Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Search and retrieve content from Product Hunt. Get posts, topics, users, and collections via the GraphQL API. Use when user mentions Product Hunt, PH, or product launches.
.claude/skills/producthunt/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-14 | ✗→✓ | ▲ Improved | — | — |
| case-16 | ✗→✓ | ▲ Improved | — | — |
| case-21 | ✗→✓ | ▲ Improved | — | — |
| case-15 | ✗→✓ | ▲ Improved | — | — |
| case-20 | ✓→✓ | ＝ Same ✓ | — | — |
Get posts, topics, users, and collections from Product Hunt via the official GraphQL API.
Set access token in ~/.zshrc:
bashexport PRODUCTHUNT_ACCESS_TOKEN="your_developer_token"
Get your token from: https://www.producthunt.com/v2/oauth/applications
Quick Check:
bashcd <skill_directory> python3 scripts/get_posts.py --limit 3
All commands run from the skill directory.
bashpython3 scripts/get_post.py chatgpt # Get post by slug python3 scripts/get_post.py 12345 # Get post by ID python3 scripts/get_posts.py --limit 20 # Today's featured posts python3 scripts/get_posts.py --topic ai --limit 10 # Posts in topic python3 scripts/get_posts.py --after 2026-01-01 # Posts after date python3 scripts/get_post_comments.py POST_ID --limit 20
bashpython3 scripts/get_topic.py artificial-intelligence # Get topic by slug python3 scripts/get_topics.py --query "AI" --limit 20 # Search topics python3 scripts/get_topics.py --limit 50 # Popular topics
bashpython3 scripts/get_user.py rrhoover # Get user by username python3 scripts/get_user_posts.py rrhoover --limit 20 # User's posts
bashpython3 scripts/get_collection.py SLUG_OR_ID # Get collection python3 scripts/get_collections.py --featured --limit 20
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 7 counted toward the lift figure. The other 15 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +18 percentage points is the difference between those two pass rates over the 7 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.