CtrlK
BlogDocsLog inGet started
Tessl Logo

extract-transcripts

Extract readable transcripts from Claude Code and Codex CLI session JSONL files

82

11.87x
Quality

74%

Does it follow best practices?

Impact

95%

11.87x

Average score across 3 eval scenarios

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xbigboss/claude-code/extract-transcripts/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

83%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an excellent, concise, fully actionable command reference. Its main weakness is the absence of validation/checkpoint guidance for the batch and indexing operations, which caps workflow clarity.

Suggestions

Add validation checkpoints for batch operations, e.g. 'After `index`, run `recent` to confirm sessions were ingested' or guidance on verifying output before relying on `--all`.

For `index --full`, note the destructive/overwriting nature of a reindex and recommend a verification step afterward.

Consider splitting the dense options list and DuckDB reference into a short reference file to push progressive disclosure toward 5.

DimensionReasoningScore

Conciseness

The body is a lean command reference with no padding or explanation of concepts Claude already knows; it assumes competence and every example earns its place.

5 / 5

Actionability

Provides fully executable, copy-paste-ready commands covering the common cases (single/all extraction, summary, output to file, Codex, and DuckDB index/search/show) with all flags documented.

5 / 5

Workflow Clarity

Commands are well-organized and the single-file path is clear, but batch operations (`--all`, `index --full`) and the `--skip-empty` flow lack validation checkpoints or error-recovery feedback loops; per the rubric, missing validation for batch operations caps workflow clarity at 3.

3 / 5

Progressive Disclosure

Single self-contained file with clear, well-labeled sections (Scripts, File Locations, DuckDB Index, Output Format) and no nested references; good structure overall, though the options list and DuckDB section are dense enough they could be split, so it is not a perfect 5.

4 / 5

Total

17

/

20

Passed

Description

65%Weight 40%Scale 1-5

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 is specific and clearly distinguishes a niche, but it omits any explicit "Use when..." trigger guidance, which caps its completeness. Adding a trigger clause and a few more natural synonyms would raise the score.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to extract or review transcripts from Claude Code or Codex CLI session .jsonl files.'

Include more natural trigger terms and synonyms such as '.jsonl', 'session logs', or 'conversation history' to broaden keyword coverage.

Optionally mention the secondary capabilities (index/search across sessions, summaries) to improve specificity and completeness.

DimensionReasoningScore

Specificity

Names the domain ("readable transcripts") and one concrete action ("Extract") from Claude Code and Codex CLI JSONL files, but does not enumerate the fuller range of capabilities (indexing, searching, summarizing) shown in the body, so it is not comprehensive.

3 / 5

Completeness

It clearly states what the skill does ("Extract readable transcripts from Claude Code and Codex CLI session JSONL files") but provides no "Use when..." clause or equivalent trigger guidance; per the rubric, a missing explicit trigger caps completeness at 3.

3 / 5

Trigger Term Quality

Contains natural terms users would say ("transcripts", "session", "Claude Code", "Codex CLI", "JSONL"), with good keyword coverage, though some synonyms/extensions (".jsonl", "logs", "history") are not present.

4 / 5

Distinctiveness Conflict Risk

Targets a clearly specific niche (Claude Code and Codex CLI session JSONL files) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

15

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
NeverSight/skills_feed
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.