verify-implementation
Use after implementing changes to run verification commands and ensure tests pass, code builds, and functionality works.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use after implementing changes to run verification commands and ensure tests pass, code builds, and functionality works.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Generic migration orchestrator that reads CHANGELOG.md to understand and execute version-specific migrations
Determine feature slug interactively by auto-detecting next number and prompting user for description
Share personal documents to the shared namespace with atomic git commit and push
Use when creating implementation plans to generate properly structured plans with phases, success criteria, and project references.
Use when documenting research findings to create properly structured research documents with frontmatter, sections, and file references.
ALWAYS check this skill before using grep, glob, Task tool, or doing any codebase exploration. Guides you to use specialized agents that are more efficient than basic tools.
| name | verify-implementation |
| description | Use after implementing changes to run verification commands and ensure tests pass, code builds, and functionality works. |
Run verification commands after implementing changes to ensure correctness.
Check thoughts/notes/commands.md (created by discover-project-commands skill) for:
DO NOT run verification commands directly in main context.
Spawn a verification agent to run checks and return summary:
Task(subagent_type="Bash",
prompt="Run verification commands from plan success criteria:
- make test
- make lint
- make build
[list all automated checks from plan]
Return concise summary:
- If all pass: ✅ All verification passed
- If any fail: ❌ Verification failed
- List ONLY the failing checks
- Include first few lines of error
- Omit stack traces and verbose output
Maximum output: 2k tokens")
Why use an agent:
spawn-implementation-agents)Agent returns:
Check commands.md, then run appropriate command:
make test - If Make target existsnpm test - If npm script existsgo test ./... - Direct Go commandpytest - Direct Python commandCheck commands.md, then run:
make lint - If Make target existsnpm run lint - If npm script existsgolangci-lint run - Direct Go commandeslint . - Direct JavaScript commandCheck commands.md, then run:
make build - If Make target existsnpm run build - If npm script existsgo build ./... - Direct Go commandnpm run typecheck - TypeScriptmypy . - Pythonthoughts/notes/commands.mdIf verification fails:
# Read the commands reference
cat thoughts/notes/commands.md
# Run appropriate commands
make test
make lint
make build
# All pass? Mark phase complete in plan
# Any fail? Debug and fix before proceeding
Always spawn agent for verification - never run commands directly in main context.
See spawn-implementation-agents skill for full orchestration pattern.