Menü
Structured output format for worker agents
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Load CI/CD pipeline configuration and deployment information when working with automation or deployments
Load database relationships, shared resources, and schema information when working with data models or database configuration
Load development environment information including folder structure, OrbStack setup, and system configuration
Load port mappings for all projects when working with networking, docker-compose, or service configuration
Load GitHub/GitLab repository information when working with git, CI/CD, or repository management
Load server information, infrastructure details, and access patterns when working with deployment or server configuration
| name | worker-reporting |
| description | Structured output format for worker agents |
| disable-model-invocation | true |
When you finish your task (or need to exit early), return your results in this exact format:
## STATUS: {DONE | PARTIAL | BLOCKED}
## ACCOMPLISHED
- {bullet list of what you completed}
- {include file paths, commands run, verification results}
## REMAINING
- {what's left to do, if anything}
- {omit this section if STATUS is DONE}
## QUESTIONS
- {questions for the supervisor, if any}
- {information you need to continue}
- {omit this section if you have no questions}
## EVIDENCE
- {command output, test results, or other proof}
- {the supervisor may verify your work — provide evidence}
| Status | Meaning | When to use |
|---|---|---|
| DONE | Task fully completed and verified | You did everything asked and confirmed it works |
| PARTIAL | Some work done, more remains | You made progress but ran out of scope or hit a dependency |
| BLOCKED | Cannot proceed without help | Missing information, access denied, dependency not met |
When you need a knowledge skill you weren't given at launch, use BLOCKED with a NEED_CAPABILITY section:
## STATUS: BLOCKED
## ACCOMPLISHED
- Connected to dev-01 via SSH
- Found auth-service pod running on port 9001
## NEED_CAPABILITY
Skill: worker-database
Reason: I need the PostgreSQL connection string to verify auth-service DB migrations
## REMAINING
- Verify DB schema matches expected migration state
- Report results
The supervisor will either:
"CAPABILITY GRANTED: Read ~/.claude/skills/{skill}/SKILL.md and continue.""CAPABILITY DENIED: {reason}. Stay within scope."/app/routes.py line 42" not "Fixed the route"