pricing-finder
Tell it what your product is (URL or description) and it finds 5 competitors globally, fetches their actual pricing pages, extracts every tier and price point, and returns a complete pricing intelligence report: the dominant pricing model in your space, a benchmark price table, feature gate analysis, competitive positioning map, and a concrete recommended pricing strategy for your product. Use when asked to research competitor pricing, find pricing benchmarks, decide how to price a product, understand pricing models in a space, or build a pricing strategy.
npx skills add Varnan-Tech/opendirectory --skill pricing-finder --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Tell it your product URL or description. It finds 5 competitors globally, fetches their pricing pages, and returns a complete pricing intelligence report: the dominant pricing model in your space, a benchmark price table, feature gate analysis, competitive positioning map, and a concrete pricing recommendation for your product.
Zero required API keys. Runs entirely on free pip dependencies. Optional API keys improve quality.
How it works
- Accept a product URL or pasted description to define the product.
- In Step 3, fetch the product page via Firecrawl if available or via requests + BS4 as fallback; store content to /tmp/pf-product-raw.md.
- In Step 4, run AI to derive: product_name, one_line_description, industry_taxonomy, differentiators (2-3 specifics), icp, geography_bias, page_source, then write analysis to /tmp/pf-product-analysis.json.
- In Step 4b, perform competitor discovery using scripts/research.py to produce a list of 5 competitor candidates with name, url, pricing_url, description, and source_url.
- In Step 5, confirm the 5 competitors to fetch pricing from; then save confirmed list to /tmp/pf-competitors-confirmed.json.
- In Step 6, fetch pricing pages for confirmed competitors via a 3-tier fallback: direct, Google cache, then DuckDuckGo snippet search; summarize fetch results and data_quality per competitor.
- In Step 7, extract structured pricing data per competitor from the fetched content, following the extraction guide; output to /tmp/pf-pricing-extracted.json with fields for each competitor, tiers, pricing_model, pricing_url, data_quality, etc.
- In Step 8, analyze all extracted pricing data to identify patterns and create a positioning analysis, writing to /tmp/pf-patterns.json.
Important: All price points, tier names, and feature gates must trace to fetched page content or search snippets. Do not estimate or infer prices.
When to use it
Use when asked to research competitor pricing, find pricing benchmarks, decide how to price a product, understand pricing models in a space, or build a pricing strategy.
What it can touch
- Tools listed: claude-code, copilot; scripts/research.py; external web fetches for product and pricing pages. All interactions are driven by the steps above and written outputs to local /tmp paths.
Caveats
- Zero-hallucination policy applies to prices, tier names, and feature gates, all sourced from fetched pages or search snippets. If data_quality is low, use snippet data with caveats. Enterprise pricing may appear as 'Contact Sales' and must be preserved as-is.
- If dependencies or pages are missing content, the workflow halts or asks for input per the prompts in the script.
# Pricing Finder Tell it your product URL or description. It finds 5 competitors, fetches their actual pricing pages, and returns a complete pricing intelligence report: dominant model in your space, benchmark price table, feature gate analysis, positioning map, and a concrete pricing recommendation for your product. **Zero required API keys.** Runs entirely on free pip dependencies. Optional API keys improve quality. --- **Zero-hallucination policy:** Every price point, tier name, and feature gate in the output must trace to fetched pricing page content or a DuckDuckGo search snippet. This applies to: - Competitor prices: extracted verbatim from fetched page content only - "Contact Sales": recorded as-is, never estimated or replaced with a number - Tier names: copied exactly from the page, not paraphrased - Feature lists: extracted from page content, not inferred from product knowledge - Positioning observations: derived from the benchmark table data only --- ## Common Mistakes | The agent will want to... | Why that's wrong | |---|---| | Fill in "Contact Sales" with an estimated price | Never estimate enterprise pricing. Record it as "Contact Sales" exactly. | | Use training knowl
- Common Mistakes
- Read Reference Files Before Each Run
- Step 1: Setup Check
- Step 2: Parse Input
- Step 3: Fetch Product Page
- Step 4: Product Analysis (AI)
- Step 4b: Phase 1 -- Competitor Discovery
- Step 5: Competitor Confirmation
- Step 6: Phase 2 -- Fetch Pricing Pages
- Step 7: Pricing Extraction (AI)
- Step 8: Pattern Analysis (AI)
- Step 9: Positioning Map + Recommendation (AI)
- Step 10: Self-QA, Present, and Save
cat references/pricing-models.md
cat references/extraction-guide.md
cat references/positioning-guide.md
echo "TAVILY_API_KEY: ${TAVILY_API_KEY:+set (search quality enhanced)}${TAVILY_API_KEY:-not set, DuckDuckGo will be used (free)}"
echo "FIRECRAWL_API_KEY: ${FIRECRAWL_API_KEY:+set (JS rendering enhanced)}${FIRECRAWL_API_KEY:-not set, requests+BS4 will be used (free)}"
echo ""
python3 -c "from ddgs import DDGS; import requests, bs4, html2text; print('Dependencies OK')" 2>/dev/null \
from urllib.parse import urlparse
import sys, re
url = 'URL_HERE'What does the pricing-finder skill do?
Tell it what your product is (URL or description) and it finds 5 competitors globally, fetches their actual pricing pages, extracts every tier and price point, and returns a complete pricing intelligence report: the dominant pricing model in your space, a benchmark price table, feature gate analysis, competitive positioning map, and a concrete recommended pricing strategy for your product. Use when asked to research competitor pricing, find pricing benchmarks, decide how to price a product, understand pricing models in a space, or build a pricing strategy.
How do I install it?
Run `npx skills add Varnan-Tech/opendirectory --skill pricing-finder --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From Varnan-Tech/opendirectory, a repository with 571 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.