메뉴
Orchestrate the phase workflow end to end by detecting whether the request is software delivery or solution design, then chaining the appropriate phase skills with bounded retries, status markers, and final reporting.
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
| name | phase-auto |
| description | Orchestrate the phase workflow end to end by detecting whether the request is software delivery or solution design, then chaining the appropriate phase skills with bounded retries, status markers, and final reporting. |
| origin | ECC automation-pack |
Use this skill when the user asks for /phase-auto, full automation, end-to-end delivery, from requirement to PR, or an unattended phased workflow.
Route a broad request through the correct lifecycle without losing status or verification.
Use the software delivery route when the request is mainly code, bug fix, feature work, refactoring, tests, build repair, or PR delivery:
phase-research -> phase-plan -> phase-implement -> phase-test -> phase-review -> phase-ship
Use the solution-design route when the request is mainly concept design, product/technical planning, architecture proposal, roadmap, research plan, or non-code execution:
phase-design -> phase-validate -> phase-execute -> phase-verify
Report:
End with PHASE_AUTO_DONE, PHASE_AUTO_BLOCKED, or PHASE_AUTO_FAILED.
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
API Key penetration testing skill for buyer/seller platform API key security assessment. Runs secret scanning (trufflehog + gitleaks), endpoint fuzzing (ffuf + arjun), traffic analysis, and records all findings.
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.