transcript-analyzer

Included with Lifetime

$97 forever

Analyze Claude Code session transcripts to debug plugins, understand context usage, and trace execution flow

AI Agentsscripts

What this skill does


# Transcript Analyzer Skill

Use this skill when you need to analyze Claude Code session transcripts for:
- Debugging plugin behavior
- Understanding context/token usage patterns
- Tracing tool execution flow
- Finding sources of context bloat
- Investigating errors or unexpected behavior

## Transcript Location

Claude Code stores session transcripts at:
```
~/.claude/projects/-PATH-TO-PROJECT/*.jsonl
```

The path uses dashes instead of slashes. For example:
- Project: `/Users/bfreis/dev/myproject`
- Transcripts: `~/.claude/projects/-Users-bfreis-dev-myproject/*.jsonl`

## Transcript Structure

Transcripts use **JSONL format** (one JSON object per line).

### Record Types

| Type | Description |
|------|-------------|
| `summary` | Session metadata |
| `file-history-snapshot` | File change tracking |
| `user` | User messages (includes tool results) |
| `assistant` | Assistant messages (includes tool calls) |

### Message Structure

```json
{
  "type": "user" | "assistant",
  "uuid": "message-uuid",
  "parentUuid": "parent-message-uuid",
  "sessionId": "session-uuid",
  "isSidechain": false,
  "timestamp": "2025-12-06T...",
  "message": {
    "role": "user" | "assistant",
    "content": [...],
    "usage": { "input_tokens": N, "output_tokens": N }
  }
}
```

### Content Block Types

**In assistant messages:**
- `text` - Regular text response
- `tool_use` - Tool invocation with `.id`, `.name`, `.input`
- `thinking` - Extended thinking blocks

**In user messages:**
- `text` - User input
- `tool_result` - Tool output with `.tool_use_id`, `.content`

### Critical Gotchas

1. **Content is ALWAYS an array** - Even single text blocks
2. **Tool result `.content` can be string OR array** - Handle both:
   ```jq
   if .content | type == "array" then
     (.content | map(.text // "") | add)
   else
     .content
   end
   ```
3. **Use `[]?` not `[]`** - Handles missing fields gracefully
4. **Sub-agents have `isSidechain: true`** - Filter these for main conversation only
5. **`parentUuid` links threads** - Not line order

## Using transcript-tool

The skill provides a CLI at `scripts/transcript-tool`:

```bash
# Quick overview
transcript-tool summary session.jsonl

# Find context bloat sources
transcript-tool bloat session.jsonl 15

# Tool usage breakdown
transcript-tool tools session.jsonl

# Trace specific tool
transcript-tool trace-tool session.jsonl Read

# Find errors
transcript-tool errors session.jsonl

# Custom jq query
transcript-tool extract session.jsonl '.type'
```

## Common Analysis Workflows

### 1. Debug Plugin Behavior

```bash
# Find skill invocations
transcript-tool trace-skill session.jsonl plan-generator

# See what tools were used
transcript-tool tools session.jsonl

# Check for errors
transcript-tool errors session.jsonl
```

### 2. Investigate Context Bloat

```bash
# Find largest tool results
transcript-tool bloat session.jsonl 20

# Message size analysis
transcript-tool messages session.jsonl

# Identify specific large results
transcript-tool extract session.jsonl '
  select(.type == "user") |
  .message.content[]? |
  select(.type == "tool_result") |
  select((.content | tostring | length) > 10000) |
  .tool_use_id
'
```

### 3. Trace Execution Flow

```bash
# All tool calls in order
transcript-tool extract session.jsonl '
  select(.type == "assistant") |
  .message.content[]? |
  select(.type == "tool_use") |
  "\(.name): \(.input | keys | join(", "))"
'
```

## Raw jq Recipes

For complex analysis, use jq directly:

**Count content block types:**
```bash
jq -r '
  select(.type == "user" or .type == "assistant") |
  .message.content[]? |
  .type
' session.jsonl | sort | uniq -c
```

**Find tool call by ID:**
```bash
jq -r --arg id "toolu_xxx" '
  select(.type == "assistant") |
  .message.content[]? |
  select(.type == "tool_use" and .id == $id)
' session.jsonl
```

**Get corresponding tool result:**
```bash
jq -r --arg id "toolu_xxx" '
  select(.type == "user") |
  .message.content[]? |
  select(.type == "tool_result" and .tool_use_id == $id) |
  .content
' session.jsonl
```

**Token usage per message:**
```bash
jq -r '
  select(.type == "assistant" and .message.usage) |
  "\(.message.usage.input_tokens) in, \(.message.usage.output_tokens) out"
' session.jsonl
```

Files: 2

Size: 10.5 KB

Complexity: 29/100

Category: AI Agents

Source: https://github.com/bfreis/claude-mart/tree/main/plugins/transcript-analyzer/skills/transcript-analyzer

Related in AI Agents

skill-development

Included

Comprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.

AI Agentsscripts

reprompter

Included

Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.

AI Agentsscripts

adaptive-compaction

Included

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.

AI Agentsscripts

agent-skill-creator

Included

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

AI Agentsscripts

llm-wiki

Included

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

AI Agentsscripts

skill-master

Included

Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.

AI Agentsscripts