affiliate-program-search

Name: affiliate-program-search
Author: Affitor

5installs184forks

How to install affiliate-program-search?

affitor/affiliate-skills/affiliate-program-search

$npx -y skills add Affitor/affiliate-skills --skill affiliate-program-search

Installs into the current project.

Summary

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

Files · 1

View on GitHub

SKILL.md

1	# Affiliate Program Search
2
3	Help affiliate marketers research, evaluate, and pick winning programs to promote.
4	Data source: [openaffiliate.dev](https://openaffiliate.dev) — open affiliate program directory. Public API, no key required.
5
6	## Stage
7
8	This skill belongs to Stage S1: Research
9
10	## When to Use
11
12	- User wants to find affiliate programs to promote
13	- User wants to compare two or more affiliate programs
14	- User asks about commission rates, cookie duration, or earning potential
15	- User mentions openaffiliate.dev
16	- User is new to affiliate marketing and needs a starting point
17
18	## Input Schema
19
20	```
21	{
22	niche: string # (optional, default: "AI/SaaS tools") Category or niche interest
23	commission_pref: string # (optional, default: "recurring, 20%+") Commission preference
24	audience: string # (optional, default: "content creators") Target audience type
25	platform: string # (optional, default: "any") Platform they'll promote on
26	compare: string[] # (optional) Specific programs to compare head-to-head
27	}
28	```
29
30	## Workflow
31
32	### Step 1: Understand What the User Wants
33
34	Ask (if not clear from context):
35	- Niche/category interest? (AI tools, SEO, video, writing, automation...)
36	- Commission preference? (recurring vs one-time, minimum %)
37	- Audience type? (developers, marketers, beginners, enterprise...)
38	- Platform they'll promote on? (blog, LinkedIn, YouTube, X...)
39
40	If user says "just find me something good" → default to: AI/SaaS tools, recurring commission, 20%+, content creator audience.
41
42	### Step 2: Search openaffiliate.dev
43
44	See `references/openaffiliate-api.md` for integration methods.
45
46	Two methods available:
47	- API (preferred): `GET https://openaffiliate.dev/api/programs?q=<term>` — public, no auth needed, structured data
48	- Web fetch (fallback): `web_search "site:openaffiliate.dev [category]"` then `web_fetch` the page
49
50	Extract for each program: `name`, `reward_value`, `reward_type`, `cookie_days`, `stars_count`, `tags`, `description`.
51
52	### Step 3: Score Programs
53
54	Apply the scoring framework from `references/scoring-criteria.md`.
55
56	Score each program on 5 dimensions (1-10 scale):
57	1. Earning Potential (30%) — commission %, recurring vs one-time, product price
58	2. Content Potential (25%) — visual demo, free tier, content angles
59	3. Market Demand (20%) — search volume, trend direction, market size
60	4. Competition Level (15%) — fewer affiliates promoting = higher score
61	5. Trust Factor (10%) — product quality, reputation, stars on openaffiliate.dev
62
63	Overall = weighted average. Verdict: 7.5+ "Strong Pick" / 5.5-7.4 "Worth Testing" / <5.5 "Skip".
64
65	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.
66
67	### Step 4: Present Recommendation
68
69	### Step 5: Self-Validation
70
71	Before presenting output, verify:
72
73	- [ ] All scored programs have `reward_value` from API data, not hallucinated
74	- [ ] `cookie_days` is numeric and from API response
75	- [ ] Top Pick verdict matches score threshold (≥7.5 = Strong Pick, ≥6 = Worth Considering)
76	- [ ] Market Demand and Competition scores cite the search query used
77	- [ ] Stale data (>6 months) is flagged with warning
78
79	If any check fails, fix the output before delivering. Do not flag the checklist to the user — just ensure the output passes.
80
81	## Output Schema
82
83	Other skills (viral-post-writer, affiliate-blog-builder, etc.) consume these fields from conversation context:
84
85	```
86	{
87	output_schema_version: "1.0.0" # Semver — bump major on breaking changes
88	recommended_program: {
89	name: string # "HeyGen"
90	slug: string # "heygen"
91	reward_value: string # "30%"
92	reward_type: string # "cps_recurring"
93	reward_duration: string # "12 months"
94	cookie_days: number # 60
95	description: string # Short product description
96	tags: string[] # ["ai", "video"]
97	url: string # Prod

People who liked this also viewed

6 picks

Type

affiliate-program-search

5installs184forks

View on GitHub

How to install affiliate-program-search?

affitor/affiliate-skills/affiliate-program-search

$npx -y skills add Affitor/affiliate-skills --skill affiliate-program-search

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Affiliate Program Search
2
3	Help affiliate marketers research, evaluate, and pick winning programs to promote.
4	Data source: [openaffiliate.dev](https://openaffiliate.dev) — open affiliate program directory. Public API, no key required.
5
6	## Stage
7
8	This skill belongs to Stage S1: Research
9
10	## When to Use
11
12	- User wants to find affiliate programs to promote
13	- User wants to compare two or more affiliate programs
14	- User asks about commission rates, cookie duration, or earning potential
15	- User mentions openaffiliate.dev
16	- User is new to affiliate marketing and needs a starting point
17
18	## Input Schema
19
20	```
21	{
22	niche: string # (optional, default: "AI/SaaS tools") Category or niche interest
23	commission_pref: string # (optional, default: "recurring, 20%+") Commission preference
24	audience: string # (optional, default: "content creators") Target audience type
25	platform: string # (optional, default: "any") Platform they'll promote on
26	compare: string[] # (optional) Specific programs to compare head-to-head
27	}
28	```
29
30	## Workflow
31
32	### Step 1: Understand What the User Wants
33
34	Ask (if not clear from context):
35	- Niche/category interest? (AI tools, SEO, video, writing, automation...)
36	- Commission preference? (recurring vs one-time, minimum %)
37	- Audience type? (developers, marketers, beginners, enterprise...)
38	- Platform they'll promote on? (blog, LinkedIn, YouTube, X...)
39
40	If user says "just find me something good" → default to: AI/SaaS tools, recurring commission, 20%+, content creator audience.
41
42	### Step 2: Search openaffiliate.dev
43
44	See `references/openaffiliate-api.md` for integration methods.
45
46	Two methods available:
47	- API (preferred): `GET https://openaffiliate.dev/api/programs?q=<term>` — public, no auth needed, structured data
48	- Web fetch (fallback): `web_search "site:openaffiliate.dev [category]"` then `web_fetch` the page
49
50	Extract for each program: `name`, `reward_value`, `reward_type`, `cookie_days`, `stars_count`, `tags`, `description`.
51
52	### Step 3: Score Programs
53
54	Apply the scoring framework from `references/scoring-criteria.md`.
55
56	Score each program on 5 dimensions (1-10 scale):
57	1. Earning Potential (30%) — commission %, recurring vs one-time, product price
58	2. Content Potential (25%) — visual demo, free tier, content angles
59	3. Market Demand (20%) — search volume, trend direction, market size
60	4. Competition Level (15%) — fewer affiliates promoting = higher score
61	5. Trust Factor (10%) — product quality, reputation, stars on openaffiliate.dev
62
63	Overall = weighted average. Verdict: 7.5+ "Strong Pick" / 5.5-7.4 "Worth Testing" / <5.5 "Skip".
64
65	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.
66
67	### Step 4: Present Recommendation
68
69	### Step 5: Self-Validation
70
71	Before presenting output, verify:
72
73	- [ ] All scored programs have `reward_value` from API data, not hallucinated
74	- [ ] `cookie_days` is numeric and from API response
75	- [ ] Top Pick verdict matches score threshold (≥7.5 = Strong Pick, ≥6 = Worth Considering)
76	- [ ] Market Demand and Competition scores cite the search query used
77	- [ ] Stale data (>6 months) is flagged with warning
78
79	If any check fails, fix the output before delivering. Do not flag the checklist to the user — just ensure the output passes.
80
81	## Output Schema
82
83	Other skills (viral-post-writer, affiliate-blog-builder, etc.) consume these fields from conversation context:
84
85	```
86	{
87	output_schema_version: "1.0.0" # Semver — bump major on breaking changes
88	recommended_program: {
89	name: string # "HeyGen"
90	slug: string # "heygen"
91	reward_value: string # "30%"
92	reward_type: string # "cps_recurring"
93	reward_duration: string # "12 months"
94	cookie_days: number # 60
95	description: string # Short product description
96	tags: string[] # ["ai", "video"]
97	url: string # Prod

People who liked this also viewed

6 picks

Type