gh-issue-to-demand-signal

Name: gh-issue-to-demand-signal
Author: Varnan-Tech

20installs59forks

How to install gh-issue-to-demand-signal?

varnan-tech/opendirectory/gh-issue-to-demand-signal

$npx -y skills add Varnan-Tech/opendirectory --skill gh-issue-to-demand-signal

Installs into the current project.

Summary

Takes a competitor's public GitHub repo URL, fetches their open issues via the GitHub REST API, filters noise locally, clusters issues into 6 demand categories, computes a demand score per issue and per cluster, and outputs a ranked demand gap report with a GTM messaging brief. U

Files · 1

View on GitHub

SKILL.md

1	# GitHub Issue Demand Signal
2
3	Take a competitor's public GitHub repo. Fetch their open issues. Filter noise locally. Cluster into 6 demand categories. Score by real engagement. Output a ranked demand gap report and GTM messaging brief.
4
5	---
6
7	Critical rule: Every issue title in the output must be verbatim from the GitHub API response. Every cluster theme name must be derived from actual issue titles in that cluster. If fewer than 10 issues remain after noise filtering, stop and tell the user -- the repo is too small for reliable clustering. No invented issue content anywhere.
8
9	---
10
11	## Common Mistakes
12
13	\| The agent will want to... \| Why that's wrong \|
14	\|---\|---\|
15	\| Send all 200 raw issues to the AI without filtering \| Bot issues, PRs, and zero-engagement noise inflate cluster counts and waste context. Filter locally first. \|
16	\| Use comment count as the primary demand signal \| Comments include maintainer responses, off-topic discussion, and spam. reactions["+1"] is the cleanest buyer signal. \|
17	\| Paraphrase issue titles when summarizing clusters \| Paraphrasing loses the buyer's exact language, which is the entire point. Use verbatim issue titles. \|
18	\| Continue past Step 4 if fewer than 10 issues remain after filtering \| Under 10 issues means the repo is too small or the wrong URL was given. Clustering on sparse data produces meaningless categories. \|
19	\| Include pull requests in the analysis \| The GitHub Issues endpoint returns PRs too. Filter by checking that the pull_request key is absent on the issue object. \|
20	\| Mark an issue as ignored demand without checking all 3 criteria \| All three must be true: reactions >= 10, age >= 180 days, no planned/in-progress/roadmap label. Missing one criterion disqualifies the issue. \|
21
22	---
23
24	## Step 1: Setup Check
25
26	```bash
27	echo "GITHUB_TOKEN: ${GITHUB_TOKEN:-not set, unauthenticated rate limit applies (60 req/hr)}"
28	```
29
30	If GITHUB_TOKEN is not set: Continue. Tell the user: "GITHUB_TOKEN is not set. Unauthenticated rate limit is 60 requests/hour -- enough for 2 fetches before hitting the limit. For repeated use, add a token at github.com/settings/tokens (no scopes needed for public repos)."
31
32	---
33
34	## Step 2: Gather Input
35
36	You need:
37	- GitHub repo URL (e.g. https://github.com/owner/repo) or owner/repo slug (e.g. facebook/react)
38
39	Parse owner and repo from input:
40
41	```bash
42	python3 << 'PYEOF'
43	import re, sys, os
44
45	raw = "REPO_INPUT_HERE"
46
47	# Normalize to owner/repo
48	if raw.startswith("http"):
49	m = re.search(r"github\.com/([^/]+)/([^/?\s]+)", raw)
50	if not m:
51	print("ERROR: Could not parse GitHub URL. Expected format: https://github.com/owner/repo")
52	sys.exit(1)
53	owner, repo = m.group(1), m.group(2).rstrip("/")
54	elif "/" in raw:
55	parts = raw.strip().split("/")
56	owner, repo = parts[0], parts[1]
57	else:
58	print("ERROR: Input must be a GitHub URL or owner/repo slug (e.g. vercel/next.js)")
59	sys.exit(1)
60
61	print(f"Owner: {owner}")
62	print(f"Repo: {repo}")
63
64	with open("/tmp/ghd-target.txt", "w") as f:
65	f.write(f"{owner}/{repo}")
66	PYEOF
67	```
68
69	If parsing fails: Stop. Ask: "Please provide the GitHub repo as a URL (https://github.com/owner/repo) or an owner/repo slug (e.g. vercel/next.js)."
70
71	---
72
73	## Step 3: Fetch Issues from GitHub REST API
74
75	Fetch up to 200 issues (2 pages of 100). Check rate limit after the first fetch.
76
77	```bash
78	python3 << 'PYEOF'
79	import json, urllib.request, os, sys
80	from datetime import datetime, timezone
81
82	target = open("/tmp/ghd-target.txt").read().strip()
83	owner_repo = target
84	token = os.environ.get("GITHUB_TOKEN", "")
85
86	headers = {"Accept": "application/vnd.github+json", "User-Agent": "gh-issue-demand-signal/1.0"}
87	if token:
88	headers["Authorization"] = f"Bearer {token}"
89
90	all_issues = []
91	rate_limit_hit = False
92
93	for page in [1, 2]:
94	url = f"https://api.github.com/repos/{owner_repo}/issues?state=open&per_page=100&page={page}"
95	req = urllib.request.Request(url, headers=headers)
96
97	try:
98	with urllib.request.urlopen(req, timeout=30) as resp:
99	# Check rate limit after first page
100	if page == 1:
101	remaining = int(resp.headers.get("X-RateLimit-Remaining", 999))
102	reset_ts = resp.headers.get(

People who liked this also viewed

6 picks

Type

gh-issue-to-demand-signal

20installs59forks

View on GitHub

How to install gh-issue-to-demand-signal?

varnan-tech/opendirectory/gh-issue-to-demand-signal

$npx -y skills add Varnan-Tech/opendirectory --skill gh-issue-to-demand-signal

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# GitHub Issue Demand Signal
2
3	Take a competitor's public GitHub repo. Fetch their open issues. Filter noise locally. Cluster into 6 demand categories. Score by real engagement. Output a ranked demand gap report and GTM messaging brief.
4
5	---
6
7	Critical rule: Every issue title in the output must be verbatim from the GitHub API response. Every cluster theme name must be derived from actual issue titles in that cluster. If fewer than 10 issues remain after noise filtering, stop and tell the user -- the repo is too small for reliable clustering. No invented issue content anywhere.
8
9	---
10
11	## Common Mistakes
12
13	\| The agent will want to... \| Why that's wrong \|
14	\|---\|---\|
15	\| Send all 200 raw issues to the AI without filtering \| Bot issues, PRs, and zero-engagement noise inflate cluster counts and waste context. Filter locally first. \|
16	\| Use comment count as the primary demand signal \| Comments include maintainer responses, off-topic discussion, and spam. reactions["+1"] is the cleanest buyer signal. \|
17	\| Paraphrase issue titles when summarizing clusters \| Paraphrasing loses the buyer's exact language, which is the entire point. Use verbatim issue titles. \|
18	\| Continue past Step 4 if fewer than 10 issues remain after filtering \| Under 10 issues means the repo is too small or the wrong URL was given. Clustering on sparse data produces meaningless categories. \|
19	\| Include pull requests in the analysis \| The GitHub Issues endpoint returns PRs too. Filter by checking that the pull_request key is absent on the issue object. \|
20	\| Mark an issue as ignored demand without checking all 3 criteria \| All three must be true: reactions >= 10, age >= 180 days, no planned/in-progress/roadmap label. Missing one criterion disqualifies the issue. \|
21
22	---
23
24	## Step 1: Setup Check
25
26	```bash
27	echo "GITHUB_TOKEN: ${GITHUB_TOKEN:-not set, unauthenticated rate limit applies (60 req/hr)}"
28	```
29
30	If GITHUB_TOKEN is not set: Continue. Tell the user: "GITHUB_TOKEN is not set. Unauthenticated rate limit is 60 requests/hour -- enough for 2 fetches before hitting the limit. For repeated use, add a token at github.com/settings/tokens (no scopes needed for public repos)."
31
32	---
33
34	## Step 2: Gather Input
35
36	You need:
37	- GitHub repo URL (e.g. https://github.com/owner/repo) or owner/repo slug (e.g. facebook/react)
38
39	Parse owner and repo from input:
40
41	```bash
42	python3 << 'PYEOF'
43	import re, sys, os
44
45	raw = "REPO_INPUT_HERE"
46
47	# Normalize to owner/repo
48	if raw.startswith("http"):
49	m = re.search(r"github\.com/([^/]+)/([^/?\s]+)", raw)
50	if not m:
51	print("ERROR: Could not parse GitHub URL. Expected format: https://github.com/owner/repo")
52	sys.exit(1)
53	owner, repo = m.group(1), m.group(2).rstrip("/")
54	elif "/" in raw:
55	parts = raw.strip().split("/")
56	owner, repo = parts[0], parts[1]
57	else:
58	print("ERROR: Input must be a GitHub URL or owner/repo slug (e.g. vercel/next.js)")
59	sys.exit(1)
60
61	print(f"Owner: {owner}")
62	print(f"Repo: {repo}")
63
64	with open("/tmp/ghd-target.txt", "w") as f:
65	f.write(f"{owner}/{repo}")
66	PYEOF
67	```
68
69	If parsing fails: Stop. Ask: "Please provide the GitHub repo as a URL (https://github.com/owner/repo) or an owner/repo slug (e.g. vercel/next.js)."
70
71	---
72
73	## Step 3: Fetch Issues from GitHub REST API
74
75	Fetch up to 200 issues (2 pages of 100). Check rate limit after the first fetch.
76
77	```bash
78	python3 << 'PYEOF'
79	import json, urllib.request, os, sys
80	from datetime import datetime, timezone
81
82	target = open("/tmp/ghd-target.txt").read().strip()
83	owner_repo = target
84	token = os.environ.get("GITHUB_TOKEN", "")
85
86	headers = {"Accept": "application/vnd.github+json", "User-Agent": "gh-issue-demand-signal/1.0"}
87	if token:
88	headers["Authorization"] = f"Bearer {token}"
89
90	all_issues = []
91	rate_limit_hit = False
92
93	for page in [1, 2]:
94	url = f"https://api.github.com/repos/{owner_repo}/issues?state=open&per_page=100&page={page}"
95	req = urllib.request.Request(url, headers=headers)
96
97	try:
98	with urllib.request.urlopen(req, timeout=30) as resp:
99	# Check rate limit after first page
100	if page == 1:
101	remaining = int(resp.headers.get("X-RateLimit-Remaining", 999))
102	reset_ts = resp.headers.get(

People who liked this also viewed

6 picks

Type