Your agent has read everything and has no opinion. Borrow one.

• Write the thing that does not exist yet

  For the point where the answer stops being "install something" and starts being "build it". Two Anthropic meta-skills that make the skill-or-server decision legible, and the third-party one that tests the failure both of them leave open.

  1. 1Skill creator
  2. 2Mcp builder
  3. 3Mcp tester

  agentscliIn house · 3 steps

• Write against the API that exists today

  The worst failure in third-party integration work does not look like a failure. The call is idiomatic, the types line up, and the method was removed two majors ago. Two items for what is true now, two for proving it stays true.

  • Context7
  • GitHub
  • Mockserver
  • Keploy

  agentscliIn house · 4 items

• Read a codebase you did not write

  Four servers that answer the four different questions an agent gets wrong on a repository it has never seen: where is anything, why is it like that, what version am I calling, and what shape is the whole thing.

  • Serena MCP: the IDE for your agent
  • GitHub
  • Context7
  • Hustcc mcp mermaid

  agentscliIn house · 4 items

• Find the cause before writing the fix

  A stack trace tells you where the program died, not where it went wrong. Five items that supply four different kinds of evidence, in the order an investigation actually needs them, and a test at the end that can say no.

  1. 1Root cause analysis
  2. 2Sentry mcp
  3. 3Serena MCP: the IDE for your agent
  4. 4GitHub
  5. and 1 more

  agentscliIn house · 5 steps

• Change a schema without taking the site down

  The dangerous migration is not the one that fails. It is the one that runs perfectly and holds a lock on your busiest table for four minutes. One item for the idioms, one that reads the live schema, and two that read the SQL before anything does.

  1. 1Pg aiguide
  2. 2DBHub
  3. 3Migrationpilot
  4. 4Sqlsure

  agentscliIn house · 4 steps

• Build the design, then go and look

  An agent implementing a design generates pixels and reasons in text. It will tell you the header is blue and centred while it renders red and left. Four items that make it read exact values, wait for the page to settle, actually look, and then keep looking after you have gone.

  1. 1Figma Context MCP
  2. 2Webapp testing
  3. 3Chrome DevTools MCP
  4. 4Playwright mcp

  agentscliIn house · 4 steps

• A review that is not a rubber stamp

  Three systems that can each contradict the pull request description in a different way, and one procedure that makes the agent go and ask them. Reach without judgment is "LGTM, consider adding tests" in a costume.

  1. 1GitHub
  2. 2Context7
  3. 3Sentry mcp
  4. 4Open code review

  agentscliIn house · 4 steps

• 1

  GitHub

  github/github-mcp-server/io.github.github/github-mcp-server · MCP server

  in 4 stacks31,881★ repo

  Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.

• 2

  Context7

  upstash/context7/io.github.upstash/context7 · MCP server

  in 3 stacks60,113★ repo

  Up-to-date code docs for any prompt

• 3

  Serena MCP: the IDE for your agent

  oraios/serena/io.github.oraios/serena · MCP server

  in 2 stacks27,343★ repo

  A powerful toolkit for coding, providing semantic retrieval and editing capabilities.

• 4

  Sentry mcp

  getsentry/sentry-mcp/io.github.getsentry/sentry-mcp · MCP server

  in 2 stacksno license804★ repo

  MCP server for Sentry - error monitoring, issue tracking, and debugging for AI assistants

• 5

  Skill creator

  anthropics/skills/skills/skill-creator · Skill

  in 1 stackno license164,354★ repo

  Public repository for Agent Skills

• 6

  Mcp builder

  anthropics/skills/skills/mcp-builder · Skill

  in 1 stackno license164,354★ repo

  Public repository for Agent Skills

Inclusion is the default, so the catalog is large and most of it has had nothing done to it beyond reading its repository. Rows where a signal is missing say which one.

Open the catalog