenarios listed). Also includes a helpful negative boundary ('Do NOT use for technical implementation, code review, or software architecture'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'partnerships,' 'affiliate program,' 'referral program,' 'partner ecosystem,' 'integration partner,' 'reseller,' 'co-marketing,' 'PartnerStack,' 'revenue share.' These are terms users would naturally use when seeking help with partnership programs. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche around partnership and affiliate program design with highly specific trigger terms like 'PartnerStack,' 'reseller,' 'co-marketing,' and 'revenue share.' The explicit exclusion of technical implementation further reduces conflict risk with engineering-focused skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured skill with excellent concrete guidance (specific percentages, timelines, scoring models, platform recommendations). However, it is significantly over-verbose—it includes explanatory context Claude doesn't need (e.g., why integration partnerships matter, what co-creation means) and could be 40-50% shorter without losing any actionable content. The progressive disclosure is decent but the main file carries too much detail that should be in reference files.
Suggestions
Remove explanatory/contextual paragraphs that describe industry trends Claude doesn't need (e.g., 'The partner landscape has shifted decisively...', 'Integration partnerships have become the fastest-growing...'). These waste tokens without adding actionable guidance.
Move the detailed commission structures table, clawback policies table, and platform comparison table to `references/implementation-guide.md` or a dedicated `references/compensation-structures.md`, keeping only the tier summary and key decision points in the main skill.
Condense the 'Before Starting' section into a compact checklist format rather than full sentences—e.g., '- Product: core capability, primary use case' instead of 'What is the current product? Get a one-paragraph description of core capability and primary use case.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. It explains concepts Claude already knows (what co-creation ecosystems are, why integration partnerships win), includes lengthy philosophical context ('The partner landscape has shifted decisively'), and has massive tables that could be condensed significantly. The Section 4 intro paragraph about why integration partnerships win is pure filler. | 1 / 3 |
Actionability | The content provides highly specific, concrete guidance: exact commission percentages by tier and revenue model, specific platform recommendations with pricing, a detailed launch checklist with day-by-day timelines, a scoring model with exact weights and point values for integration prioritization, and clear decision trees. This is copy-paste ready for program design. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit timelines: the affiliate launch checklist has week-by-week actions, the integration partner onboarding has a clear 4-step process with week ranges, and the platform decision tree provides clear branching logic. Validation checkpoints exist (Month 2 analysis, QA testing with beta customers, monthly partner syncs). | 3 / 3 |
Progressive Disclosure | The skill references external files (`references/implementation-guide.md` and `references/quick-reference.md`) which is good, but the main file itself is a wall of content that could benefit from more aggressive splitting. The model comparison tables, full commission structures, and platform selection details could live in reference files, keeping the SKILL.md as a leaner overview. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- tech-leads-club/agent-skills
- Commit
906a57d
- 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.