Affiliate Program Search

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

openaffiliate.dev is a public, open API — no API key, no authentication, no rate limits, no free-tier restrictions.

Audit 0.4.1 · source sha 2515ce9634da · 15 Oct 2026Report an issue or request a re-scan

• PublisherAffitor GitHub organizationOwner of the repository this skill is read from
• Source folderAffitor/affiliate-skills/skills/research/affiliate-program-searchThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdict2515ce9634daA new audit runs when the source changes
• Repository statusNot archivedLast push 2 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Research and evaluate affiliate programs to find the best ones to promote. Use this skill when the user asks anything about finding affiliate programs, comparing commission rates, evaluating affiliate opportunities,…

---
name: affiliate-program-search
description: >
  Research and evaluate affiliate programs to find the best ones to promote.
  Use this skill when the user asks anything about finding affiliate programs,
  comparing commission rates, evaluating affiliate opportunities, searching for
  products to promote, picking a niche, or mentions openaffiliate.dev.
  Also trigger for: "which SaaS should I promote", "best affiliate programs for X",
  "high commission programs", "recurring commission affiliate", "compare these
  affiliate programs", "is X affiliate program worth it", "find me something to promote",
  "what pays the most", "affiliate programs with long cookie duration".
license: MIT
version: "1.0.0"
tags: ["affiliate-marketing", "research", "niche-analysis", "program-discovery", "saas", "commission"]
compatibility: "Claude Code, ChatGPT, Gemini CLI, Cursor, Windsurf, OpenClaw, any AI agent"
metadata:
  author: affitor
  version: "1.0"
  stage: S1-Research
---

# Affiliate Program Search

Help affiliate marketers research, evaluate, and pick winning programs to promote.
Data source: [openaffiliate.dev](https://openaffiliate.dev/?utm_source=affiliate-skills) — open affiliate program directory. Public API, no key required.

## Stage

This skill belongs to Stage S1: Research

## When to Use

- User wants to find affiliate programs to promote
- User wants to compare two or more affiliate programs
- User asks about commission rates, cookie duration, or earning potential
- User mentions openaffiliate.dev
- User is new to affiliate marketing and needs a starting point

## Input Schema

```
{
  niche: string             # (optional, default: "AI/SaaS tools") Category or niche interest
  commission_pref: string   # (optional, default: "recurring, 20%+") Commission preference
  audience: string          # (optional, default: "content creators") Target audience type
  platform: string          # (optional, default: "any") Platform they'll promote on
  compare: string[]         # (optional) Specific programs to compare head-to-head
}
```

## Workflow

### Step 1: Understand What the User Wants

Ask (if not clear from context):
- Niche/category interest? (AI tools, SEO, video, writing, automation...)
- Commission preference? (recurring vs one-time, minimum %)
- Audience type? (developers, marketers, beginners, enterprise...)
- Platform they'll promote on? (blog, LinkedIn, YouTube, X...)

If user says "just find me something good" → default to: AI/SaaS tools, recurring commission, 20%+, content creator audience.

### Step 2: Search openaffiliate.dev

See `references/openaffiliate-api.md` for integration methods.

Two methods available:
- **API (preferred):** `GET https://openaffiliate.dev/api/programs?q=<term>&utm_source=affiliate-skills` — public, no auth needed, structured data
- **Web fetch (fallback):** `web_search "site:openaffiliate.dev [category]"` then `web_fetch` the page

Extract for each program: `name`, `reward_value`, `reward_type`, `cookie_days`, `stars_count`, `tags`, `description`.

### Step 3: Score Programs

Apply the scoring framework from `references/scoring-criteria.md`.

Score each program on 5 dimensions (1-10 scale):
1. **Earning Potential** (30%) — commission %, recurring vs one-time, product price
2. **Content Potential** (25%) — visual demo, free tier, content angles
3. **Market Demand** (20%) — search volume, trend direction, market size
4. **Competition Level** (15%) — fewer affiliates promoting = higher score
5. **Trust Factor** (10%) — product quality, reputation, stars on openaffiliate.dev

Overall = weighted average. Verdict: 7.5+ "Strong Pick" / 5.5-7.4 "Worth Testing" / <5.5 "Skip".

For dimensions that require external data (Market Demand, Competition Level), use `web_search` to check Google results count for "[product] review" and "[product] affiliate" queries.

### Step 4: Present Recommendation

### Step 5: Self-Validation

Before presenting output, verify:

- [ ] All scored programs have `reward_value` from API data, not hallucinated
- [ ] `cookie_days` is numeric and from API response
- [ ] Top Pick verdict matches score threshold (≥7.5 = Strong Pick, ≥6 = Worth Considering)
- [ ] Market Demand and Competition scores cite the search query used
- [ ] Stale data (>6 months) is flagged with warning

If any check fails, fix the output before delivering. Do not flag the checklist to the user — just ensure the output passes.

## Output Schema

Other skills (viral-post-writer, affiliate-blog-builder, etc.) consume these fields from conversation context:

```
{
  output_schema_version: "1.0.0"  # Semver — bump major on breaking changes
  recommended_program: {
    name: string              # "HeyGen"
    slug: string              # "heygen"
    reward_value: string      # "30%"
    reward_type: string       # "cps_recurring"
    reward_duration: string   # "12 months"
    cookie_days: number       # 60
    description: string       # Short product description
    tags: string[]            # ["ai", "video"]
    url: string               # Product website
  }
  score: {
    overall: number           # 8.2
    verdict: string           # "Strong Pick"
    reasoning: string         # Why this is the top pick
  }
  runner_up: Program | null   # Same structure, second choice
  all_scored: ProgramScore[]  # Full list of scored programs
}
```

## Output Format

```
## Programs Found

| Program | Commission | Type | Cookie | Stars | Score |
|---------|-----------|------|--------|-------|-------|
| HeyGen  | 30%       | Recurring | 60d | ⭐ 42 | 8.2/10 |
| ...     | ...       | ...  | ...    | ...   | .../10 |

## Top Pick: [Program Name]

**Why:** [2-3 sentences explaining why this is the best fit]

| Dimension | Score | Note |
|-----------|-------|------|
| Earning Potential | 8/10 | 30% recurring on $24-48/mo |
| Content Potential | 9/10 | Visual AI video, easy to demo |
| Market Demand | 8/10 | AI video trending, high search volume |
| Competition | 6/10 | Growing number of

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

1. 2026-10-15
   ✓SAFE B 89 / 100

   first audit · source 2515ce9634da

Questions about Affiliate Program Search

• github.com/Affitor/affiliate-skills/tree/main/skills/research/af — the audited source at commit 2515ce9634da and every finding aboveObserved · 15 Oct 2026

Spotted something wrong? Report a correction · Methodology