Agent skill

Niche Opportunity Finder

by Affitor in Affitor/affiliate-skills

Find untapped affiliate niches with real earning potential. An agent skill from Affitor/affiliate-skills.

MITAuto-check passedMarketing & SEO

Install Niche Opportunity Finder

skills CLI
$ npx skills add Affitor/affiliate-skills --skill niche-opportunity-finder -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Affitor/affiliate-skills niche-opportunity-finder --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Affitor/affiliate-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/research/niche-opportunity-finder .claude/skills/niche-opportunity-finder && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
niche-opportunity-finder
GitHub stars
701
Token cost
~2.7k tokens
SKILL.md length
918 words
Files
2
Skills in repo
50
Repo updated
First seen
Licence
MIT

At a glance

Find untapped affiliate niches with real earning potential. An agent skill from Affitor/affiliate-skills.

  • Works in 7 steps: Understand the User's Situation → Generate Niche Candidates → Score Each Niche → …
  • The user asks about picking a niche
  • SKILL.md covers Stage, When to Use, Input Schema and Workflow, plus 6 more sections
  • Reaches openaffiliate.dev

What it does

Niche Opportunity Finder is an agent skill from Affitor/affiliate-skills. Find untapped affiliate niches with real earning potential. Use this skill when the user asks about picking a niche, finding a niche to start affiliate marketing, what niche to get into, niche research, niche ideas, beginner niche selection, low competition niches, profitable niches, or says "I don't know what to promote", "help me pick a niche", "what niche should I start with", "find me a niche with less competition", "niche ideas for affiliate", "is X a good niche for affiliate marketing", "best niches 2024"…

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file. Compatibility notes: Claude Code, ChatGPT, Gemini CLI, Cursor, Windsurf, OpenClaw, any AI agent

It sits in Marketing & SEO, covering Influencer and creator marketing. The repository describes itself as: 50 AI agent skills for affiliate marketing. Research trending content, write data-backed posts, generate infographics, build landing pages, deploy — full flywheel with social… The licence is MIT.

When your agent uses it

  • The user asks about picking a niche
  • Finding a niche to start affiliate marketing
  • What niche to get into
  • Beginner niche selection

Example prompts

  • “t know what to promote”
  • “help me pick a niche”
  • “what niche should I start with”
  • “/niche-opportunity-finder”

Requirements

  • Compatibility (from SKILL.md): Claude Code, ChatGPT, Gemini CLI, Cursor, Windsurf, OpenClaw, any AI agent

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Understand the User's Situation
  2. Generate Niche Candidates
  3. Score Each Niche
  4. Validate Top 3 Niches on openaffiliate.dev
  5. Build the Opportunity Brief
  6. Recommend Next Steps
  7. Self-Validation

What it can do on your machine

Read from SKILL.md and the folder at commit e43bfae. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • openaffiliate.dev

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Claude Code, ChatGPT, Gemini CLI, Cursor, Windsurf, OpenClaw, any AI agent

    From compatibility in the SKILL.md frontmatter.

Context cost

Niche Opportunity Finder loads about 2.7k tokens when it runs. Until then it costs about 140 tokens; SKILL.md has 918 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~140
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Affitor/affiliate-skills at commit e43bfae, republished under its MIT licence (© Affitor). 918 words, ~2,728 tokens.

Download SKILL.mdSave it as .claude/skills/niche-opportunity-finder/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
niche-opportunity-finder
description
Find untapped affiliate niches with real earning potential. Use this skill when the user asks about picking a niche, finding a niche to start affiliate marketing, what niche to get into, niche research, niche ideas, beginner niche selection, low competition niches, profitable niches, or says "I don't know what to promote", "help me pick a niche", "what niche should I start with", "find me a niche with less competition", "niche ideas for affiliate", "is X a good niche for affiliate marketing", "best niches 2024", "untapped niches".
compatibility
Claude Code, ChatGPT, Gemini CLI, Cursor, Windsurf, OpenClaw, any AI agent
license
MIT
version
1.0.0
tags
affiliate-marketing, research, niche-analysis, program-discovery, niche, opportunity
metadata.author
affitor
metadata.version
1.0
metadata.stage
S1-Research

Niche Opportunity Finder

Analyze search demand, competition, and available affiliate programs to surface untapped niches worth entering. Outputs a scored shortlist with clear reasoning so beginners can start promoting in under an hour.

Stage

This skill belongs to Stage S1: Research

When to Use

  • User is new to affiliate marketing and has no niche
  • User is unhappy with their current niche and wants alternatives
  • User wants to validate a niche idea before investing time
  • User asks which niches are trending or low-competition
  • User wants to find niches underserved by existing affiliates

Input Schema

{
  interests: string[]       # (optional) Topics user already knows or cares about
  audience: string          # (optional) Who they plan to reach — "beginners", "professionals", "parents"
  platform: string          # (optional) Where they'll publish — "blog", "tiktok", "youtube", "linkedin"
  budget: string            # (optional) "zero" | "low ($0-50/mo)" | "medium ($50-200/mo)"
  goal: string              # (optional) "first $100" | "side income $1k/mo" | "full-time income"
  avoid: string[]           # (optional) Niches or topics to exclude
}

Workflow

Step 1: Understand the User's Situation

Ask (if not already clear from context):

  1. Any topics you already know well or are curious about?
  2. Where will you publish content? (blog, TikTok, YouTube, newsletter...)
  3. What's your income goal in the first 6 months?

If user says "just find me something" → default to: AI/SaaS tools, YouTube or blog, goal = first $500/mo.

Step 2: Generate Niche Candidates

Produce 8-12 niche candidates across 3 tiers:

Tier A — Trending (high demand, growing fast): Use web_search "fastest growing affiliate niches [current year]" and web_search "trending affiliate programs [current year]" to find niches with momentum. Look for: AI tools, health tech, fintech, remote work tools, creator economy.

Tier B — Evergreen (stable demand, proven programs): Always-on niches: personal finance, web hosting, email marketing, SEO tools, fitness/wellness, online education, cybersecurity.

Tier C — Micro-niches (narrow, low competition, high intent): Examples: AI tools for lawyers, budgeting apps for freelancers, SEO for Shopify stores, productivity tools for ADHD. These are combinations of a vertical + a job or persona. Use web_search "[vertical] affiliate programs [persona]" to discover.

Step 3: Score Each Niche

Score each candidate on 4 dimensions (1-10 scale each):

DimensionWeightHow to Assess
Search Demand30%`web_search "[niche] how to" — look at result count and autosuggest depth
Program Availability30%Search openaffiliate.dev (GET /api/programs?q=[niche]) or web_search "[niche] affiliate programs" — count quality programs
Competition Level25%Search "[niche] best tools" — how saturated is the top 10? Fewer exact-match affiliate sites = less competition. Score 10 = very low competition
Content Potential15%Can tutorials, comparisons, listicles, and reviews be made for this niche easily?

Overall score = weighted average. Cut anything below 5.5.

Verdict: 7.5+ = "High Opportunity" / 5.5-7.4 = "Worth Testing" / <5.5 = "Saturated/Skip"

Step 4: Validate Top 3 Niches on openaffiliate.dev

For the top 3 niches, query GET https://openaffiliate.dev/api/programs?q=[niche]&utm_source=affiliate-skills (see affiliate-program-search/references/openaffiliate-api.md) to verify real programs exist with good commission structures:

  • At least 3 programs with reward_value 20%+ OR reward_type cps_recurring
  • At least one program with cookie_days >= 30
  • Programs with stars_count > 5 (community-validated quality)

If a niche scores well on demand but has no programs on openaffiliate.dev, use web_search "[niche] affiliate program signup" to verify alternatives exist.

Step 5: Build the Opportunity Brief

For the top-ranked niche, produce a one-page opportunity brief (see Output Format). For runner-up niches, produce summary cards only.

Step 6: Recommend Next Steps

Map user's chosen niche to the affiliate funnel:

  1. Use affiliate-program-search to find the best specific program in this niche
  2. Use tiktok-script-writer or twitter-thread-writer for first content
  3. Use commission-calculator to project first 90 days of income
Step 7: Self-Validation

Before presenting output, verify:

  • Search demand backed by data (autosuggest depth, result count)
  • Top niche has ≥3 programs with 20%+ commission on openaffiliate.dev
  • Competition score reflects actual top-10 SERP analysis
  • Content angles are specific and actionable, not generic

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

Show full SKILL.md (340 more words)Show less

Output Schema

{
  output_schema_version: "1.0.0"  # Semver — bump major on breaking changes
  top_niche: {
    name: string              # "AI Productivity Tools"
    tier: string              # "Trending" | "Evergreen" | "Micro-niche"
    score: number             # 8.4
    verdict: string           # "High Opportunity"
    why: string               # 2-3 sentence rationale
    example_programs: string[] # ["Notion", "ClickUp", "Reclaim AI"]
    content_angles: string[]  # ["comparison", "workflow walkthrough", "beginner guide"]
    difficulty: string        # "Beginner-friendly" | "Intermediate" | "Advanced"
  }
  runner_up: NicheCandidate   # Same structure
  all_scored: NicheScore[]    # Full list with scores
  recommended_next_skill: string  # "affiliate-program-search"
}

Output Format

## Niche Opportunity Report

### Top Pick: [Niche Name]

**Opportunity Score:** [X.X/10] — [Verdict]
**Tier:** [Trending / Evergreen / Micro-niche]
**Difficulty:** [Beginner-friendly / Intermediate / Advanced]

**Why this niche:**
[2-3 sentences covering demand, program quality, and why it's not yet saturated]

| Dimension | Score | Evidence |
|-----------|-------|----------|
| Search Demand | X/10 | [What search data showed] |
| Program Availability | X/10 | [X programs found, avg commission Y%] |
| Competition Level | X/10 | [What competitor landscape looks like] |
| Content Potential | X/10 | [Content formats that work here] |
| **Overall** | **X.X/10** | **[Verdict]** |

**Example affiliate programs:** [Program A], [Program B], [Program C]

**Content angles to start with:**
1. [Angle 1 — specific post/video idea]
2. [Angle 2]
3. [Angle 3]

---

### Runner-up: [Niche Name] — [X.X/10]
[2-sentence summary + why it's #2]

### Other Candidates Scored

| Niche | Score | Verdict | Note |
|-------|-------|---------|------|
| ...   | ...   | ...     | ...  |

---

## Next Steps

1. Run `affiliate-program-search` to find the best [Niche] program on openaffiliate.dev
2. Run `commission-calculator` to project 90-day earnings
3. Run `tiktok-script-writer` or `twitter-thread-writer` to create your first piece of content

Error Handling

  • No interests provided: Default to AI/SaaS tools niche. Explain the default.
  • Niche too broad (e.g., "health"): Break into sub-niches and score each separately. Present as micro-niche grid.
  • Niche too narrow (e.g., "left-handed guitarists who use Linux"): Widen one dimension and present a spectrum of options.
  • No programs found for top niche: Still present the niche but flag program gap. Suggest direct brand deals as alternative.
  • User picks a saturated niche: Don't just say no. Find the micro-niche angle within it that is less saturated.
  • Conflicting interests: Ask user to pick one dimension (monetization speed vs. passion vs. content ease) and sort by that.

Examples

Example 1: User: "I want to start affiliate marketing but have no idea what niche to pick" → Ask: any interests? what platform? income goal? → If no answer: default to AI/SaaS tools on YouTube/TikTok, goal = first $500/mo → Generate 10 candidates, score all, return top 3 with detailed brief for #1

Example 2: User: "Is fitness a good niche for affiliate marketing?" → Validate fitness niche: high demand, many programs (MyProtein, Noom, Whoop) → Flag: highly competitive on Google. Score = 6.2 "Worth Testing" → Suggest micro-niches: fitness for new moms, home gym under $500, wearables for runners → Score micro-niches — surface the strongest one

Example 3: User: "I know a lot about Notion and productivity tools" → Lean into existing knowledge: AI productivity tools, note-taking apps, PKM space → Score with "expert authority" bonus — existing knowledge = faster content creation → Surface programs: Notion, Obsidian affiliate, ClickUp, Reclaim AI → Recommend micro-niche: "AI tools for knowledge workers" — score 8.1

References

  • affiliate-program-search/references/openaffiliate-api.md — how to fetch programs from openaffiliate.dev
  • shared/references/affiliate-glossary.md — affiliate marketing terminology
  • shared/references/ftc-compliance.md — disclosure requirements
  • shared/references/flywheel-connections.md — master flywheel connection map

Flywheel Connections

Feeds Into
  • affiliate-program-search (S1) — validated niches to search programs in
  • monopoly-niche-finder (S1) — niche data for intersection analysis
  • keyword-cluster-architect (S3) — niche defines keyword universe
  • content-moat-calculator (S3) — niche for feasibility analysis
Fed By
  • performance-report (S6) — performance data identifies best-performing niches
  • conversion-tracker (S6) — conversion data reveals profitable niches
Feedback Loop
  • Performance data from S6 shows which niche characteristics predict success → refine opportunity scoring
yaml
chain_metadata:
  skill_slug: "niche-opportunity-finder"
  stage: "research"
  timestamp: string
  suggested_next:
    - "affiliate-program-search"
    - "monopoly-niche-finder"
    - "keyword-cluster-architect"

© Affitor, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/research/niche-opportunity-finder of Affitor/affiliate-skills.

  • SKILL.md
  • LICENSE.txt

Open the folder on GitHubat commit e43bfae

Compare with similar skills

Niche Opportunity Finder next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Niche Opportunity Finder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Niche Opportunity Finder this skillAffitor/affiliate-skills701—~2.7kAutomated safety check: PassMIT
Audience ResearchScrapeCreators/social-media-research-skills3.4k—~635Automated safety check: NotesMIT
Influencer Discoverytigerless-labs/influencer-discovery212—~2.5kAutomated safety check: NotesNone
Opencloneteam-attention/openclone130—~2.6kAutomated safety check: NotesMIT
Reelclaw Adsdansugc/reelclaw145—~3.9kAutomated safety check: NotesMIT
Effect Monitoringvivy-yi/xiaohongshu-skills4811 repos~4.5kAutomated safety check: PassNone

Similar skills

  • Audience Research

    ScrapeCreators/social-media-research-skills

    A skill your agent uses when the user wants to evaluate a creator, influencer, or brand audience using public profile signals, TikTok audience demographics, follower/following data, comments…

    3.4k GitHub stars~635 tokensUpdated 1 mo ago
    Marketing & SEOAuto-check: notes
  • Influencer Discovery

    tigerless-labs/influencer-discovery

    Find the bloggers/creators who can help promote your work, capture their contact info, and append them to the target sheet in Google Sheets.

    212 GitHub stars~2.5k tokensUpdated 18 days ago
    Marketing & SEOAuto-check: notes
  • Openclone

    team-attention/openclone

    Create, manage, or talk to an openclone "clone" — a named AI persona with one or more categories (vc, tech, founder, expert, influencer, politician, celebrity) and attached knowledge.

    130 GitHub stars~2.6k tokensUpdated 1 mo ago
    Marketing & SEOAuto-check: notes
  • Reelclaw Ads

    dansugc/reelclaw

    Make short-form UGC video ads (TikTok, Reels, Shorts) for the product in the current repo with DansUGC ReelClaw and real human creator reactions from the DansUGC library.

    145 GitHub stars~3.9k tokensUpdated 12 days ago
    Marketing & SEOAuto-check: notes
  • Effect Monitoring

    vivy-yi/xiaohongshu-skills

    A skill your agent uses when monitoring Xiaohongshu marketing campaign performance, tracking promotion effectiveness, analyzing advertising ROI, measuring influencer collaboration results…

    481 GitHub starsUsed in 1 repo~4.5k tokens
    Marketing & SEOAuto-check passed
  • Twitter Search

    juntoku9/claude-for-crypto-research

    Search Twitter/X for crypto sentiment, influencer opinions, and community discussions.

    106 GitHub stars~1k tokensUpdated 8 mo ago
    Marketing & SEOAuto-check passed

More from Affitor/affiliate-skills

All 50 skills in this repo
  • Affiliate Check

    Affitor/affiliate-skills

    Live affiliate program data from openaffiliate.dev. An agent skill from Affitor/affiliate-skills.

    701 GitHub stars~808 tokensUpdated 26 days ago
    Auto-check: notes
  • Affiliate Program Search

    Affitor/affiliate-skills

    Research and evaluate affiliate programs to find the best ones to promote.

    701 GitHub stars~2.4k tokensUpdated 26 days ago
    Auto-check passed
  • Bio Link Deployer

    Affitor/affiliate-skills

    Create a Linktree-style bio link hub page as a single self-contained HTML file.

    701 GitHub stars~3k tokensUpdated 26 days ago
    Auto-check passed
  • Conversion Tracker

    Affitor/affiliate-skills

    Set up affiliate conversion tracking with UTM parameters and link tagging.

    701 GitHub stars~2.1k tokensUpdated 26 days ago
    Auto-check passed
  • Performance Report

    Affitor/affiliate-skills

    Generate affiliate performance reports with KPIs and recommendations.

    701 GitHub stars~2.5k tokensUpdated 26 days ago
    Auto-check passed
  • Product Showcase Page

    Affitor/affiliate-skills

    Build a single-product deep-dive showcase page as a self-contained HTML file.

    701 GitHub stars~3.6k tokensUpdated 26 days ago
    Auto-check passed

Categories

Questions about Niche Opportunity Finder

What does Niche Opportunity Finder do?

Find untapped affiliate niches with real earning potential. An agent skill from Affitor/affiliate-skills. Niche Opportunity Finder is an agent skill from Affitor/affiliate-skills. Find untapped affiliate niches with real earning potential.

When should I use Niche Opportunity Finder?

Niche Opportunity Finder fits situations like: the user asks about picking a niche; finding a niche to start affiliate marketing; what niche to get into; beginner niche selection.

How do I install Niche Opportunity Finder in Claude Code?

Run `npx skills add Affitor/affiliate-skills --skill niche-opportunity-finder -a claude-code`. Or copy the skill folder (skills/research/niche-opportunity-finder in Affitor/affiliate-skills) into .claude/skills/niche-opportunity-finder in your project. Claude Code loads it when a task matches its description.

How do I install Niche Opportunity Finder in Codex?

Run `npx skills add Affitor/affiliate-skills --skill niche-opportunity-finder -a codex`. Or copy the skill folder (skills/research/niche-opportunity-finder in Affitor/affiliate-skills) into .agents/skills/niche-opportunity-finder in your project. Codex loads it when a task matches its description.

Can I use Niche Opportunity Finder in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Affitor/affiliate-skills --skill niche-opportunity-finder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/niche-opportunity-finder, .gemini/skills/niche-opportunity-finder, .github/skills/niche-opportunity-finder and .opencode/skills/niche-opportunity-finder in your project.

What does Niche Opportunity Finder need to run?

SKILL.md names no scripts, command-line tools or credentials: Niche Opportunity Finder is instructions for the agent only. Compatibility (from SKILL.md): Claude Code, ChatGPT, Gemini CLI, Cursor, Windsurf, OpenClaw, any AI agent.

Does Niche Opportunity Finder access the network?

SKILL.md names 1 domain. In commands or code: openaffiliate.dev; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Niche Opportunity Finder safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Niche Opportunity Finder use?

Niche Opportunity Finder is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Niche Opportunity Finder use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Niche Opportunity Finder?

Skills that share tags, products or a category with Niche Opportunity Finder: Audience Research (ScrapeCreators/social-media-research-skills, 3.4k stars), Influencer Discovery (tigerless-labs/influencer-discovery, 212 stars), Openclone (team-attention/openclone, 130 stars) and Reelclaw Ads (dansugc/reelclaw, 145 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Niche Opportunity Finder?

Affitor (a GitHub organization) maintains it in Affitor/affiliate-skills, which has 701 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on September 15, 2026.

Source: Affitor/affiliate-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.