verify

Run full verification on recent code changes — tests, LLD compliance, and security review. Claude MUST run this automatically after building any feature. Do not wait for user to ask.

SKILL.md

GitHub

Run a full verification pass on the code changes just made. Launch these 3 agents IN PARALLEL:

  1. test-writer agent — Write tests for any new services/routes that don't have tests yet. Run all tests. Report pass/fail.

  2. lld-checker agent — Validate that the new code matches docs/LLD.md — check API shapes, data models, error formats, component boundaries.

  3. security-reviewer agent — Check for SQL injection, hardcoded secrets, missing input validation, unsafe deserialization, credentials in logs.

After all 3 agents complete, synthesize their results into a single report:

Verification Report

  • Tests: X passed, Y failed (list failures)
  • LLD Compliance: matches / mismatches found (list each)
  • Security: issues found / clean (list each)
  • Overall: PASS or FAIL

If any agent reports issues, list them clearly so the user can decide what to fix.

Related in other

limits-colimits

Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context polluti...

by parcadei
3,392

ddttom-allaboutv2-claude-skills-block-collection-and-party

The Block Collection and Block Party are repositories for existing AEM blocks, build tools, code snippets, integration p...

by mattnigh
20

nodnarbnitram-claude-code-extensions-claude-skills-esphome-confi

This skill should be used when the user asks to "create an esphome config", "set up an esp32 device", "configure esphome...

by mattnigh
20