transcript-saver

Save and export the current Claude Code session as a shareable HTML transcript. Use this skill when the user asks to save, export, archive, or publish their current Claude Code conversation or session. Triggers on phrases like "save this transcript", "export this session", "create a transcript", "archive this conversation", "publish to gist", or "share this session". Wraps Simon Willison's claude-code-transcripts tool for in-session use.

2.83x

Quality

88%

Does it follow best practices?

Impact

85%

2.83x

Average score across 3 eval scenarios

Securityby

Critical

Do not install without reviewing

Quality

Content

81%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 content is highly actionable and clearly structured for a single-purpose skill, with executable commands and real script references. The main weakness is conciseness — repeated gist/gh instructions and overlapping example sections could be consolidated.

Suggestions

Consolidate the repeated GitHub CLI / gh auth install instructions into a single section (Installation Requirements) and have Troubleshooting reference it instead of restating it.

Merge or trim the 'Usage Examples' section, which largely duplicates the Quick Start commands, to reduce token overhead.

Consider removing the placeholder '/path/to/skill/' prefix in Quick Start in favor of the relative 'scripts/save_transcript.py' form used later, to avoid inconsistent path references.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but includes redundancy — the gist/gh install instructions appear in Installation Requirements, Troubleshooting, and Command Reference, and the Usage Examples largely restate the Quick Start commands, fitting the 'mostly efficient but could be tightened' anchor rather than the lean 'efficient' level above.	3 / 5
Actionability	Provides fully executable, copy-paste-ready commands in Quick Start, a complete option reference, and concrete troubleshooting fixes, matching the 'fully executable; copy-paste ready; specific examples cover common cases' anchor.	5 / 5
Workflow Clarity	This is a simple single-action skill (invoke save_transcript.py with flags); the single action is unambiguous and no destructive or batch operations are present, so the simple-skill exception allows the top score.	5 / 5
Progressive Disclosure	Well-organized single-file skill with a real referenced script (scripts/save_transcript.py) at one level deep and clear section navigation; minor organization gaps from duplicated example content keep it just below the 'clear overview, easy navigation' top anchor.	4 / 5
	Total	17 / 20 Passed

Description

95%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 strong, clearly stating what the skill does and when to use it, with comprehensive natural trigger phrases and a distinct niche. Minor specificity gaps (e.g., the exact output format beyond 'HTML transcript') keep specificity just below maximum.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Save and export the current Claude Code session as a shareable HTML transcript', 'publish to gist', 'Wraps Simon Willison's claude-code-transcripts tool') with only minor gaps in coverage, fitting the 'lists several specific actions; minor gaps' anchor.	4 / 5
Completeness	Explicitly answers both 'what' (save/export current session as HTML transcript, wraps claude-code-transcripts) and 'when' with concrete trigger phrases ('Use this skill when the user asks to save, export, archive, or publish...'), matching the top anchor.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural user phrases including synonyms — 'save this transcript', 'export this session', 'archive this conversation', 'publish to gist', 'share this session' — matching the 'comprehensive coverage of natural terms including synonyms' anchor.	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Claude Code transcript export) with distinct triggers and minimal overlap risk with other skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: fpl9000/ai-skills
Path: transcript-saver/SKILL.md
Commit: 46b1ac6

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.