pricing-finder

Name: pricing-finder
Author: Varnan-Tech

20installs59forks

How to install pricing-finder?

varnan-tech/opendirectory/pricing-finder

$npx -y skills add Varnan-Tech/opendirectory --skill pricing-finder

Installs into the current project.

Summary

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, f

Files · 1

View on GitHub

SKILL.md

1	# Pricing Finder
2
3	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.
4
5	Zero required API keys. Runs entirely on free pip dependencies. Optional API keys improve quality.
6
7	---
8
9	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:
10	- Competitor prices: extracted verbatim from fetched page content only
11	- "Contact Sales": recorded as-is, never estimated or replaced with a number
12	- Tier names: copied exactly from the page, not paraphrased
13	- Feature lists: extracted from page content, not inferred from product knowledge
14	- Positioning observations: derived from the benchmark table data only
15
16	---
17
18	## Common Mistakes
19
20	\| The agent will want to... \| Why that's wrong \|
21	\|---\|---\|
22	\| Fill in "Contact Sales" with an estimated price \| Never estimate enterprise pricing. Record it as "Contact Sales" exactly. \|
23	\| Use training knowledge for competitor prices \| Every price must trace to fetched page content or a search snippet. \|
24	\| Skip the competitor confirmation step \| Always show discovered competitors and wait for confirmation. Wrong competitors = wrong benchmarks. \|
25	\| Recommend a price without referencing benchmark data \| Every price recommendation must cite a specific number from the benchmark table. \|
26	\| Mark a page as high quality when content < 500 chars \| < 500 chars means the page was not fetched -- mark data_quality as 'low' and use search snippet fallback. \|
27	\| Use em dashes in output \| Replace all em dashes with hyphens. \|
28
29	---
30
31	## Read Reference Files Before Each Run
32
33	```bash
34	cat references/pricing-models.md
35	cat references/extraction-guide.md
36	cat references/positioning-guide.md
37	```
38
39	---
40
41	## Step 1: Setup Check
42
43	```bash
44	echo "TAVILY_API_KEY: ${TAVILY_API_KEY:+set (search quality enhanced)}${TAVILY_API_KEY:-not set, DuckDuckGo will be used (free)}"
45	echo "FIRECRAWL_API_KEY: ${FIRECRAWL_API_KEY:+set (JS rendering enhanced)}${FIRECRAWL_API_KEY:-not set, requests+BS4 will be used (free)}"
46	echo ""
47	python3 -c "from ddgs import DDGS; import requests, bs4, html2text; print('Dependencies OK')" 2>/dev/null \
48	\|\| echo "ERROR: Missing dependencies. Run: pip install ddgs requests beautifulsoup4 html2text"
49	```
50
51	If dependencies are missing: Stop immediately. Tell the user: "Missing Python dependencies. Run this to install them: `pip install ddgs requests beautifulsoup4 html2text` -- all free, no accounts needed. Then try again."
52
53	If only API keys are missing: Continue. DuckDuckGo and requests+BS4 are the free defaults.
54
55	Derive product slug:
56
57	```bash
58	PRODUCT_SLUG=$(python3 -c "
59	from urllib.parse import urlparse
60	import sys, re
61	url = 'URL_HERE'
62	if url.startswith('http'):
63	host = urlparse(url).netloc.replace('www.', '')
64	print(host.split('.')[0])
65	else:
66	print(re.sub(r'[^a-z0-9]', '-', url[:30].lower()).strip('-'))
67	")
68	echo "Product slug: $PRODUCT_SLUG"
69	```
70
71	---
72
73	## Step 2: Parse Input
74
75	Collect from the conversation:
76	- `product_url`: the URL to fetch (required, unless user pastes a description directly)
77	- `geography`: optional -- US / Europe / India / global. Default: US
78
79	If the user provides only a pasted description (no URL): Skip Steps 3 and 4. Go directly to Step 4 (product analysis) using the pasted text as `product_content`. Set `page_source` to `user_description` and note in `data_quality_flags`.
80
81	If neither URL nor description: Ask: "What is the URL of your product or startup? Or paste a short description: what it does, who it's for, and what makes it different."
82
83	---
84
85	## Step 3: Fetch Product Page
86
87	Primary: Firecrawl (if FIRECRAWL_API_KEY is set)
88
89	```bash
90	curl -s -X POST https://api.firecrawl.dev/v1/scrape \
91	-H "Authorization: Bearer $FIRECRAWL_API_KEY" \
92	-H "Content-Type: application/json" \
93	-d '{"url": "URL_HERE", "formats": ["markdown"], "onlyMainContent": true}' \
94	\| python3 -c "
95	import sys, json
96	d = json.load(sys.stdin)
97	content = d.get('data', {}).get('markdown', '') or d.get('markdown', '')
98	print(f'Fetched via Firecrawl: {len(content)} characters')
99	open('/

People who liked this also viewed

6 picks

Type

pricing-finder

20installs59forks

View on GitHub

How to install pricing-finder?

varnan-tech/opendirectory/pricing-finder

$npx -y skills add Varnan-Tech/opendirectory --skill pricing-finder

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Pricing Finder
2
3	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.
4
5	Zero required API keys. Runs entirely on free pip dependencies. Optional API keys improve quality.
6
7	---
8
9	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:
10	- Competitor prices: extracted verbatim from fetched page content only
11	- "Contact Sales": recorded as-is, never estimated or replaced with a number
12	- Tier names: copied exactly from the page, not paraphrased
13	- Feature lists: extracted from page content, not inferred from product knowledge
14	- Positioning observations: derived from the benchmark table data only
15
16	---
17
18	## Common Mistakes
19
20	\| The agent will want to... \| Why that's wrong \|
21	\|---\|---\|
22	\| Fill in "Contact Sales" with an estimated price \| Never estimate enterprise pricing. Record it as "Contact Sales" exactly. \|
23	\| Use training knowledge for competitor prices \| Every price must trace to fetched page content or a search snippet. \|
24	\| Skip the competitor confirmation step \| Always show discovered competitors and wait for confirmation. Wrong competitors = wrong benchmarks. \|
25	\| Recommend a price without referencing benchmark data \| Every price recommendation must cite a specific number from the benchmark table. \|
26	\| Mark a page as high quality when content < 500 chars \| < 500 chars means the page was not fetched -- mark data_quality as 'low' and use search snippet fallback. \|
27	\| Use em dashes in output \| Replace all em dashes with hyphens. \|
28
29	---
30
31	## Read Reference Files Before Each Run
32
33	```bash
34	cat references/pricing-models.md
35	cat references/extraction-guide.md
36	cat references/positioning-guide.md
37	```
38
39	---
40
41	## Step 1: Setup Check
42
43	```bash
44	echo "TAVILY_API_KEY: ${TAVILY_API_KEY:+set (search quality enhanced)}${TAVILY_API_KEY:-not set, DuckDuckGo will be used (free)}"
45	echo "FIRECRAWL_API_KEY: ${FIRECRAWL_API_KEY:+set (JS rendering enhanced)}${FIRECRAWL_API_KEY:-not set, requests+BS4 will be used (free)}"
46	echo ""
47	python3 -c "from ddgs import DDGS; import requests, bs4, html2text; print('Dependencies OK')" 2>/dev/null \
48	\|\| echo "ERROR: Missing dependencies. Run: pip install ddgs requests beautifulsoup4 html2text"
49	```
50
51	If dependencies are missing: Stop immediately. Tell the user: "Missing Python dependencies. Run this to install them: `pip install ddgs requests beautifulsoup4 html2text` -- all free, no accounts needed. Then try again."
52
53	If only API keys are missing: Continue. DuckDuckGo and requests+BS4 are the free defaults.
54
55	Derive product slug:
56
57	```bash
58	PRODUCT_SLUG=$(python3 -c "
59	from urllib.parse import urlparse
60	import sys, re
61	url = 'URL_HERE'
62	if url.startswith('http'):
63	host = urlparse(url).netloc.replace('www.', '')
64	print(host.split('.')[0])
65	else:
66	print(re.sub(r'[^a-z0-9]', '-', url[:30].lower()).strip('-'))
67	")
68	echo "Product slug: $PRODUCT_SLUG"
69	```
70
71	---
72
73	## Step 2: Parse Input
74
75	Collect from the conversation:
76	- `product_url`: the URL to fetch (required, unless user pastes a description directly)
77	- `geography`: optional -- US / Europe / India / global. Default: US
78
79	If the user provides only a pasted description (no URL): Skip Steps 3 and 4. Go directly to Step 4 (product analysis) using the pasted text as `product_content`. Set `page_source` to `user_description` and note in `data_quality_flags`.
80
81	If neither URL nor description: Ask: "What is the URL of your product or startup? Or paste a short description: what it does, who it's for, and what makes it different."
82
83	---
84
85	## Step 3: Fetch Product Page
86
87	Primary: Firecrawl (if FIRECRAWL_API_KEY is set)
88
89	```bash
90	curl -s -X POST https://api.firecrawl.dev/v1/scrape \
91	-H "Authorization: Bearer $FIRECRAWL_API_KEY" \
92	-H "Content-Type: application/json" \
93	-d '{"url": "URL_HERE", "formats": ["markdown"], "onlyMainContent": true}' \
94	\| python3 -c "
95	import sys, json
96	d = json.load(sys.stdin)
97	content = d.get('data', {}).get('markdown', '') or d.get('markdown', '')
98	print(f'Fetched via Firecrawl: {len(content)} characters')
99	open('/

People who liked this also viewed

6 picks

Type