asciinema-analyzer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

asciinema-analyzer

Semantic analysis of converted .txt recordings for Claude Code consumption. Uses tiered analysis: ripgrep (primary, 50-200ms) -> YAKE (secondary, 1-5s) -> TF-IDF (optional).

Platform: macOS, Linux (requires ripgrep, optional YAKE)

针对Claude Code的转换后.txt录屏文件语义分析工具。采用分层分析机制：ripgrep（核心工具，耗时50-200ms）-> YAKE（次要工具，耗时1-5s）-> TF-IDF（可选）。

平台支持: macOS、Linux（需要安装ripgrep，YAKE为可选依赖）

When to Use This Skill

适用场景

Use this skill when:

Searching for keywords or patterns in converted recordings
Extracting topics or themes from session transcripts
Finding specific commands or errors in session history
Auto-discovering unexpected terms in recordings
Analyzing session content for documentation or review

在以下场景中使用本工具：

在转换后的录屏文件中搜索关键词或模式
从会话转录文本中提取主题或核心内容
在会话历史中查找特定命令或错误信息
自动发现录屏文件中的异常术语
分析会话内容用于文档编写或复盘评审

Analysis Tiers

分层分析机制

Tier	Tool	Speed (4MB)	When to Use
1	ripgrep	50-200ms	Always start here (curated)
2	YAKE	1-5s	Auto-discover unexpected terms
3	TF-IDF	5-30s	Topic modeling (optional)

Decision: Start with Tier 1 (ripgrep + curated keywords). Only use Tier 2 (YAKE) when auto-discovery is explicitly requested.

层级	工具	处理速度（4MB文件）	适用场景
1	ripgrep	50-200ms	优先使用（精准匹配预设关键词）
2	YAKE	1-5s	自动发现未预设的异常术语
3	TF-IDF	5-30s	主题建模（可选功能）

决策建议：从第1层级开始（ripgrep + 预设关键词集）。仅当明确需要自动发现功能时，才使用第2层级（YAKE）。

Requirements

依赖要求

Component	Required	Installation	Notes
ripgrep	Yes	`brew install ripgrep`	Primary search tool
YAKE	Optional	`uv run --with yake`	For auto-discovery tier

组件	是否必需	安装方式	说明
ripgrep	是	`brew install ripgrep`	核心搜索工具
YAKE	可选	`uv run --with yake`	用于自动发现层级的分析

Workflow Phases (ALL MANDATORY)

工作流阶段（全部为必填步骤）

IMPORTANT: All phases are MANDATORY. Do NOT skip any phase. AskUserQuestion MUST be used at each decision point.

重要提示：所有阶段均为必填，请勿跳过任何步骤。在每个决策点必须使用AskUserQuestion交互。

Phase 0: Preflight Check

阶段0：前置检查

Purpose: Verify input file exists and check for .txt (converted) format.

bash

/usr/bin/env bash << 'PREFLIGHT_EOF'
INPUT_FILE="${1:-}"

if [[ -z "$INPUT_FILE" ]]; then
  echo "NO_FILE_PROVIDED"
elif [[ ! -f "$INPUT_FILE" ]]; then
  echo "FILE_NOT_FOUND: $INPUT_FILE"
elif [[ "$INPUT_FILE" == *.cast ]]; then
  echo "WRONG_FORMAT: Convert to .txt first with /asciinema-tools:convert"
elif [[ "$INPUT_FILE" == *.txt ]]; then
  SIZE=$(ls -lh "$INPUT_FILE" | awk '{print $5}')
  LINES=$(wc -l < "$INPUT_FILE" | tr -d ' ')
  echo "READY: $INPUT_FILE ($SIZE, $LINES lines)"
else
  echo "UNKNOWN_FORMAT: Expected .txt file"
fi
PREFLIGHT_EOF

If no .txt file found, suggest running

/asciinema-tools:convert

first.

目的：验证输入文件是否存在，并检查是否为.txt（转换后）格式。

bash

/usr/bin/env bash << 'PREFLIGHT_EOF'
INPUT_FILE="${1:-}"

if [[ -z "$INPUT_FILE" ]]; then
  echo "NO_FILE_PROVIDED"
elif [[ ! -f "$INPUT_FILE" ]]; then
  echo "FILE_NOT_FOUND: $INPUT_FILE"
elif [[ "$INPUT_FILE" == *.cast ]]; then
  echo "WRONG_FORMAT: Convert to .txt first with /asciinema-tools:convert"
elif [[ "$INPUT_FILE" == *.txt ]]; then
  SIZE=$(ls -lh "$INPUT_FILE" | awk '{print $5}')
  LINES=$(wc -l < "$INPUT_FILE" | tr -d ' ')
  echo "READY: $INPUT_FILE ($SIZE, $LINES lines)"
else
  echo "UNKNOWN_FORMAT: Expected .txt file"
fi
PREFLIGHT_EOF

如果未找到.txt文件，建议先运行

/asciinema-tools:convert

进行格式转换。

Phase 1: File Selection (MANDATORY)

阶段1：文件选择（必填）

Purpose: Discover .txt files and let user select which to analyze.

目的：发现当前目录下的.txt文件，并让用户选择要分析的文件。

Step 1.1: Discover .txt Files

步骤1.1：发现.txt文件

bash

/usr/bin/env bash << 'DISCOVER_TXT_EOF'

bash

/usr/bin/env bash << 'DISCOVER_TXT_EOF'

Find .txt files that look like converted recordings

查找看起来是转换后录屏的.txt文件

for file in $(fd -e txt . --max-depth 3 2>/dev/null | head -10); do SIZE=$(ls -lh "$file" 2>/dev/null | awk '{print $5}') LINES=$(wc -l < "$file" 2>/dev/null | tr -d ' ') BASENAME=$(basename "$file") echo "FILE:$file|SIZE:$SIZE|LINES:$LINES|NAME:$BASENAME" done DISCOVER_TXT_EOF

undefined

undefined

Step 1.2: Present File Selection (MANDATORY AskUserQuestion)

步骤1.2：展示文件选择选项（必须使用AskUserQuestion）

Question: "Which file would you like to analyze?"
Header: "File"
Options:
  - Label: "{filename}.txt ({size})"
    Description: "{line_count} lines"
  - Label: "{filename2}.txt ({size2})"
    Description: "{line_count2} lines"
  - Label: "Enter path"
    Description: "Provide a custom path to a .txt file"
  - Label: "Convert first"
    Description: "Run /asciinema-tools:convert before analysis"

问题: "你想分析哪个文件？"
标题: "文件选择"
选项:
  - 标签: "{filename}.txt ({size})"
    描述: "{line_count} 行"
  - 标签: "{filename2}.txt ({size2})"
    描述: "{line_count2} 行"
  - 标签: "输入路径"
    描述: "提供自定义的.txt文件路径"
  - 标签: "先转换格式"
    描述: "在分析前运行 /asciinema-tools:convert 转换格式"

Phase 2: Analysis Type (MANDATORY)

阶段2：分析类型选择（必填）

Purpose: Let user choose analysis depth.

Question: "What type of analysis do you need?"
Header: "Type"
Options:
  - Label: "Curated keywords (Recommended)"
    Description: "Fast search (50-200ms) with domain-specific keyword sets"
  - Label: "Auto-discover keywords"
    Description: "YAKE unsupervised extraction (1-5s) - finds unexpected patterns"
  - Label: "Full analysis"
    Description: "Both curated + auto-discovery for comprehensive results"
  - Label: "Density analysis"
    Description: "Find high-concentration sections (peak activity windows)"

目的：让用户选择分析的深度。

问题: "你需要哪种类型的分析？"
标题: "分析类型"
选项:
  - 标签: "预设关键词分析（推荐）"
    描述: "基于领域专属关键词集的快速搜索（耗时50-200ms）"
  - 标签: "自动发现关键词"
    描述: "YAKE无监督提取（耗时1-5s）- 发现未预设的模式"
  - 标签: "全面分析"
    描述: "同时进行预设关键词分析和自动发现，获取完整结果"
  - 标签: "密度分析"
    描述: "查找关键词浓度最高的段落（活跃峰值区间）"

Phase 3: Domain Selection (MANDATORY)

阶段3：领域选择（必填）

Purpose: Let user select which keyword domains to search.

Question: "Which domain keywords to search?"
Header: "Domain"
multiSelect: true
Options:
  - Label: "Trading/Quantitative"
    Description: "sharpe, sortino, calmar, backtest, drawdown, pnl, cagr, alpha, beta"
  - Label: "ML/AI"
    Description: "epoch, loss, accuracy, sota, training, model, validation, inference"
  - Label: "Development"
    Description: "iteration, refactor, fix, test, deploy, build, commit, merge"
  - Label: "Claude Code"
    Description: "Skill, TodoWrite, Read, Edit, Bash, Grep, iteration complete"

See Domain Keywords Reference for complete keyword lists.

目的：让用户选择要搜索的关键词领域。

问题: "你想搜索哪个领域的关键词？"
标题: "领域选择"
支持多选: 是
选项:
  - 标签: "交易/量化金融"
    描述: "sharpe、sortino、calmar、backtest、drawdown、pnl、cagr、alpha、beta"
  - 标签: "机器学习/人工智能"
    描述: "epoch、loss、accuracy、sota、training、model、validation、inference"
  - 标签: "软件开发"
    描述: "iteration、refactor、fix、test、deploy、build、commit、merge"
  - 标签: "Claude Code"
    描述: "Skill、TodoWrite、Read、Edit、Bash、Grep、iteration complete"

完整关键词列表请参考领域关键词参考文档。

Phase 4: Execute Curated Analysis

阶段4：执行预设关键词分析

Purpose: Run Grep searches for selected domain keywords.

目的：针对选中的领域运行Grep搜索。

Step 4.1: Trading Domain

步骤4.1：交易领域

bash

/usr/bin/env bash << 'TRADING_EOF'
INPUT_FILE="${1:?}"
echo "=== Trading/Quantitative Keywords ==="

KEYWORDS="sharpe sortino calmar backtest drawdown pnl cagr alpha beta roi volatility"
for kw in $KEYWORDS; do
  COUNT=$(rg -c -i "$kw" "$INPUT_FILE" 2>/dev/null || echo "0")
  if [[ "$COUNT" -gt 0 ]]; then
    echo "  $kw: $COUNT"
  fi
done
TRADING_EOF

bash

/usr/bin/env bash << 'TRADING_EOF'
INPUT_FILE="${1:?}"
echo "=== 交易/量化金融关键词分析 ==="

KEYWORDS="sharpe sortino calmar backtest drawdown pnl cagr alpha beta roi volatility"
for kw in $KEYWORDS; do
  COUNT=$(rg -c -i "$kw" "$INPUT_FILE" 2>/dev/null || echo "0")
  if [[ "$COUNT" -gt 0 ]]; then
    echo "  $kw: $COUNT"
  fi
done
TRADING_EOF

Step 4.2: ML/AI Domain

步骤4.2：机器学习/人工智能领域

bash

/usr/bin/env bash << 'ML_EOF'
INPUT_FILE="${1:?}"
echo "=== ML/AI Keywords ==="

KEYWORDS="epoch loss accuracy sota training model validation inference tensor gradient"
for kw in $KEYWORDS; do
  COUNT=$(rg -c -i "$kw" "$INPUT_FILE" 2>/dev/null || echo "0")
  if [[ "$COUNT" -gt 0 ]]; then
    echo "  $kw: $COUNT"
  fi
done
ML_EOF

bash

/usr/bin/env bash << 'ML_EOF'
INPUT_FILE="${1:?}"
echo "=== 机器学习/人工智能关键词分析 ==="

KEYWORDS="epoch loss accuracy sota training model validation inference tensor gradient"
for kw in $KEYWORDS; do
  COUNT=$(rg -c -i "$kw" "$INPUT_FILE" 2>/dev/null || echo "0")
  if [[ "$COUNT" -gt 0 ]]; then
    echo "  $kw: $COUNT"
  fi
done
ML_EOF

Step 4.3: Development Domain

步骤4.3：软件开发领域

bash

/usr/bin/env bash << 'DEV_EOF'
INPUT_FILE="${1:?}"
echo "=== Development Keywords ==="

KEYWORDS="iteration refactor fix test deploy build commit merge debug error"
for kw in $KEYWORDS; do
  COUNT=$(rg -c -i "$kw" "$INPUT_FILE" 2>/dev/null || echo "0")
  if [[ "$COUNT" -gt 0 ]]; then
    echo "  $kw: $COUNT"
  fi
done
DEV_EOF

bash

/usr/bin/env bash << 'DEV_EOF'
INPUT_FILE="${1:?}"
echo "=== 软件开发关键词分析 ==="

KEYWORDS="iteration refactor fix test deploy build commit merge debug error"
for kw in $KEYWORDS; do
  COUNT=$(rg -c -i "$kw" "$INPUT_FILE" 2>/dev/null || echo "0")
  if [[ "$COUNT" -gt 0 ]]; then
    echo "  $kw: $COUNT"
  fi
done
DEV_EOF

Step 4.4: Claude Code Domain

步骤4.4：Claude Code领域

bash

/usr/bin/env bash << 'CLAUDE_EOF'
INPUT_FILE="${1:?}"
echo "=== Claude Code Keywords ==="

KEYWORDS="Skill TodoWrite Read Edit Bash Grep Write"
for kw in $KEYWORDS; do
  COUNT=$(rg -c "$kw" "$INPUT_FILE" 2>/dev/null || echo "0")
  if [[ "$COUNT" -gt 0 ]]; then
    echo "  $kw: $COUNT"
  fi
done

bash

/usr/bin/env bash << 'CLAUDE_EOF'
INPUT_FILE="${1:?}"
echo "=== Claude Code关键词分析 ==="

KEYWORDS="Skill TodoWrite Read Edit Bash Grep Write"
for kw in $KEYWORDS; do
  COUNT=$(rg -c "$kw" "$INPUT_FILE" 2>/dev/null || echo "0")
  if [[ "$COUNT" -gt 0 ]]; then
    echo "  $kw: $COUNT"
  fi
done

Special patterns

特殊模式匹配

ITERATION=$(rg -c "iteration complete" "$INPUT_FILE" 2>/dev/null || echo "0") echo " 'iteration complete': $ITERATION" CLAUDE_EOF

---

ITERATION=$(rg -c "iteration complete" "$INPUT_FILE" 2>/dev/null || echo "0") echo " 'iteration complete': $ITERATION" CLAUDE_EOF

---

Phase 5: YAKE Auto-Discovery (if selected)

阶段5：YAKE自动发现分析（若选中）

Purpose: Run unsupervised keyword extraction.

bash

/usr/bin/env bash << 'YAKE_EOF'
INPUT_FILE="${1:?}"
echo "=== Auto-discovered Keywords (YAKE) ==="

uv run --with yake python3 -c "
import yake

kw = yake.KeywordExtractor(
    lan='en',
    n=2,           # bi-grams
    dedupLim=0.9,  # dedup threshold
    top=20         # top keywords
)

with open('$INPUT_FILE') as f:
    text = f.read()

keywords = kw.extract_keywords(text)
for score, keyword in keywords:
    print(f'{score:.4f}  {keyword}')
"
YAKE_EOF

目的：运行无监督关键词提取。

bash

/usr/bin/env bash << 'YAKE_EOF'
INPUT_FILE="${1:?}"
echo "=== YAKE自动发现关键词 ==="

uv run --with yake python3 -c "
import yake

kw = yake.KeywordExtractor(
    lan='en',
    n=2,           # 提取双词组合
    dedupLim=0.9,  # 去重阈值
    top=20         # 提取前20个关键词
)

with open('$INPUT_FILE') as f:
    text = f.read()

keywords = kw.extract_keywords(text)
for score, keyword in keywords:
    print(f'{score:.4f}  {keyword}')
"
YAKE_EOF

Phase 6: Density Analysis (if selected)

阶段6：密度分析（若选中）

Purpose: Find sections with highest keyword concentration.

bash

/usr/bin/env bash << 'DENSITY_EOF'
INPUT_FILE="${1:?}"
KEYWORD="${2:-sharpe}"
WINDOW_SIZE=100  # lines

echo "=== Density Analysis: '$KEYWORD' ==="
echo "Window size: $WINDOW_SIZE lines"
echo ""

TOTAL_LINES=$(wc -l < "$INPUT_FILE" | tr -d ' ')
TOTAL_MATCHES=$(rg -c -i "$KEYWORD" "$INPUT_FILE" 2>/dev/null || echo "0")

echo "Total matches: $TOTAL_MATCHES in $TOTAL_LINES lines"
echo "Overall density: $(echo "scale=4; $TOTAL_MATCHES / $TOTAL_LINES * 1000" | bc) per 1000 lines"
echo ""

目的：查找关键词浓度最高的段落。

bash

/usr/bin/env bash << 'DENSITY_EOF'
INPUT_FILE="${1:?}"
KEYWORD="${2:-sharpe}"
WINDOW_SIZE=100  # 窗口大小（行数）

echo "=== 密度分析: '$KEYWORD' ==="
echo "窗口大小: $WINDOW_SIZE 行"
echo ""

TOTAL_LINES=$(wc -l < "$INPUT_FILE" | tr -d ' ')
TOTAL_MATCHES=$(rg -c -i "$KEYWORD" "$INPUT_FILE" 2>/dev/null || echo "0")

echo "总匹配次数: $TOTAL_MATCHES 次，共 $TOTAL_LINES 行"
echo "整体密度: $(echo "scale=4; $TOTAL_MATCHES / $TOTAL_LINES * 1000" | bc) 次/千行"
echo ""

Find peak windows

查找峰值窗口

echo "Top 5 densest windows:" awk -v ws="$WINDOW_SIZE" -v kw="$KEYWORD" ' BEGIN { IGNORECASE=1 } { lines[NR] = $0 if (tolower($0) ~ tolower(kw)) matches[NR] = 1 } END { for (start = 1; start <= NR - ws; start += ws/2) { count = 0 for (i = start; i < start + ws && i <= NR; i++) { if (matches[i]) count++ } if (count > 0) { printf "Lines %d-%d: %d matches (%.1f per 100)\n", start, start+ws-1, count, count*100/ws } } } ' "$INPUT_FILE" | sort -t: -k2 -rn | head -5 DENSITY_EOF

---

echo "关键词密度最高的5个窗口:" awk -v ws="$WINDOW_SIZE" -v kw="$KEYWORD" ' BEGIN { IGNORECASE=1 } { lines[NR] = $0 if (tolower($0) ~ tolower(kw)) matches[NR] = 1 } END { for (start = 1; start <= NR - ws; start += ws/2) { count = 0 for (i = start; i < start + ws && i <= NR; i++) { if (matches[i]) count++ } if (count > 0) { printf "第 %d-%d 行: %d 次匹配 (每百行 %.1f 次)\n", start, start+ws-1, count, count*100/ws } } } ' "$INPUT_FILE" | sort -t: -k2 -rn | head -5 DENSITY_EOF

---

Phase 7: Report Format (MANDATORY)

阶段7：报告格式选择（必填）

Purpose: Let user choose output format.

Question: "How should results be presented?"
Header: "Output"
Options:
  - Label: "Summary table (Recommended)"
    Description: "Keyword counts + top 5 peak sections"
  - Label: "Detailed report"
    Description: "Full analysis with timestamps and surrounding context"
  - Label: "JSON export"
    Description: "Machine-readable output for further processing"
  - Label: "Markdown report"
    Description: "Save formatted report to file"

目的：让用户选择结果的展示格式。

问题: "你希望结果以什么格式展示？"
标题: "输出格式"
选项:
  - 标签: "汇总表格（推荐）"
    描述: "关键词统计结果 + 前5个密度峰值段落"
  - 标签: "详细报告"
    描述: "包含时间戳和上下文的完整分析结果"
  - 标签: "JSON导出"
    描述: "机器可读格式，便于后续处理"
  - 标签: "Markdown报告"
    描述: "保存为格式化的Markdown文件"

Phase 8: Follow-up Actions (MANDATORY)

阶段8：后续操作选择（必填）

Purpose: Guide user to next action.

Question: "Analysis complete. What's next?"
Header: "Next"
Options:
  - Label: "Jump to peak section"
    Description: "Read the highest-density section in the file"
  - Label: "Search for specific keyword"
    Description: "Grep for a custom term with context"
  - Label: "Cross-reference with .cast"
    Description: "Map findings back to original timestamps"
  - Label: "Done"
    Description: "Exit - no further action needed"

目的：引导用户进行后续操作。

问题: "分析完成。接下来要做什么？"
标题: "后续操作"
选项:
  - 标签: "跳转至峰值段落"
    描述: "查看文件中关键词密度最高的段落"
  - 标签: "搜索自定义关键词"
    描述: "使用Grep搜索自定义术语并展示上下文"
  - 标签: "与.cast文件关联"
    描述: "将分析结果映射回原始录屏的时间戳"
  - 标签: "完成"
    描述: "退出 - 无需进一步操作"

TodoWrite Task Template

TodoWrite任务模板

1. [Preflight] Check input file exists and is .txt format
2. [Preflight] Suggest /convert if .cast file provided
3. [Discovery] Find .txt files with line counts
4. [Selection] AskUserQuestion: file to analyze
5. [Type] AskUserQuestion: analysis type (curated/auto/full/density)
6. [Domain] AskUserQuestion: keyword domains (multi-select)
7. [Curated] Run Grep searches for selected domains
8. [Auto] Run YAKE if auto-discovery selected
9. [Density] Calculate density windows if requested
10. [Format] AskUserQuestion: report format
11. [Next] AskUserQuestion: follow-up actions

1. [前置检查] 验证输入文件存在且为.txt格式
2. [前置检查] 若提供的是.cast文件，建议先运行/convert进行转换
3. [发现] 查找带行数统计的.txt文件
4. [选择] 询问用户：要分析的文件
5. [类型] 询问用户：分析类型（预设/自动/全面/密度）
6. [领域] 询问用户：关键词领域（支持多选）
7. [预设分析] 针对选中领域运行Grep搜索
8. [自动分析] 若选中自动发现，则运行YAKE
9. [密度分析] 若请求则计算密度窗口
10. [格式] 询问用户：报告格式
11. [后续] 询问用户：后续操作

Post-Change Checklist

修改后检查清单

After modifying this skill:

All bash blocks use heredoc wrapper
Curated keywords match references/domain-keywords.md
Analysis tiers match references/analysis-tiers.md
YAKE invocation uses
```
uv run --with yake
```
All AskUserQuestion phases are present
TodoWrite template matches actual workflow

在修改本工具后，请检查以下内容：

所有bash代码块均使用heredoc包装
预设关键词与
```
references/domain-keywords.md
```
保持一致
分层分析机制与
```
references/analysis-tiers.md
```
保持一致
YAKE调用使用
```
uv run --with yake
```
命令
所有AskUserQuestion交互阶段均已包含
TodoWrite模板与实际工作流一致

Reference Documentation

参考文档

Domain Keywords Reference
Analysis Tiers Reference
ripgrep Manual
YAKE Documentation

领域关键词参考文档
分层分析机制参考文档
ripgrep官方手册
YAKE官方文档

Troubleshooting

故障排查

Issue	Cause	Solution
"WRONG_FORMAT" error	.cast file provided	Run /asciinema-tools:convert first to create .txt
ripgrep not found	Not installed	`brew install ripgrep`
YAKE import error	Package not installed	`uv run --with yake` handles this automatically
No keywords found	Wrong domain selected	Try different domain or auto-discovery mode
Density analysis empty	Keyword not in file	Use curated search first to find valid keywords
File too large for YAKE	Memory constraints	Use Tier 1 (ripgrep) only for large files
Zero matches in all domains	File is binary or corrupted	Verify file is plain text with `file` command
fd command not found	Not installed	`brew install fd` or use `find` alternative

问题	原因	解决方案
出现"WRONG_FORMAT"错误	提供了.cast格式文件	先运行/asciinema-tools:convert转换为.txt格式
找不到ripgrep	未安装ripgrep	执行 `brew install ripgrep` 进行安装
YAKE导入错误	未安装YAKE依赖	`uv run --with yake` 会自动处理依赖安装
未找到任何关键词	选择的领域不正确	尝试更换领域或使用自动发现模式
密度分析结果为空	文件中无该关键词	先使用预设搜索找到有效的关键词
YAKE处理大文件失败	内存限制	仅使用第1层级（ripgrep）处理大文件
所有领域均无匹配结果	文件为二进制或已损坏	使用 `file` 命令验证文件是否为纯文本格式
找不到fd命令	未安装fd	执行 `brew install fd` 或使用 `find` 命令替代