论文生成
- 作者仓库星标 435
- 作者更新于 实时读取
- 作者仓库 nvim
- 领域
- 通用
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @benbrastmckie · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: skill-math-research
description: Research mathematical tasks using domain context and codebase exploration. Invoke for math-langu…
category: 通用
runtime: 无特殊运行时
---
# skill-math-research 输出预览
## PART A: 任务判断
- 适用问题:通用任务拆解、检查和交付。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“Context References / Trigger Conditions / Execution Flow”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于通用任务拆解、检查和交付,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Context References / Trigger Conditions / Execution Flow”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、执行终端命令、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、执行终端命令;主要在本地完成;通常不需要额外 API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 原文没有稳定的斜杠命令要求。安装验证后通常全局生效,直接在对话里点名这个 Skill 并描述任务即可。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件、执行终端命令。
先用一个小任务确认它会围绕“Context References / Trigger Conditions / Execution Flow”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: skill-math-research
description: Research mathematical tasks using domain context and codebase exploration. Invoke for math-langu…
category: 通用
source: benbrastmckie/nvim
---
# skill-math-research
## 什么时候使用
- 把通用方向的常用动作沉淀成 Agent 可调用的技能 适合处理通用任务拆解、检查、交付和复盘,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代的步骤;通常不需要额外…
- 面向通用任务拆解、检查和交付,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Context References / Trigger Conditions / Execution Flow」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件、执行终端命令;主要在本地完成;通常不需要额外 API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "skill-math-research" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Context References / Trigger Conditions / Execution Flow
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件、执行终端命令 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} Math Research Skill
Thin wrapper that delegates mathematical research to math-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 "math"
- Research involves algebra, lattice theory, order theory, topology, or category theory
- Domain context files are needed for mathematical foundations
Execution Flow
Stage 1: Input Validation
Validate required inputs:
task_number- Must be provided and exist in state.jsonfocus_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:
{
"session_id": "sess_{timestamp}_{random}",
"delegation_depth": 1,
"delegation_path": ["orchestrator", "research", "skill-math-research"],
"timeout": 3600,
"task_context": {
"task_number": N,
"task_name": "{project_name}",
"description": "{description}",
"task_type": "math"
},
"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: "math-research-agent"
- prompt: [Include task_context, delegation_context, focus_prompt, metadata_file_path]
- description: "Execute math research for task {N}"
DO NOT use Skill(math-research-agent) - this will FAIL.
The subagent will:
- Load domain context files from
.claude/context/project/math/ - Search codebase for existing patterns
- Use Mathlib lookup tools
- Execute web research for mathematical literature
- 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: Parse Subagent Return (Read Metadata File)
Read the metadata file.
Stage 7: Update Task Status (Postflight)
If status is "researched", update state.json and TODO.md.
Stage 8: Link Artifacts
Add artifact to state.json with summary. Update TODO.md per @.claude/context/patterns/artifact-linking-todo.md with field_name=**Research**, next_field=**Plan**.
Stage 9: Git Commit
Commit changes with session ID using targeted staging.
Stage 10: Cleanup
Remove marker and metadata files.
Stage 11: Return Brief Summary
Return a brief text summary (NOT JSON). Example:
Research completed for task {N}:
- Found existing patterns in source files
- Loaded domain context for algebra/lattice theory
- Used Mathlib lookup tools to discover relevant theorems
- Created report at specs/{NNN}_{SLUG}/reports/MM_{short-slug}.md
- Status updated to [RESEARCHED]
- Changes committed
Error Handling
Input Validation Errors
Return immediately with error message if task not found.
Metadata File Missing
If subagent didn't write metadata file, keep status as "researching".
Git Commit Failure
Non-blocking: Log failure but continue with success response.
Return Format
This skill returns a brief text summary (NOT JSON). The JSON metadata is written to the file and processed internally.
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核