Skip to content
Back to skills

Community Check

ASecurity

Before you adopt a tool or technique, find out what the daily.dev community actually thinks. Reads the most-discussed posts and their comment threads on a topic and summarizes the consensus, the dissent, and the gotchas, with sources.

  • 8 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added October 17, 2026
ai-agentsgorailsapiperformance

Works with

  • api
  • mcp

Security analysis

A100/100

Scanned October 17, 2026

npx -y skills add dailydotdev/marketplace --skill community-check --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Community Check?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Community Check
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/dailydotdev-community-check/badge)](https://www.skillsdirectory.com/skills/dailydotdev-community-check)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: community-check
description: Before you adopt a tool or technique, find out what the daily.dev community actually thinks. Reads the most-discussed posts and their comment threads on a topic and summarizes the consensus, the dissent, and the gotchas, with sources.
---

# Community Check

Answer the question "what do developers on daily.dev actually think about X?" by reading discussions, not just articles. Articles tell you what authors claim; comment threads tell you what happened in production.

## Requirements

One of:

- The daily.dev MCP server (`https://api.daily.dev/mcp`) connected to your agent, or
- A daily.dev personal access token in `DAILY_DEV_TOKEN` (create one at https://daily.dev/settings/api). Base URL `https://api.daily.dev/public/v1`, header `Authorization: Bearer $DAILY_DEV_TOKEN`. Never send the token anywhere except `api.daily.dev`.

Each step below lists the MCP tool first and the REST call after it.

## Steps

1. **Find the posts.** Run both and merge:
   - `getSearchPosts` with `q` set to the topic and `limit` 15 (REST: `GET /search/posts?q=<topic>&limit=15`).
   - `getFeedsDiscussed` with `limit` 20 and `period` 30, filtered with `tag` when the topic is a known tag (REST: `GET /feeds/discussed?limit=20&period=30&tag=<tag>`). Use `getSearchTags` (`GET /search/tags?q=`) to confirm the tag name first.
2. **Pick the conversations.** From the merged list keep the 4–6 posts with the most `numComments`. Ignore posts with fewer than 3 comments.
3. **Read the threads.** For each kept post call `getPostsByIdComments` with `limit` 30 (REST: `GET /posts/{id}/comments?limit=30`). Read replies too, they are nested under `children`.
4. **Synthesize.** Group what you read into:
   - **Consensus**: claims repeated across threads by different people.
   - **Dissent**: credible disagreement, with the strongest version of the argument.
   - **Gotchas from production**: specific failures, migrations, costs, performance numbers.
   - **Open questions**: things people asked that nobody answered well.
5. **Cite.** Every claim gets the post title linked to its `commentsPermalink`. Quote comments sparingly and attribute them by `author.username`.

## Output

Keep it under 400 words unless asked for more. Lead with a one-sentence verdict, then the four groups, then a "Sources" list. Include upvote and comment counts next to each source so the reader can judge weight.

## Guardrails

- Read-only. Don't upvote, bookmark or comment.
- If fewer than two posts have real discussion, say so instead of inventing a consensus.
- Each call uses one request of the user's daily.dev API quota. Stay under ~10 calls per check.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.