extract-transcripts
Extract readable transcripts from Claude Code and Codex CLI session JSONL files
75
Quality
63%
Does it follow best practices?
Impact
95%
11.87xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xbigboss/claude-code/extract-transcripts/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a clear, distinctive niche (Claude Code/Codex CLI session files) but suffers from incomplete guidance. It lacks explicit trigger conditions ('Use when...') and could benefit from additional natural keywords users might employ when seeking this functionality.
Suggestions
Add a 'Use when...' clause with trigger scenarios like 'Use when the user wants to read, convert, or analyze Claude Code or Codex CLI session files, or mentions JSONL conversation logs.'
Include additional natural trigger terms users might say: 'session logs', 'conversation history', 'chat export', '.jsonl files', 'session data'
Expand the action list to be more specific: 'Extract readable transcripts, convert to markdown, parse conversation turns from Claude Code and Codex CLI session JSONL files'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Claude Code and Codex CLI session files) and one action (extract readable transcripts), but doesn't list multiple concrete actions or detail what 'readable transcripts' entails. | 2 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes specific terms like 'Claude Code', 'Codex CLI', 'JSONL', and 'transcripts' which are relevant, but misses common variations users might say like 'session logs', 'conversation history', 'chat export', or '.jsonl files'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Claude Code and Codex CLI JSONL files specifically - unlikely to conflict with other skills due to the precise tool names and file format mentioned. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that efficiently documents transcript extraction tools with executable commands and clear organization. The main weakness is the lack of validation guidance for batch operations, though for a read-only extraction task this is less critical than for destructive operations.
Suggestions
Add a brief note about verifying extraction success, especially for batch '--all' operations (e.g., checking output file count or reviewing summary output)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, providing only necessary command examples and options without explaining what JSONL files are or how transcript extraction works conceptually. Every section serves a clear purpose. | 3 / 3 |
Actionability | Provides fully executable bash commands with real paths and flags. All examples are copy-paste ready with clear option descriptions and concrete file locations. | 3 / 3 |
Workflow Clarity | Commands are clearly listed but there's no explicit workflow sequence or validation steps. For batch operations like '--all' processing, there's no guidance on verifying results or handling errors. | 2 / 3 |
Progressive Disclosure | Content is well-organized into logical sections (Scripts, Session Locations, DuckDB Index, Output Format) with clear headers. The skill is appropriately self-contained without needing external references for this scope. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- NeverSight/skills_feed
- Commit
5342bca
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.