doctor
Load Devflow Native execution rules and repeated-mistake memory before running shell, browser, MCP, or test commands.
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
Load Devflow Native execution rules and repeated-mistake memory before running shell, browser, MCP, or test commands.
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
Initialize or bootstrap a repository with Devflow Native presets by calling devflow init and interpreting the result.
Run configured Devflow Native verification gates and record pass or fail evidence for a work item.
Inspect, install, verify, or repair native Devflow harness files for Codex, Claude Code, MCP, hooks, skills, gates, and review requirements.
Request, perform, or record Devflow Native review evidence before a task can be claimed done.
Inspect Devflow Native project truth, including repo state, work items, sessions, gates, review requirements, and latest handoff context.
Create, start, update, ready, block, unblock, rename, or list Devflow Native work items from local repo state.
| name | doctor |
| description | Load Devflow Native execution rules and repeated-mistake memory before running shell, browser, MCP, or test commands. |
Use before command-heavy work, debugging, browser automation, MCP transport work, or any task likely to hit platform-specific tooling issues.
devflow doctor --json.executionContract exactly. On Windows PowerShell, keep commands
PowerShell-compatible and avoid Bash-only syntax unless the task targets
WSL.devflow mistakes detect --json and
record high-confidence candidates only when appropriate.devflow mistakes promote --id <id> --target agents|skill|hook|config --dry-run --json
to inspect patch candidates. Record maintainer evidence with
devflow mistakes review --id <id> --status approved|rejected --summary <text> --json
before applying any durable rule.devflow mistakes promote --id <id> --target <target> --apply --json.
Use devflow mistakes rules --json to confirm the active promoted rule.State platform assumptions, required command style, available tools, repeated mistakes, active promoted rules, and any command forms to avoid.