数据分析
- 作者仓库星标 435
- 作者更新于 实时读取
- 作者仓库 nvim
- 领域
- 数据
- 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-financial-analysis
description: Financial analysis with forcing questions and spreadsheet generation Thin wrapper that routes fi…
category: 数据
runtime: 无特殊运行时
---
# skill-financial-analysis 输出预览
## PART A: 任务判断
- 适用问题:表格、CSV、数据集、指标或分析流程。
- 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 Pointers / Trigger Conditions / Direct Invocation”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表格、CSV、数据集、指标或分析流程,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Context Pointers / Trigger Conditions / Direct Invocation”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。 原文出现了 `/research` 这类斜杠命令;如果你的 Agent 支持命令触发,优先用命令开场,再补充目标和边界。
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 Pointers / Trigger Conditions / Direct Invocation”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-financial-analysis
description: Financial analysis with forcing questions and spreadsheet generation Thin wrapper that routes fi…
category: 数据
source: benbrastmckie/nvim
---
# skill-financial-analysis
## 什么时候使用
- 把数据处理方向的常用动作沉淀成 Agent 可调用的技能 适合处理表格、CSV、指标、数据集、分析和可视化报告,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…
- 面向表格、CSV、数据集、指标或分析流程,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 Pointers / Trigger Conditions / Direct Invocation」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-financial-analysis" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Context Pointers / Trigger Conditions / Direct Invocation
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
} Financial Analysis Skill
Thin wrapper that routes financial analysis research requests to the financial-analysis-agent.
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 Pointers
Reference (do not load eagerly):
- Path:
.claude/context/formats/return-metadata-file.md- Metadata file schema - Path:
.claude/context/patterns/jq-escaping-workarounds.md- jq escaping patterns (Issue #1132)
Note: This skill is a thin wrapper. Context is loaded by the delegated agent, not this skill.
Trigger Conditions
This skill activates when:
Direct Invocation
- User runs
/researchon a task with languagefounder:financial-analysis
When NOT to trigger
Do not invoke for:
- Cost breakdown from scratch (use skill-spreadsheet)
- Market sizing (use skill-market)
- General business analysis (use skill-analyze)
- Document review without data gathering (use skill-finance)
Execution Flow
Stage 1: Input Validation
Validate required inputs:
task_number- Must be provided and exist in state.jsonmode- Optional, one of: REVIEW, DILIGENCE, AUDIT, FORECAST
# Lookup task
task_data=$(jq -r --argjson num "$task_number" \
'.active_projects[] | select(.project_number == $num)' \
specs/state.json)
# Validate exists
if [ -z "$task_data" ]; then
return error "Task $task_number not found"
fi
# Extract fields
task_type=$(echo "$task_data" | jq -r '.task_type // "founder"')
status=$(echo "$task_data" | jq -r '.status')
project_name=$(echo "$task_data" | jq -r '.project_name')
description=$(echo "$task_data" | jq -r '.description // ""')
forcing_data=$(echo "$task_data" | jq -r '.forcing_data // null')
Stage 2: Preflight Status Update
bash .claude/scripts/update-task-status.sh preflight "$task_number" research "$session_id"
Stage 3: Create Postflight Marker
padded_num=$(printf "%03d" "$task_number")
mkdir -p "specs/${padded_num}_${project_name}"
cat > "specs/${padded_num}_${project_name}/.postflight-pending" << EOF
{
"session_id": "${session_id}",
"skill": "skill-financial-analysis",
"task_number": ${task_number},
"operation": "research",
"reason": "Postflight pending: status update, artifact linking, git commit",
"created": "$(date -u +%Y-%m-%dT%H:%M:%SZ)",
"stop_hook_active": false
}
EOF
Stage 3a: Read Artifact Number
artifact_number=$(jq -r --argjson num "$task_number" \
'.active_projects[] | select(.project_number == $num) | .next_artifact_number // 1' \
specs/state.json)
artifact_padded=$(printf "%02d" "$artifact_number")
Stage 4: Prepare Delegation Context
{
"session_id": "{session_id}",
"delegation_depth": 1,
"delegation_path": ["orchestrator", "research", "skill-financial-analysis"],
"timeout": 3600,
"task_context": {
"task_number": "{N}",
"task_name": "{project_name}",
"description": "{description}",
"task_type": "{task_type}"
},
"artifact_number": "{artifact_number}",
"mode": "{mode if provided}",
"forcing_data": "{forcing_data from state.json if present}",
"metadata_file_path": "specs/{NNN}_{SLUG}/.return-meta.json"
}
Stage 5: Invoke Subagent
CRITICAL: Use the Agent tool to spawn the subagent.
Tool: Agent (NOT Skill, NOT Plan)
Parameters:
- subagent_type: "financial-analysis-agent"
- prompt: [Include task_context, delegation_context, forcing_data]
- description: "Execute financial analysis for task {N}"
The subagent will:
- Ask forcing questions to gather financial data
- Generate XLSX spreadsheet with formulas
- Export financial-metrics.json for Typst integration
- Create research report
- Write metadata to .return-meta.json
Stage 5b: Self-Execution Fallback
CRITICAL: If you performed the work above WITHOUT using the Agent tool (i.e., you read files,
wrote artifacts, or updated metadata directly instead of spawning a subagent), you MUST write a
.return-meta.json file now before proceeding to postflight. Use the schema from
return-metadata-file.md with the appropriate status value for this operation.
If you DID use the Agent tool, skip this stage -- the subagent already wrote the metadata.
Postflight (ALWAYS EXECUTE)
The following stages MUST execute after work is complete, whether the work was done by a subagent or inline (Stage 5b). Do NOT skip these stages for any reason.
Stage 6: Read Metadata File
metadata_file="specs/${padded_num}_${project_name}/.return-meta.json"
if [ -f "$metadata_file" ] && jq empty "$metadata_file" 2>/dev/null; then
status=$(jq -r '.status' "$metadata_file")
# Extract artifacts array
else
status="failed"
fi
Stage 7: Update Task Status (Postflight)
if [ "$status" = "researched" ]; then
bash .claude/scripts/update-task-status.sh postflight "$task_number" research "$session_id"
# Increment next_artifact_number
jq '(.active_projects[] | select(.project_number == '$task_number')).next_artifact_number =
(((.active_projects[] | select(.project_number == '$task_number')).next_artifact_number // 1) + 1)' \
specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json
fi
Stage 8: Link Artifacts
Link all artifacts (research report, spreadsheet, metrics JSON) to state.json using two-step jq pattern.
Update TODO.md: Link artifact per @.claude/context/patterns/artifact-linking-todo.md with field_name=**Research**, next_field=**Plan**.
Stage 9: Git Commit
git add -A
git commit -m "task ${task_number}: complete financial analysis research
Session: ${session_id}
Stage 10: Cleanup
rm -f "specs/${padded_num}_${project_name}/.postflight-pending"
rm -f "specs/${padded_num}_${project_name}/.return-meta.json"
Stage 11: Return Brief Summary
Financial analysis research complete for task {N}:
- Mode: {MODE}, forcing questions completed
- Generated XLSX, JSON metrics, and research report
- Status updated to [RESEARCHED]
MUST NOT (Postflight Boundary)
After the agent returns, this skill MUST NOT:
- Edit source files - All work is done by agent
- Run build/test commands - Verification is done by agent
- Use AskUserQuestion - Interactive tools are for agent use only
- Analyze financial data - Analysis is agent work
- Write reports or spreadsheets - Artifact creation is agent work
The postflight phase is LIMITED TO:
- Reading agent metadata file
- Calling
update-task-status.shfor status updates - Incrementing
next_artifact_numbervia jq - Linking artifacts in state.json
- Git commit
- Cleanup of temp/marker files
Reference: @.claude/context/standards/postflight-tool-restrictions.md
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