competitor-pr-finder

Name: competitor-pr-finder
Author: Varnan-Tech

20installs59forks

How to install competitor-pr-finder?

varnan-tech/opendirectory/competitor-pr-finder

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

Installs into the current project.

Summary

Give it your product URL or description. It finds your top 5 competitors, runs three-track PR research across all of them (editorial, podcasts, communities), identifies which channels appear most frequently, looks up the journalist or host for each, and returns a tiered outreach

Files · 1

View on GitHub

SKILL.md

1	# Competitor PR Finder
2
3	Give it your product URL. It finds your competitors, researches every PR channel they used (news, podcasts, communities), surfaces the channels that appear across multiple competitors (your proven targets), finds the journalist or host for each, and drafts a personalized cold pitch for your product at every tier-1 channel.
4
5	---
6
7	Zero-hallucination policy: Every channel, journalist name, story angle, and pitch detail in the output must trace to a specific Tavily search result or the fetched product page. This applies to:
8	- Competitor names: must appear in Tavily search results, not AI training knowledge
9	- Channel names: must have a URL in the search results
10	- Journalist/host names: must appear verbatim in a Tavily snippet
11	- Story angles: extracted from article/episode titles in search results only
12	- Pitch drafts: reference specific evidence from search data + product analysis
13
14	---
15
16	## Common Mistakes
17
18	\| The agent will want to... \| Why that's wrong \|
19	\|---\|---\|
20	\| Name a journalist from training knowledge \| Every journalist name must trace to a search result snippet. Writing "Sarah Perez covers startups at TechCrunch" from memory is hallucination. \|
21	\| List channels without evidence URLs \| Every channel in the output must have at least one URL from the PR search results proving a competitor was featured there. \|
22	\| Skip the competitor confirmation step \| Always show discovered competitors and wait for the user to confirm. Wrong competitors = wasted searches and a useless output. \|
23	\| Generate generic pitches ("We'd love to be featured") \| Every pitch must reference a specific angle from the evidence AND a specific differentiator from the product analysis. \|
24	\| Mark a channel as Tier 1 with only 1 competitor occurrence \| Tier 1 = 3+ competitors. Tier 2 = exactly 2. Tier 3 = 1. Do not promote channels that haven't proven themselves. \|
25	\| Use em dashes in output \| Replace all em dashes (--) with hyphens. \|
26
27	---
28
29	## Read Reference Files Before Each Run
30
31	```bash
32	cat references/pr-channel-types.md
33	cat references/pitch-guide.md
34	cat references/tier-scoring.md
35	```
36
37	---
38
39	## Step 1: Setup Check
40
41	```bash
42	echo "TAVILY_API_KEY: ${TAVILY_API_KEY:+set}${TAVILY_API_KEY:-NOT SET -- required}"
43	echo "FIRECRAWL_API_KEY: ${FIRECRAWL_API_KEY:+set}${FIRECRAWL_API_KEY:-not set, Tavily extract will be used as fallback}"
44	```
45
46	If TAVILY_API_KEY is missing: Stop immediately. Tell the user: "TAVILY_API_KEY is required to research competitors and find PR coverage. There is no fallback. Get it at app.tavily.com -- free tier: 1000 credits/month (about 43 full runs at ~23 searches/run). Add it to your .env file."
47
48	If only FIRECRAWL_API_KEY is missing: Continue. Tavily extract will be used for the URL fetch.
49
50	---
51
52	## Step 2: Parse Input
53
54	Collect from the conversation:
55	- `product_url`: the URL to fetch (required, unless user pastes a description directly)
56	- `product_name`: optional, derived from page if not provided
57	- `geography`: optional -- US / Europe / global. Default: US
58
59	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`.
60
61	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 is for, and what makes it different from competitors."
62
63	Derive product slug:
64
65	```bash
66	PRODUCT_SLUG=$(python3 -c "
67	from urllib.parse import urlparse
68	import sys
69	url = 'URL_HERE'
70	if url.startswith('http'):
71	host = urlparse(url).netloc.replace('www.', '')
72	print(host.split('.')[0])
73	else:
74	import re
75	print(re.sub(r'[^a-z0-9]', '-', url[:30].lower()).strip('-'))
76	")
77	echo "Product slug: $PRODUCT_SLUG"
78	```
79
80	---
81
82	## Step 3: Fetch Product Page
83
84	Primary: Firecrawl (if FIRECRAWL_API_KEY is set)
85
86	```bash
87	curl -s -X POST https://api.firecrawl.dev/v1/scrape \
88	-H "Authorization: Bearer $FIRECRAWL_API_KEY" \
89	-H "Content-Type: application/json" \
90	-d '{"url": "URL_HERE", "formats": ["markdown"], "onlyMainContent": true}' \
91	\| python3 -c "
92	import sys, json
93	d = json.load(sys.stdin)
94	content = d.get('data', {}).get('markdown', '') or d.get('markdown', '')
95	print(f'Fetched via Firecrawl: {len(content)} characters')
96	open

People who liked this also viewed

6 picks

Type

competitor-pr-finder

20installs59forks

View on GitHub

How to install competitor-pr-finder?

varnan-tech/opendirectory/competitor-pr-finder

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Competitor PR Finder
2
3	Give it your product URL. It finds your competitors, researches every PR channel they used (news, podcasts, communities), surfaces the channels that appear across multiple competitors (your proven targets), finds the journalist or host for each, and drafts a personalized cold pitch for your product at every tier-1 channel.
4
5	---
6
7	Zero-hallucination policy: Every channel, journalist name, story angle, and pitch detail in the output must trace to a specific Tavily search result or the fetched product page. This applies to:
8	- Competitor names: must appear in Tavily search results, not AI training knowledge
9	- Channel names: must have a URL in the search results
10	- Journalist/host names: must appear verbatim in a Tavily snippet
11	- Story angles: extracted from article/episode titles in search results only
12	- Pitch drafts: reference specific evidence from search data + product analysis
13
14	---
15
16	## Common Mistakes
17
18	\| The agent will want to... \| Why that's wrong \|
19	\|---\|---\|
20	\| Name a journalist from training knowledge \| Every journalist name must trace to a search result snippet. Writing "Sarah Perez covers startups at TechCrunch" from memory is hallucination. \|
21	\| List channels without evidence URLs \| Every channel in the output must have at least one URL from the PR search results proving a competitor was featured there. \|
22	\| Skip the competitor confirmation step \| Always show discovered competitors and wait for the user to confirm. Wrong competitors = wasted searches and a useless output. \|
23	\| Generate generic pitches ("We'd love to be featured") \| Every pitch must reference a specific angle from the evidence AND a specific differentiator from the product analysis. \|
24	\| Mark a channel as Tier 1 with only 1 competitor occurrence \| Tier 1 = 3+ competitors. Tier 2 = exactly 2. Tier 3 = 1. Do not promote channels that haven't proven themselves. \|
25	\| Use em dashes in output \| Replace all em dashes (--) with hyphens. \|
26
27	---
28
29	## Read Reference Files Before Each Run
30
31	```bash
32	cat references/pr-channel-types.md
33	cat references/pitch-guide.md
34	cat references/tier-scoring.md
35	```
36
37	---
38
39	## Step 1: Setup Check
40
41	```bash
42	echo "TAVILY_API_KEY: ${TAVILY_API_KEY:+set}${TAVILY_API_KEY:-NOT SET -- required}"
43	echo "FIRECRAWL_API_KEY: ${FIRECRAWL_API_KEY:+set}${FIRECRAWL_API_KEY:-not set, Tavily extract will be used as fallback}"
44	```
45
46	If TAVILY_API_KEY is missing: Stop immediately. Tell the user: "TAVILY_API_KEY is required to research competitors and find PR coverage. There is no fallback. Get it at app.tavily.com -- free tier: 1000 credits/month (about 43 full runs at ~23 searches/run). Add it to your .env file."
47
48	If only FIRECRAWL_API_KEY is missing: Continue. Tavily extract will be used for the URL fetch.
49
50	---
51
52	## Step 2: Parse Input
53
54	Collect from the conversation:
55	- `product_url`: the URL to fetch (required, unless user pastes a description directly)
56	- `product_name`: optional, derived from page if not provided
57	- `geography`: optional -- US / Europe / global. Default: US
58
59	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`.
60
61	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 is for, and what makes it different from competitors."
62
63	Derive product slug:
64
65	```bash
66	PRODUCT_SLUG=$(python3 -c "
67	from urllib.parse import urlparse
68	import sys
69	url = 'URL_HERE'
70	if url.startswith('http'):
71	host = urlparse(url).netloc.replace('www.', '')
72	print(host.split('.')[0])
73	else:
74	import re
75	print(re.sub(r'[^a-z0-9]', '-', url[:30].lower()).strip('-'))
76	")
77	echo "Product slug: $PRODUCT_SLUG"
78	```
79
80	---
81
82	## Step 3: Fetch Product Page
83
84	Primary: Firecrawl (if FIRECRAWL_API_KEY is set)
85
86	```bash
87	curl -s -X POST https://api.firecrawl.dev/v1/scrape \
88	-H "Authorization: Bearer $FIRECRAWL_API_KEY" \
89	-H "Content-Type: application/json" \
90	-d '{"url": "URL_HERE", "formats": ["markdown"], "onlyMainContent": true}' \
91	\| python3 -c "
92	import sys, json
93	d = json.load(sys.stdin)
94	content = d.get('data', {}).get('markdown', '') or d.get('markdown', '')
95	print(f'Fetched via Firecrawl: {len(content)} characters')
96	open

People who liked this also viewed

6 picks

Type