一键导入
ensure-agent-workflow
Ensure global agent instruction files include the standard '# Workflow' block; update idempotently and report a unified diff.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Ensure global agent instruction files include the standard '# Workflow' block; update idempotently and report a unified diff.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Analyze a project's past Codex sessions, memory files, and existing local skills to recommend the highest-value skills to create or update. Use when a user asks what skills a project needs, wants skill ideas grounded in real project history, wants an audit of current project-local skills, or wants recommendations for updating stale or incomplete skills instead of creating duplicates.
Apply treys-swarm-planner to the PT Study System by grounding in repo canon, the active execution board, Conductor tracks, planner APIs, and the `study_tasks` schema. Use when planning significant work in this repo and then executing it end-to-end with a backward-built wave/task graph until the goal is complete, unless the user explicitly asks for plan-only or review-only output.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Execute tasks from a track's implementation plan following TDD workflow
Manage track lifecycle: archive, restore, delete, rename, and cleanup
Create a new track with specification and phased implementation plan
| name | ensure-agent-workflow |
| description | Ensure global agent instruction files include the standard '# Workflow' block; update idempotently and report a unified diff. |
Ensure global instruction files for Claude and Codex contain the standard "# Workflow" block. Update idempotently without duplicates and preserve existing content/formatting.
# Workflow
- For any multi-step work: create and maintain the Task list; complete tasks one-by-one.
- Delegate:
- Exploration/searching to a read-only subagent when possible
- Test running to a test-runner subagent
- Final review to code-reviewer subagent
- Prefer background subagents for long-running tasks; summarize results back in the main thread.
For each file: