技能正式研究
- 作者仓库星标 435
- 作者仓库 nvim
- 领域
- 通用
- 作者声明的智能体
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 88 / 100 · 启发式扫描,不代表运行安全
- 运行环境证据
- 未执行;当前没有隔离运行测试证据
- 作者 / 版本 / 许可证
- @benbrastmckie · 未声明许可证
- 上下文用量评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部接口密钥
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 运行环境要求
- 未检出明确要求
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- 命令执行
- 网络行为
- 仅限本地
- 安装命令数
- 无(仅作为资料)
需要注意: 未声明工具权限范围;实际权限由运行环境决定。
# Formal Research Skill
Thin wrapper that delegates formal reasoning research to `formal-research-agent` subagent.
**IMPORTANT**: This skill implements the skill-internal postflight pattern. After the subagent returns, this skill handles all postflight operations (status update, artifact linking, git commit) before returning.
## Context References
Reference (do not load eagerly):
- Path: `.claude/context/formats/return-metadata-file.md` - Metadata file schema
Note: This skill is a thin wrapper with internal postflight. Context is loaded by the delegated agent.
## Trigger Conditions
This skill activates when:
- Task type is "formal"
- Research requires cross-domain coordination (logic + math, math + physics, etc.)
- Domain context files are needed from multiple formal domains
---
## Execution Flow
### Stage 1: Input Validation
Validate required inputs:
- `task_number` - Must be provided and exist in state.json
- `focus_prompt` - Optional focus for research direction
---
### Stage 2: Preflight Status Update
Update task status to "researching" BEFORE invoking subagent.
---
### Stage 3: Create Postflight Marker
Create the marker file to prevent premature termination.
---
### Stage 4: Prepare Delegation Context
Prepare delegation context for the subagent:
```json
{
"session_id": "sess_{timestamp}_{random}",
"delegation_depth": 1,
"delegation_path": ["orchestrator", "research", "skill-formal-research"],
"timeout": 3600,
"task_context": {
"task_number": N,
"task_name": "{project_name}",
"description": "{description}",
"task_type": "formal"
},
"focus_prompt": "{optional focus}",
"metadata_file_path": "specs/{NNN}_{SLUG}/.return-meta.json"
}
```
---
### Stage 5: Invoke Subagent
**CRITICAL**: You MUST use the **Agent** tool to spawn the subagent.
**Required Tool Invocation**:
```
Tool: Agent (NOT Skill, NOT Plan)
Parameters:
- subagent_type: "formal-research-agent"
- prompt: [Include task_context, delegation_context, focus_prompt, metadata_file_path]
- description: "Execute formal research for task {N}"
```
**DO NOT** use `Skill(formal-research-agent)` - this will FAIL.
The subagent will:
- Analyze task for domain routing (logic, math, physics)
- Load appropriate domain context files
- Coordinate cross-domain research when needed
- Use Mathlib lookup tools
- Execute web research
- Create research report in `specs/{NNN}_{SLUG}/reports/`
- Write metadata to `specs/{NNN}_{SLUG}/.return-meta.json`
- Return a brief text summary (NOT JSON)
---
### Stage 5b: Self-Execution Fallback
**CRITICAL**: If you performed the work above WITHOUT using the Agent tool (i.e., you read files,
wrote artifacts, or updated metadata directly instead of spawning a subagent), you MUST write a
`.return-meta.json` file now before proceeding to postflight. Use the schema from
`return-metadata-file.md` with status value "researched".
If you DID use the Agent tool, skip this stage -- the subagent already wrote the metadata.
---
## Postflight (ALWAYS EXECUTE)
The following stages MUST execute after work is complete, whether the work was done by a
subagent or inline (Stage 5b). Do NOT skip these stages for any reason.
### Stage 6-11: Standard Postflight
Parse metadata file, update task status, link artifacts (update TODO.md per `@.claude/context/patterns/artifact-linking-todo.md` with `field_name=**Research**`, `next_field=**Plan**`), git commit, cleanup, return brief summary.
---
## Error Handling
Standard error handling patterns: validate inputs, handle missing metadata, non-blocking git failures.
---
## Return Format
This skill returns a **brief text summary** (NOT JSON). The JSON metadata is written to the file and processed internally.
章节与文件索引
按说明文件中的顺序排列。
上下文参考
触发条件
第一阶段:输入验证
第 2 阶段:预检状态更新
第 3 阶段:创建飞行后标记
文件/命令 -> formal-research-agent · .claude/context/formats/return-metadata-file.md · task_number · focus_prompt · Skill(formal-research-agent) · specs/{NNN}_{SLUG}/reports/ · specs/{NNN}_{SLUG}/.return-meta.json · .return-meta.json
内容校验值 -> 217de50a6a1a
当前原文的自动摘译,尚未人工审校。
上下文参考
参考(不要急于加载):路径:
.claude/context/formats/return-metadata-file.md- 元数据文件架构 注意:此技能是一个带有内部 postflight 的薄包装器。上下文由委托代理加载。触发条件
该技能在以下情况下激活: 任务类型为“正式” 研究需要跨领域协调(逻辑 + 数学、数学 + 物理等) 需要来自多个正式领域的领域上下文文件
第一阶段:输入验证
验证所需的输入:
task_number- 必须提供并存在于 state.jsonfocus_prompt- 研究方向的可选焦点第 2 阶段:预检状态更新
在调用子代理之前将任务状态更新为“正在研究”。
第 3 阶段:创建飞行后标记
创建标记文件以防止过早终止。