doctor by yonatangross/orchestkit
npx skills add https://github.com/yonatangross/orchestkit --skill doctor包含钩子
此技能使用 Claude 钩子,可自动响应事件执行代码。安装前请仔细审阅。
FLAGS = "$ARGUMENTS" # 完整参数字符串,例如 "--verbose" 或 "--json"
FLAG = "$ARGUMENTS[0]" # 第一个标记:-v, --verbose, --json, --category=X
# $ARGUMENTS[0], $ARGUMENTS[1] 用于索引访问 (CC 2.1.59)
/ork:doctor 命令对您的 OrchestKit 安装执行全面的健康检查。它会自动检测已安装的插件并验证 13 个类别:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
claude plugin validate 以进行官方 CC frontmatter + hooks.json 验证(CC >= 2.1.77)npm run build 后提示 (CC 2.1.69+): 修复医生发现的问题后,运行
/reload-plugins以激活插件更改,无需重启会话。
/ork:doctor # 标准健康检查
/ork:doctor -v # 详细输出
/ork:doctor --json # 用于 CI 的机器可读格式
| 标志 | 描述 |
|---|---|
-v, --verbose | 每个检查的详细输出 |
--json | 用于 CI 集成的 JSON 输出 |
--category=X | 仅运行特定类别 |
详细检查流程 : 加载
Read("${CLAUDE_SKILL_DIR}/rules/diagnostic-checks.md")以获取每个类别的 bash 命令和验证逻辑。MCP 特定检查 : 加载
Read("${CLAUDE_SKILL_DIR}/rules/mcp-status-checks.md")以进行凭据验证和配置错误检测。输出示例 : 加载
Read("${CLAUDE_SKILL_DIR}/references/health-check-outputs.md")以获取每个类别的示例输出。
| 类别 | 检查内容 | 参考 |
|---|---|---|
| 0. 已安装插件 | 自动检测 ork 插件,统计技能/代理数量 | 加载 ${CLAUDE_SKILL_DIR}/rules/diagnostic-checks.md |
| 1. 技能 | Frontmatter、上下文字段、令牌预算、链接 | 加载 ${CLAUDE_SKILL_DIR}/references/skills-validation.md |
| 2. 代理 | Frontmatter、模型、技能引用、工具引用 | 加载 ${CLAUDE_SKILL_DIR}/references/agents-validation.md |
| 3. 钩子 | hooks.json 模式、捆绑包、异步模式 | 加载 ${CLAUDE_SKILL_DIR}/references/hook-validation.md |
| 类别 | 检查内容 | 参考 |
|---|---|---|
| 4. 内存 | .claude/memory/ 存在性,decisions.jsonl 完整性,队列深度 | 加载 ${CLAUDE_SKILL_DIR}/references/memory-health.md |
| 5. 构建 | plugins/ 与 src/ 同步,清单计数,孤儿文件 | 加载 ${CLAUDE_SKILL_DIR}/rules/diagnostic-checks.md |
| 类别 | 检查内容 |
|---|---|
| 6. 权限规则 | 不可达规则检测 (CC 2.1.3) |
| 7. 模式合规性 | JSON 文件与模式的匹配 |
| 8. 协调 | 多工作树锁健康状态、陈旧锁、稀疏路径配置 |
| 9. 上下文预算 | 令牌使用量与预算对比 |
| 类别 | 检查内容 | 参考 |
|---|---|---|
| 10. CC 版本与渠道 | 运行时版本与最低要求版本对比,发布渠道(稳定版/测试版/Alpha 版) | 加载 ${CLAUDE_SKILL_DIR}/references/version-compatibility.md |
| 11. 外部依赖项 | 可选工具 (agent-browser) | 加载 ${CLAUDE_SKILL_DIR}/rules/diagnostic-checks.md |
| 12. MCP 状态 | 启用/禁用状态,凭据检查 | 加载 ${CLAUDE_SKILL_DIR}/rules/mcp-status-checks.md |
| 13. 插件验证 | 官方 CC frontmatter + hooks.json 验证 (CC >= 2.1.77) | 加载 ${CLAUDE_SKILL_DIR}/rules/diagnostic-checks.md |
加载
Read("${CLAUDE_SKILL_DIR}/references/report-format.md")以获取 ASCII 报告模板、JSON CI 输出模式和退出代码。
加载
Read("${CLAUDE_SKILL_DIR}/references/remediation-guide.md")以获取完整的结果解读表和常见故障(技能验证、构建同步、内存)的故障排除步骤。
ork:configure - 配置插件设置ork:quality-gates - CI/CD 集成security-scanning - 全面审计使用 Read("${CLAUDE_SKILL_DIR}/references/<file>") 或 Read("${CLAUDE_SKILL_DIR}/rules/<file>") 按需加载:
| 文件 | 内容 |
|---|---|
rules/diagnostic-checks.md | 每个类别的 bash 命令和验证逻辑 |
rules/mcp-status-checks.md | 凭据验证和配置错误检测 |
references/remediation-guide.md | 结果解读和故障排除步骤 |
references/health-check-outputs.md | 每个类别的示例输出 |
references/skills-validation.md | 技能 frontmatter 和结构检查 |
references/agents-validation.md | 代理 frontmatter 和工具引用检查 |
references/hook-validation.md | 钩子注册和捆绑包检查 |
references/memory-health.md | 内存系统完整性检查 |
references/permission-rules.md | 权限规则检测 |
references/schema-validation.md | JSON 模式合规性 |
references/report-format.md | ASCII 报告模板和 JSON CI 输出 |
references/version-compatibility.md | CC 版本和渠道验证 |
每周安装次数
82
代码仓库
GitHub 星标数
132
首次出现
2026 年 1 月 22 日
安全审计
安装于
gemini-cli76
opencode75
github-copilot74
codex74
cursor72
claude-code70
Contains Hooks
This skill uses Claude hooks which can execute code automatically in response to events. Review carefully before installing.
FLAGS = "$ARGUMENTS" # Full argument string, e.g., "--verbose" or "--json"
FLAG = "$ARGUMENTS[0]" # First token: -v, --verbose, --json, --category=X
# $ARGUMENTS[0], $ARGUMENTS[1] for indexed access (CC 2.1.59)
The /ork:doctor command performs comprehensive health checks on your OrchestKit installation. It auto-detects installed plugins and validates 13 categories:
claude plugin validate for official CC frontmatter + hooks.json validation (CC >= 2.1.77)npm run buildTip (CC 2.1.69+): After fixing issues found by doctor, run
/reload-pluginsto activate plugin changes without restarting your session.
/ork:doctor # Standard health check
/ork:doctor -v # Verbose output
/ork:doctor --json # Machine-readable for CI
| Flag | Description |
|---|---|
-v, --verbose | Detailed output per check |
--json | JSON output for CI integration |
--category=X | Run only specific category |
Detailed check procedures : Load
Read("${CLAUDE_SKILL_DIR}/rules/diagnostic-checks.md")for bash commands and validation logic per category.MCP-specific checks : Load
Read("${CLAUDE_SKILL_DIR}/rules/mcp-status-checks.md")for credential validation and misconfiguration detection.Output examples : Load
Read("${CLAUDE_SKILL_DIR}/references/health-check-outputs.md")for sample output per category.
| Category | What It Checks | Reference |
|---|---|---|
| 0. Installed Plugins | Auto-detects ork plugin, counts skills/agents | load ${CLAUDE_SKILL_DIR}/rules/diagnostic-checks.md |
| 1. Skills | Frontmatter, context field, token budget, links | load ${CLAUDE_SKILL_DIR}/references/skills-validation.md |
| 2. Agents | Frontmatter, model, skill refs, tool refs | load ${CLAUDE_SKILL_DIR}/references/agents-validation.md |
| 3. Hooks | hooks.json schema, bundles, async patterns | load ${CLAUDE_SKILL_DIR}/references/hook-validation.md |
| Category | What It Checks | Reference |
|---|---|---|
| 4. Memory | .claude/memory/ exists, decisions.jsonl integrity, queue depth | load ${CLAUDE_SKILL_DIR}/references/memory-health.md |
| 5. Build | plugins/ sync with src/, manifest counts, orphans | load ${CLAUDE_SKILL_DIR}/rules/diagnostic-checks.md |
| Category | What It Checks |
|---|---|
| 6. Permission Rules | Unreachable rules detection (CC 2.1.3) |
| 7. Schema Compliance | JSON files against schemas |
| 8. Coordination | Multi-worktree lock health, stale locks, sparse paths config |
| 9. Context Budget | Token usage against budget |
| Category | What It Checks | Reference |
|---|---|---|
| 10. CC Version & Channel | Runtime version against minimum required, release channel (stable/beta/alpha) | load ${CLAUDE_SKILL_DIR}/references/version-compatibility.md |
| 11. External Deps | Optional tools (agent-browser) | load ${CLAUDE_SKILL_DIR}/rules/diagnostic-checks.md |
| 12. MCP Status | Enabled/disabled state, credential checks | load ${CLAUDE_SKILL_DIR}/rules/mcp-status-checks.md |
| 13. Plugin Validate | Official CC frontmatter + hooks.json validation (CC >= 2.1.77) | load ${CLAUDE_SKILL_DIR}/rules/diagnostic-checks.md |
Load
Read("${CLAUDE_SKILL_DIR}/references/report-format.md")for ASCII report templates, JSON CI output schema, and exit codes.
Load
Read("${CLAUDE_SKILL_DIR}/references/remediation-guide.md")for the full results interpretation table and troubleshooting steps for common failures (skills validation, build sync, memory).
ork:configure - Configure plugin settingsork:quality-gates - CI/CD integrationsecurity-scanning - Comprehensive auditsLoad on demand with Read("${CLAUDE_SKILL_DIR}/references/<file>") or Read("${CLAUDE_SKILL_DIR}/rules/<file>"):
| File | Content |
|---|---|
rules/diagnostic-checks.md | Bash commands and validation logic per category |
rules/mcp-status-checks.md | Credential validation and misconfiguration detection |
references/remediation-guide.md | Results interpretation and troubleshooting steps |
references/health-check-outputs.md | Sample output per category |
references/skills-validation.md | Skills frontmatter and structure checks |
references/agents-validation.md |
Weekly Installs
82
Repository
GitHub Stars
132
First Seen
Jan 22, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
gemini-cli76
opencode75
github-copilot74
codex74
cursor72
claude-code70
Azure Data Explorer (Kusto) 查询技能:KQL数据分析、日志遥测与时间序列处理
138,800 周安装
| Agents frontmatter and tool ref checks |
references/hook-validation.md | Hook registration and bundle checks |
references/memory-health.md | Memory system integrity checks |
references/permission-rules.md | Permission rule detection |
references/schema-validation.md | JSON schema compliance |
references/report-format.md | ASCII report templates and JSON CI output |
references/version-compatibility.md | CC version and channel validation |