一键导入
verify
Run the full quality gate — formatting, linting, type checking, and tests. Use after implementing changes to confirm everything passes.
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
Run the full quality gate — formatting, linting, type checking, and tests. Use after implementing changes to confirm everything passes.
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
Run, resume, and manage checkpointflow workflows interactively. Use this skill whenever the user wants to run a workflow, execute a YAML pipeline, resume a paused run, check workflow status, cancel a run, or interact with cpf at runtime. Also triggers on phrases like "run the workflow", "execute this", "resume the run", "what's the status", or when the user provides input for a waiting workflow step.
Create and improve Claude Code skills using a structured checkpointflow workflow with test-driven iteration. Use this skill whenever the user wants to create a skill, make a skill, build a skill, improve an existing skill, test a skill with evals, benchmark skill quality, optimize a skill description, or turn a conversation into a reusable skill. Also triggers on "skill for X", "automate this as a skill", "package this as a skill", and similar phrases. Always use this instead of the generic skill-creator when in the checkpointflow repo.
Create and edit checkpointflow workflow YAML files. Use this skill whenever the user wants to create a workflow, automate a process as a YAML pipeline, define steps that mix CLI commands with human or agent checkpoints, turn a conversation into a reusable runbook, or asks about writing cpf/checkpointflow workflows. Also use it when you see keywords like "workflow", "runbook", "approval flow", "pause and resume", or "await event" in the context of automation.
| name | verify |
| description | Run the full quality gate — formatting, linting, type checking, and tests. Use after implementing changes to confirm everything passes. |
Run the complete quality gate for this project. Execute each step sequentially and report results:
uv run ruff format --check . — verify formattinguv run ruff check . — lintuv run mypy — strict type checkinguv run pytest — run all testsIf any step fails, stop and report the failure with details. If all pass, confirm the change is ready.