gh-issue-to-demand-signal

name	gh-issue-to-demand-signal
description	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. Use when asked to scan a competitor's GitHub issues, find what their users are begging for, turn GitHub complaints into product positioning, identify competitor feature gaps, or generate messaging from real user demand. Trigger when a user says "scan competitor issues", "what are users asking for on X repo", "find demand gaps in Y", "turn GitHub issues into messaging", or "what should I build based on competitor complaints".
compatibility	["claude-code","gemini-cli","github-copilot"]

GitHub Issue Demand Signal

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.

---

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.

---

Common Mistakes

The agent will want to...	Why that's wrong
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.
Use comment count as the primary demand signal	Comments include maintainer responses, off-topic discussion, and spam. reactions["+1"] is the cleanest buyer signal.
Paraphrase issue titles when summarizing clusters	Paraphrasing loses the buyer's exact language, which is the entire point. Use verbatim issue titles.
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.
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.
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.

---

Step 1: Setup Check

echo "GITHUB_TOKEN: ${GITHUB_TOKEN:-not set, unauthenticated rate limit applies (60 req/hr)}"

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)."

---

Step 2: Gather Input

You need:

• GitHub repo URL (e.g. https://github.com/owner/repo) or owner/repo slug (e.g. facebook/react)

Parse owner and repo from input:

python3 << 'PYEOF'
import re, sys, os

raw = "REPO_INPUT_HERE"

# Normalize to owner/repo
if raw.startswith("http"):
    m = re.search(r"github\.com/([^/]+)/([^/?\s]+)", raw)
    if not m:
        print("ERROR: Could not parse GitHub URL. Expected format: https://github.com/owner/repo")
        sys.exit(1)
    owner, repo = m.group(1), m.group(2).rstrip("/")
elif "/" in raw:
    parts = raw.strip().split("/")
    owner, repo = parts[0], parts[1]
else:
    print("ERROR: Input must be a GitHub URL or owner/repo slug (e.g. vercel/next.js)")
    sys.exit(1)

print(f"Owner: {owner}")
print(f"Repo: {repo}")

with open("/tmp/ghd-target.txt", "w") as f:
    f.write(f"{owner}/{repo}")
PYEOF

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)."

---

Step 3: Fetch Issues from GitHub REST API

Fetch up to 200 issues (2 pages of 100). Check rate limit after the first fetch.

python3 << 'PYEOF'
import json, urllib.request, os, sys
from datetime import datetime, timezone

target = open("/tmp/ghd-target.txt").read().strip()
owner_repo = target
token = os.environ.get("GITHUB_TOKEN", "")

headers = {"Accept": "application/vnd.github+json", "User-Agent": "gh-issue-demand-signal/1.0"}
if token:
    headers["Authorization"] = f"Bearer {token}"

all_issues = []
rate_limit_hit = False

for page in [1, 2]:
    url = f"https://api.github.com/repos/{owner_repo}/issues?state=open&per_page=100&page={page}"
    req = urllib.request.Request(url, headers=headers)

    try:
        with urllib.request.urlopen(req, timeout=30) as resp:
            # Check rate limit after first page
            if page == 1:
                remaining = int(resp.headers.get("X-RateLimit-Remaining", 999))
                reset_ts = resp.headers.get("X-RateLimit-Reset", "")
                if remaining == 0:
                    reset_str = datetime.fromtimestamp(int(reset_ts), tz=timezone.utc).strftime("%H:%M UTC") if reset_ts else "unknown"
                    print(f"ERROR: GitHub rate limit exhausted. Resets at {reset_str}.")
                    print("Add GITHUB_TOKEN to your .env file to get 5000 req/hr. See github.com/settings/tokens (no scopes needed).")
                    sys.exit(1)
                print(f"Rate limit remaining: {remaining}")

                # Check for 404/403
                status = resp.status
                if status == 404:
                    print(f)
                    sys.exit(1)

            page_data = json.loads(resp.read())
             not page_data:
                (f)
                
            all_issues.extend(page_data)
            (f)
    except urllib.error.HTTPError as e:
         e.code == 404:
            (f)
         e.code == 403:
            (f)
        :
            (f)
        sys.exit(1)
    except Exception as e:
        (f)
        sys.exit(1)

(f)
json.dump(all_issues, open(, ), indent=2)
PYEOF

If GitHub returns 404: Stop. Tell the user: "Repo not found. Check the URL or slug and try again. Private repos are not accessible without authentication and explicit repo scope."

If GitHub returns 403 with rate limit header: Stop. Show the reset time and tell the user to add GITHUB_TOKEN.

---

Step 4: Pre-Process Locally -- Filter, Score, Detect Ignored Demand

No API call. Pure Python. Run before anything goes to the AI.

python3 << 'PYEOF'
import json, re
from datetime import datetime, timezone

raw = json.load(open("/tmp/ghd-raw-issues.json"))
target = open("/tmp/ghd-target.txt").read().strip()
now = datetime.now(tz=timezone.utc)

noise_patterns = re.compile(
    r"^(chore|deps|bump|renovate|dependabot|release|ci|build|revert)[\s:\[]",
    re.IGNORECASE
)
pr_title_patterns = re.compile(
    r"^(feat|fix|refactor|docs|test|style|perf|chore)(\(.+\))?:",
    re.IGNORECASE
)

filtered = []
noise_count = 0
noise_reasons = {}

for issue in raw:
    # Skip pull requests (GitHub Issues endpoint returns PRs too)
    if "pull_request" in issue:
        noise_count += 1
        noise_reasons["pull_request"] = noise_reasons.get("pull_request", 0) + 1
        continue

    title = issue.get("title", "")
    reactions = issue.get("reactions", {}).get("+1", 0)
    comments = issue.get("comments", 0)
    user_type = (issue.get("user") or {}).get("type", "User")

    # Skip bot-authored issues
    if user_type == "Bot":
        noise_count += 1
        noise_reasons["bot_author"] = noise_reasons.get("bot_author", 0) + 1
        continue

    # Skip bot-pattern titles
    if noise_patterns.match(title):
        noise_count += 1
        noise_reasons["bot_title"] = noise_reasons.get("bot_title", 0) + 1
        continue

    # Skip PR-as-issue titles
    if pr_title_patterns.match(title):
        noise_count += 1
        noise_reasons["pr_as_issue"] = noise_reasons.get(, 0) + 1
        

    
     reactions == 0 and comments == 0:
        noise_count += 1
        noise_reasons[] = noise_reasons.get(, 0) + 1
        

    
    demand_score = (reactions * 2) + (comments * 0.5)

    
    created_at = issue.get(, )
     created_at:
        created = datetime.fromisoformat(created_at.replace(, ))
        age_days = (now - created).days
    :
        age_days = 0

    labels = [l.get(, ).lower()  l  issue.get(, [])]
    has_planned_label = any(
        kw  label  label  labels
         kw  [, , , , ]
    )

    ignored_demand = (
        reactions >= 10 and
        age_days >= 180 and
        not has_planned_label
    )

    filtered.append({
        : issue[],
        : title,
        : issue.get(, f),
        : reactions,
        : comments,
        : demand_score,
        : age_days,
        : labels,
        : ignored_demand,
        : (issue.get() or )[:300]
    })


filtered.sort(key=lambda x: x[], reverse=True)

(f)
(f)
(f)

 len(filtered) < 10:
    (f)
    ()
    import sys; sys.exit(1)


ignored = [i  i  filtered  i[]]
(f)

json.dump(filtered, open(, ), indent=2)
()
PYEOF

If fewer than 10 issues remain after filtering: Stop. Tell the user exactly how many issues were found and filtered, and why the repo is too small for reliable demand clustering.

---

Step 5: Cluster Issues

Print the filtered issues for analysis:

python3 << 'PYEOF'
import json
filtered = json.load(open("/tmp/ghd-filtered-issues.json"))
target = open("/tmp/ghd-target.txt").read().strip()

issue_list = filtered[:150]
print(f"Repo: {target}")
print(f"Issues to cluster: {len(issue_list)}")
print()
for i in issue_list:
    labels_str = f" [{', '.join(i['labels'][:3])}]" if i['labels'] else ""
    print(f"#{i['number']} [score:{round(i['demand_score'],1)} reactions:{i['reactions_plus1']}] {i['title']}{labels_str}")
PYEOF

Classify each issue printed above into one of these 6 categories: feature_gap, bug_pattern, ux_complaint, performance, integration_missing, docs_missing

Rules:

• Classify each issue into exactly one category
• Extract a 1-sentence pain statement using the user's exact language from the title -- do not paraphrase
• Identify 5-8 cluster themes: short phrases (3-6 words) capturing dominant complaint patterns across all issues
• No em dashes. No marketing language.

Write your analysis to /tmp/ghd-clusters.json with this exact structure:

{
  "classified_issues": [
    {"number": 123, "category": "feature_gap", "pain_statement": "Users need X which does not exist yet"}
  ],
  "cluster_themes": [
    {"theme_name": "Missing export options", "category": "feature_gap", "issue_numbers": [123, 456, 789]}
  ],
  "category_counts": {"feature_gap": 5, "bug_pattern": 3, "ux_complaint": 4,      

After writing the file, confirm with:

python3 -c "
import json
d = json.load(open('/tmp/ghd-clusters.json'))
print(f'Classified: {len(d[\"classified_issues\"])} issues, {len(d[\"cluster_themes\"])} themes')
print('Categories:', d['category_counts'])
"

---

Step 6: Messaging Brief

Compute total demand score per cluster and print the top 3:

python3 << 'PYEOF'
import json

filtered = json.load(open("/tmp/ghd-filtered-issues.json"))
clusters = json.load(open("/tmp/ghd-clusters.json"))
target = open("/tmp/ghd-target.txt").read().strip()

demand_by_issue = {i["number"]: i["demand_score"] for i in filtered}
issue_titles = {i["number"]: i["title"] for i in filtered}
issue_reactions = {i["number"]: i["reactions_plus1"] for i in filtered}

enriched_themes = []
for theme in clusters.get("cluster_themes", []):
    issue_nums = theme.get("issue_numbers", [])
    total_demand = sum(demand_by_issue.get(n, 0) for n in issue_nums)
    top_issues = sorted(issue_nums, key=lambda n: demand_by_issue.get(n, 0), reverse=True)[:3]
    enriched_themes.append({
        "theme_name": theme["theme_name"],
        "category": theme["category"],
        "issue_count": len(issue_nums),
        "total_demand_score": round(total_demand, 1),
        "top_issues": [
            {"number": n, "title": issue_titles.get(n, ""), "reactions": issue_reactions.get(n, 0)}
            for n in top_issues
        ]
    })

enriched_themes.sort(key=lambda x: x["total_demand_score"], reverse=True)
json.dump(enriched_themes, open("/tmp/ghd-enriched-themes.json", "w"), indent=2)

print(f)
 t  enriched_themes[:3]:
    (f)
     ti  t[]:
        (f)
PYEOF

Generate a GTM messaging brief from the top 3 clusters printed above.

Rules:

• Each positioning angle must cite the specific cluster it comes from
• Each outreach hook must quote a verbatim issue title in quotation marks
• Headlines must include a number or specific named pain -- no generic statements
• No em dashes. No forbidden words: powerful, robust, seamless, innovative, game-changing, streamline, leverage, transform

Write your brief to /tmp/ghd-brief.json with this exact structure:

{
  "positioning_angles": [
    {
      "angle_name": "3-5 word label",
      "cluster_source": "theme_name from cluster",
      "positioning_statement": "2-3 sentences on what your product does that this competitor does not",
      "evidence": "verbatim issue title that best illustrates this gap"
    }
  ],
  "outreach_hooks": [
    {
      "hook_type": "pain quote hook",
      "hook_text": "2-3 sentences quoting a verbatim issue title in quotes",
      "best_for": "audience this hook works for"
    }
  ],
  "cluster_headlines": [
    {
      "theme_name": "from the cluster",
      "headline": "specific headline with a number or named pain"
       
    
  

After writing the file, confirm with:

python3 -c "
import json
d = json.load(open('/tmp/ghd-brief.json'))
print('Positioning angles:', len(d.get('positioning_angles', [])))
print('Outreach hooks:', len(d.get('outreach_hooks', [])))
print('Cluster headlines:', len(d.get('cluster_headlines', [])))
"

---

Step 7: Self-QA

Run before presenting. Verify evidence. Remove violations. Check output integrity.

python3 << 'PYEOF'
import json

filtered = json.load(open("/tmp/ghd-filtered-issues.json"))
clusters = json.load(open("/tmp/ghd-clusters.json"))
themes = json.load(open("/tmp/ghd-enriched-themes.json"))
brief = json.load(open("/tmp/ghd-brief.json"))
target = open("/tmp/ghd-target.txt").read().strip()

failures = []
real_titles = {i["number"]: i["title"] for i in filtered}

# Verify: classified_issues only reference real issue numbers
real_numbers = set(real_titles.keys())
hallucinated = [
    c["number"] for c in clusters.get("classified_issues", [])
    if c["number"] not in real_numbers
]
if hallucinated:
    failures.append(f"Removed {len(hallucinated)} hallucinated issue numbers from classified_issues: {hallucinated[:5]}")
    clusters["classified_issues"] = [
        c for c in clusters.get("classified_issues", [])
        if c["number"] in real_numbers
    ]

# Verify: top-10 list is sorted by demand_score descending
top10 = filtered[:10]
for i, issue in enumerate(top10):
    if i > 0 and issue["demand_score"] > top10[i-1]["demand_score"]:
        failures.append("Top-10 list was not sorted by demand_score -- re-sorted.")
        filtered.sort(key=lambda x: x["demand_score"], reverse=True)
        top10 = filtered[:10]
        break

# Verify: ignored demand issues meet all 3 criteria
ignored = [i  i  filtered  i[]]
 issue  ignored:
     issue[] < 10 or issue[] < 180:
        issue[] = False
        failures.append(f)


 len(brief.get(, [])) != 3:
    failures.append(f)
 len(brief.get(, [])) != 3:
    failures.append(f)
 len(brief.get(, [])) != 3:
    failures.append(f)


brief_str = json.dumps(brief)
   brief_str:
    brief_str = brief_str.replace(, )
    brief = json.loads(brief_str)
    failures.append()


forbidden = [, , , , , , , ]
full_text = (json.dumps(clusters) + json.dumps(brief)).lower()
 word  forbidden:
     word  full_text:
        failures.append(f)


output = {
    : target,
    : len(filtered),
    : clusters,
    : themes,
    : filtered,
    : brief,
    : failures
}

json.dump(output, open(, ), indent=2)
(f)
 f  failures:
    (f)
 not failures:
    ()
PYEOF

---

Step 8: Save and Present Output

python3 << 'PYEOF'
import json
from datetime import datetime, timezone

output = json.load(open("/tmp/ghd-output.json"))
target = output["repo"]
repo_slug = target.replace("/", "-")
date_str = datetime.now(tz=timezone.utc).strftime("%Y-%m-%d")

filtered = output["filtered_issues"]
themes = output["enriched_themes"]
clusters = output["clusters"]
brief = output["messaging_brief"]
flags = output["data_quality_flags"]

ignored = [i for i in filtered if i.get("ignored_demand")]
top10 = filtered[:10]

# Build category summary from cluster data
category_counts = clusters.get("category_counts", {})

lines = [
    f"## Demand Gap Report: {target}",
    f"Issues analyzed: {output['issues_analyzed']} | Date: {date_str}",
    "",
    "---",
    "",
    "### Demand Gap Leaderboard",
    "",
    "| Rank | Theme | Category | Issues | Total Demand Score | Top Issue Reactions |",
    "|---|---|---|---|---|---|",
]

for i, theme in enumerate(themes[:8], 1):
    top_reactions = theme["top_issues"][0]["reactions"] if theme["top_issues"] else 0
    lines.append(
        f"| {i} | {theme['theme_name']} | {theme['category']} | "
        f"{theme['issue_count']} | {theme['total_demand_score']} | {top_reactions} |"
    )

lines += ["", "---", ""]

if ignored:
    lines += [
        "### Ignored Demand (High Reactions, No Maintainer Response)",
        ,
        ,
        ,
        ,
    ]
     issue  ignored[:10]:
        lines.append(
            f
            f
        )
    lines += [, , ]

lines += [
    ,
    ,
    ,
    ,
]
 i, issue  enumerate(top10, 1):
    short_title = issue[][:70] + (  len(issue[]) > 70  )
    lines.append(
        f
        f
        f
    )

lines += [, , , , ]

 theme  themes[:3]:
    lines.append(f)
    lines.append(f)
    lines.append()
    lines.append()
     ti  theme[]:
        lines.append(f)
    lines.append()

lines += [, , , ]

 angle  brief.get(, []):
    lines.append(f)
    lines.append(angle.get(, ))
    lines.append(f)
    lines.append()

lines += [, , , ]

 hook  brief.get(, []):
    lines.append(f)
    lines.append(hook.get(, ))
    lines.append(f)
    lines.append()

lines += [, ]
 flags:
    lines.append(f)
:
    lines.append()

output_path = f
import os
os.makedirs(, exist_ok=True)
open(output_path, ).write(.(lines))
(f)


( + .(lines))
PYEOF

Clean up temp files:

rm -f /tmp/ghd-target.txt /tmp/ghd-raw-issues.json /tmp/ghd-filtered-issues.json \
      /tmp/ghd-cluster-request.json /tmp/ghd-clusters.json /tmp/ghd-enriched-themes.json \
      /tmp/ghd-brief-request.json /tmp/ghd-brief.json /tmp/ghd-output.json