extract-transcripts
Extract readable transcripts from Claude Code and Codex CLI session JSONL files
83
76%
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
72%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 clearly identifies a specific niche (extracting transcripts from Claude Code/Codex CLI JSONL files) with good trigger terms that users would naturally use. However, it lacks an explicit 'Use when...' clause and could benefit from listing additional concrete actions beyond just extraction to improve completeness and specificity.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user wants to read, review, or share Claude Code or Codex CLI conversation history from .jsonl session files.'
List additional concrete actions such as 'parse conversation turns, format assistant/user messages, summarize session activity' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (transcript extraction from JSONL files) and one action (extract readable transcripts), but doesn't list multiple concrete actions like formatting options, output types, or additional capabilities. | 2 / 3 |
Completeness | Clearly answers 'what' (extract readable transcripts from JSONL files) but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'transcripts', 'Claude Code', 'Codex CLI', 'session', 'JSONL files' — these are terms users would naturally use when needing this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche — Claude Code and Codex CLI session JSONL files are highly distinctive targets, making it very unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
79%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-written, actionable skill that provides concrete, executable commands for transcript extraction. Its main strengths are conciseness and actionability—every line serves a purpose with copy-paste ready examples. Minor weaknesses include the lack of explicit workflow sequencing for multi-step operations (like indexing then searching) and the content being slightly long for a single file without references to supplementary docs.
Suggestions
Add a brief 'Common Workflows' section showing the typical sequence: index sessions → search/list → show transcript, with explicit steps numbered.
Consider splitting the DuckDB indexer documentation into a separate INDEXER.md file and referencing it from the main skill, keeping SKILL.md focused on the core extraction use case.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It assumes Claude knows what JSONL files, transcripts, and CLI tools are. Every section provides concrete commands without unnecessary explanation. No padding or concept definitions. | 3 / 3 |
Actionability | Fully concrete and copy-paste ready. Every feature is demonstrated with exact bash commands, specific file paths, and clear option flags. The options are listed concisely with their effects. | 3 / 3 |
Workflow Clarity | The skill presents individual commands clearly but doesn't provide a sequenced workflow for common use cases (e.g., index then search). The DuckDB section implies a multi-step process (index → query) but doesn't explicitly sequence it or include validation checkpoints for the indexing step. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections, but it's somewhat long for a single SKILL.md. The DuckDB indexer section and the detailed options could potentially be split into separate reference files. However, the sections are clearly delineated and navigable. | 2 / 3 |
Total | 10 / 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
f772de4
- 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.