SkillAgentSearch skills...

qa

The encyclopedia for MCP servers. Browse, compare, and evaluate 17,800+ Model Context Protocol servers with transparent, automated scoring.

Install / Use

npx skills add BbekShr/MCPpedia

Installs into whichever agent you are using.

About this skill
⚡

Claude Commands

Claude Code slash commands

Quality Score

69/100

Category

Automation

Supported Platforms

Claude Code

Our assessment of qa

qa scores 69/100 on our quality scale, 2683rd of 2,902 Automation skills we index.

Its Claude Commands is 3.0 KB long, well organised into 17 sections and no code examples: a solid amount of guidance for an agent.

It has no GitHub stars yet, so there is no community track record; judge it on its content.

Substance
26/30
Structure
13/20
Description
15/15
Adoption
0/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated yesterday, so qa is actively maintained.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 80/100, with 2 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands.

Automated pattern scan on 2026-10-18. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

qa compared with similar skills

All 4 of these similar skills score higher than qa; compare them before choosing.

SkillScoreStarsUpdatedFormat
qa (this skill)by BbekShr6901d agoClaude Commands
claude-memby thedotmack100101.5ktodayCLAUDE.md
Agent-Reachby Panniantong10098.9k3d agoCLAUDE.md
taste-skillby Leonxlnx10098.7ktodayCLAUDE.md
Understand-Anythingby Egonex-AI10086.9k6d agoCLAUDE.md

Frequently asked questions

How do I install qa?
Run npx skills add BbekShr/MCPpedia. The install tabs above show the steps for each supported agent.
Which AI agents does qa work with?
It is written for Claude Code, as a Claude Commands file. Other agents that read the same format can often use it too.
Is qa safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. It declares no license and scores 80/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is qa still maintained?
The repository was last updated yesterday, so qa is actively maintained.

QA MCPpedia

Run QA testing across the MCPpedia app — unit tests, build verification, and E2E browser checks.

Instructions

Step 1: Run unit tests

Run npm test to execute the Vitest test suite. If any tests fail, investigate and fix them before continuing.

Step 2: Run build

Run npm run build to verify no TypeScript or build errors. If the build fails, fix the errors.

Step 3: Start dev server

Kill any existing dev server on port 3000 (lsof -ti:3000 | xargs kill -9), clear the .next cache, and start a fresh dev server with npm run dev in the background.

Step 4: E2E browser tests with Playwright MCP

Once the dev server is ready at http://localhost:3000, run through these test scenarios using the Playwright MCP browser tools:

4a. Homepage

  • Navigate to http://localhost:3000
  • Take a snapshot and verify: heading text, search bar, server cards rendered, no error messages

4b. Search

  • Navigate to http://localhost:3000/servers?q=supabase
  • Take a snapshot and verify: search results appear, count is NOT "0 servers matching" (if results are visible), filter pills are rendered

4c. Score filter with search

  • Navigate to http://localhost:3000/servers?q=supabase&min_score=80
  • Take a snapshot and verify: only servers with score >= 80 shown, count matches visible results

4d. Server detail page

  • Navigate to http://localhost:3000/s/supabase (or the first server from search results)
  • Take a snapshot and verify: server name, score badge, security section, README section all render

4e. Category page

  • Navigate to http://localhost:3000/category/developer-tools
  • Take a snapshot and verify: servers listed, no archived servers visible (check for "archived" health status)

4f. Blog page

  • Navigate to http://localhost:3000/blog
  • Take a snapshot and verify: blog posts listed, links work

4g. RSS feed

  • Navigate to http://localhost:3000/blog/feed.xml
  • Verify: XML content returned, contains <item> elements

4h. robots.txt

  • Navigate to http://localhost:3000/robots.txt
  • Verify: contains Disallow for /admin, /api/, /auth/, /login

4i. Badge/Widget endpoints

  • Navigate to http://localhost:3000/api/badge/supabase
  • Verify: SVG content returned
  • Navigate to http://localhost:3000/api/widget/supabase
  • Verify: SVG content returned

Step 5: Report

After all checks, produce a summary table:

| Check | Status | Notes | |-------|--------|-------| | Unit tests | PASS/FAIL | X tests passed | | Build | PASS/FAIL | | | Homepage | PASS/FAIL | | | Search + count | PASS/FAIL | | | Score filter | PASS/FAIL | | | Server detail | PASS/FAIL | | | Category page | PASS/FAIL | | | Blog | PASS/FAIL | | | RSS feed | PASS/FAIL | | | robots.txt | PASS/FAIL | | | Badge API | PASS/FAIL | | | Widget API | PASS/FAIL | |

If any checks fail, list the failures with details on what went wrong.

Usage

  • /qa — full QA run (unit tests + build + E2E)
  • /qa quick — unit tests + build only (no browser)
  • /qa e2e — browser tests only (assumes dev server running)

Related Skills

View on GitHub
GitHub Stars0
CategoryAutomation
Updated1d ago
Forks0

Trust signals

80/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium1 low