Back to Skills

analyze-codebase-workflow

pjt222
Updated 6 days ago
24 views
17
2
17
View on GitHub
Designwordautomationdata

About

This skill automatically analyzes codebases to detect workflows, data pipelines, and file dependencies using 902 patterns across 30+ languages. It generates an annotation plan mapping I/O patterns to source files, ideal for onboarding or starting putior integration. Use it to understand data flow in unfamiliar projects or to audit pipelines before documentation.

Quick Install

Claude Code

Recommended
Primary
npx skills add pjt222/agent-almanac -a claude-code
Plugin CommandAlternative
/plugin add https://github.com/pjt222/agent-almanac
Git CloneAlternative
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/analyze-codebase-workflow

Copy and paste this command in Claude Code to install this skill

Documentation

析碼庫工作流

察庫以自察數流、檔 I/O、本依,生結構化之注計備人改。

用時

  • 入生疏之碼庫而需識數流乃用
  • 項未有 PUT 注而始 putior 整合乃用
  • 既項之數管於書文前審乃用
  • annotate-source-files 前備注計乃用

  • 必要:待析庫或源目之徑
  • 可選:特焦之子目(默:全庫)
  • 可選:納或排之語(默:諸察)
  • 可選:察之範:只入、只出、或兼(默:兼加依)

第一步:察庫之構

識源檔與其語,以知 putior 可析者。

library(putior)

# List all supported languages and their extensions
list_supported_languages()
list_supported_languages(detection_only = TRUE)  # Only languages with auto-detection

# Get supported extensions
exts <- get_supported_extensions()

以檔列解庫之組:

# Count files by extension in the target directory
find /path/to/repo -type f | sed 's/.*\.//' | sort | uniq -c | sort -rn | head -20

得: 庫中擴名之列附計。對於 get_supported_extensions() 以知覆蓋。

敗則: 若庫無合擴之檔,putior 不可自察工作流。察語雖支而檔用非標擴乎。

第二步:察語自察之覆蓋

每察之語,驗自察式之備。

# Check which languages have auto-detection patterns (18 languages, 902 patterns)
detection_langs <- list_supported_languages(detection_only = TRUE)
cat("Languages with auto-detection:\n")
print(detection_langs)

# Get pattern counts for specific languages found in the repo
for (lang in c("r", "python", "javascript", "sql", "dockerfile", "makefile")) {
  patterns <- get_detection_patterns(lang)
  cat(sprintf("%s: %d input, %d output, %d dependency patterns\n",
    lang,
    length(patterns$input),
    length(patterns$output),
    length(patterns$dependency)
  ))
}

得: 每語之式計已印。R 有 124 式,Python 159,JavaScript 71,等。

敗則: 若某語返無式,其支手注而非自察。計以手注之。

第三步:行自察

於目目行 put_auto() 以察工作流之元。

# Full auto-detection
workflow <- put_auto("./src/",
  detect_inputs = TRUE,
  detect_outputs = TRUE,
  detect_dependencies = TRUE
)

# Exclude build scripts and test helpers from scanning
workflow <- put_auto("./src/",
  detect_inputs = TRUE,
  detect_outputs = TRUE,
  detect_dependencies = TRUE,
  exclude = c("build-", "test_helper")
)

# View detected workflow nodes
print(workflow)

# Check node count
cat(sprintf("Detected %d workflow nodes\n", nrow(workflow)))

大庫則按子目漸析:

# Analyze specific subdirectories
etl_workflow <- put_auto("./src/etl/")
api_workflow <- put_auto("./src/api/")

得: 一數框,含 idlabelinputoutputsource_file 等列。每行一察工作步。

敗則: 若空,源或無可識 I/O 式。啟調試日誌:workflow <- put_auto("./src/", log_level = "DEBUG") 以察何檔被掃、何式匹。

第四步:生初圖

視自察之工作流以估覆與識隙。

# Generate diagram from auto-detected workflow
cat(put_diagram(workflow, theme = "github"))

# With source file info for traceability
cat(put_diagram(workflow, show_source_info = TRUE))

# Save to file for review
writeLines(put_diagram(workflow, theme = "github"), "workflow-auto.md")

得: Mermaid 流圖,顯察之節以數流之緣相連。節以有義之函/檔名標之。

敗則: 若圖顯離節,自察得 I/O 式而不能推連。此常——連由匹輸出名於輸入名而出。下步之注計補隙。

第五步:生注計

生結構化之計,書所察與所需手注者。

# Generate annotation suggestions
put_generate("./src/", style = "single")

# For multiline style (more readable for complex workflows)
put_generate("./src/", style = "multiline")

# Copy suggestions to clipboard for easy pasting
put_generate("./src/", output = "clipboard")

書計附覆評:

## Annotation Plan

### Auto-Detected (no manual work needed)
- `src/etl/extract.R` — 3 inputs, 2 outputs detected
- `src/etl/transform.py` — 1 input, 1 output detected

### Needs Manual Annotation
- `src/api/handler.js` — Language supported but no I/O patterns matched
- `src/config/setup.sh` — Only 12 shell patterns; complex logic missed

### Not Supported
- `src/legacy/process.f90` — Fortran not in detection languages

### Recommended Connections
- extract.R output `data.csv` → transform.py input `data.csv` (auto-linked)
- transform.py output `clean.parquet` → load.R input (needs annotation)

得: 清計分自察檔與需手注者,各有具體薦。

敗則:put_generate() 無出,確目徑正且含支語之源檔。

  • put_auto() 於目目行而無訛
  • 察工作流至少一節(除非庫無可識 I/O)
  • put_diagram() 自自察工作流生有效 Mermaid 碼
  • put_generate() 為察式之檔生注薦
  • 注計文已立附覆評

  • 掃過廣:於庫根行 put_auto(".") 或納 node_modules/.git/venv/ 等。指定源目
  • 期全覆:自察得檔 I/O 與庫呼,非業邏。四至六成覆為常;餘需手注
  • 忽依detect_dependencies = TRUEsource()importrequire() 連本。禁之失跨檔連
  • 語不合:非標擴(如 .R.r.jsx.js)或不可察。以 get_comment_prefix() 察擴被識乎。無擴之檔如 DockerfileMakefile 經全名匹支
  • 大庫:百以上源檔之庫,按模/目析以保圖可讀

  • install-putior — 前置:putior 必先裝
  • annotate-source-files — 下步:按計添手注
  • generate-workflow-diagram — 注畢生終圖
  • configure-putior-mcp — 以 MCP 工具行互析會

GitHub Repository

pjt222/agent-almanac
Path: i18n/wenyan/skills/analyze-codebase-workflow
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

Related Skills

executing-plans

Design

Use the executing-plans skill when you have a complete implementation plan to execute in controlled batches with review checkpoints. It loads and critically reviews the plan, then executes tasks in small batches (default 3 tasks) while reporting progress between each batch for architect review. This ensures systematic implementation with built-in quality control checkpoints.

View skill

requesting-code-review

Design

This skill dispatches a code-reviewer subagent to analyze code changes against requirements before proceeding. It should be used after completing tasks, implementing major features, or before merging to main. The review helps catch issues early by comparing the current implementation with the original plan.

View skill

connect-mcp-server

Design

This skill provides a comprehensive guide for developers to connect MCP servers to Claude Code using HTTP, stdio, or SSE transports. It covers installation, configuration, authentication, and security for integrating external services like GitHub, Notion, and custom APIs. Use it when setting up MCP integrations, configuring external tools, or working with Claude's Model Context Protocol.

View skill

web-cli-teleport

Design

This skill helps developers choose between Claude Code Web and CLI interfaces based on task analysis, then enables seamless session teleportation between these environments. It optimizes workflow by managing session state and context when switching between web, CLI, or mobile. Use it for complex projects requiring different tools at various stages.

View skill