
Last 30 Days Community Research
Gathers recent social and community reactions on a topic and writes a sourced Markdown briefing.
- Repository
- nexu-io/open-design
- Stars
- 105,448
- Licence
- Apache-2.0
- Files
- 15 files
What it does
When you ask about what people are saying lately, this skill tells the agent to run a bundled Python research engine that searches recent community and social sources for the last 30 days. The agent then reads the results, separates praise from criticism, notes which sources were actually checked, and saves a Markdown report in your Design Files folder with citations. It treats online content as untrusted evidence rather than instructions.
Great for
- Marketers checking launch reaction or social proof for a product
- Creators scanning what communities are discussing in their niche this month
- Researchers who want a quick, citation-backed snapshot of recent sentiment
Skip it if
- Authoritative or historical research, since it only covers the last 30 days and social sources can be unrepresentative or biased
- Situations needing sources the engine cannot reach; coverage varies and unavailable sources are labelled rather than filled in
- Use with private or sensitive topics, since the engine sends search queries to external services
Try asking
- “Run a last30days scan on community reaction to our new pricing change”
- “What are people saying about open-source design tools in the last 30 days?”
- “Give me a trend scan on AI image generators and save the briefing”
- “Create a shareable HTML brief of recent sentiment about our product launch”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 15 original files, the Apache-2.0 licence and an attribution note.
last30days.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip last30days.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip last30days.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Provide a specific topic and date window so the search and report stay focused.
- Check the Source Coverage table in the report to see which sources were really checked before relying on findings.
- Keep credentials in the local .env config only; the skill does not bundle API keys, but it can read cookies from your browser, so review that behavior before enabling it.
What's inside
- references/save-html-brief.md
- scripts/briefing.py
- scripts/last30days.py
- scripts/lib/__init__.py
- scripts/lib/bird_x.py
- scripts/lib/bluesky.py
- scripts/lib/categories.py
- scripts/lib/chrome_cookies.py
- scripts/lib/cluster.py
- scripts/lib/competitors.py
- scripts/lib/cookie_extract.py
- scripts/lib/dates.py
- scripts/lib/dedupe.py
- scripts/lib/entity_extract.py
- SKILL.md
Redistributed unmodified from nexu-io/open-design under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.