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.

Install with Tessl CLI

npx tessl i github:fpl9000/ai-skills --skill transcript-saver

What are skills?

Review — 82%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 11 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

90%

72%

Session Archival Automation

Local transcript archival with auto-naming

Criteria

Without context

With context

Uses save_transcript.py

100%

Correct --output flag

100%

Auto-name flag used

100%

uvx as primary runner

75%

uv install command

100%

index.html mentioned

100%

Paginated pages mentioned

100%

Session source documented

100%

75%

python invocation

100%

pip fallback mentioned

28%

Without context: $0.3337 · 1m 32s · 22 turns · 67 in / 5,538 out tokens

With context: $0.4214 · 1m 16s · 22 turns · 26 in / 4,016 out tokens

100%

52%

Public Transcript Sharing Workflow

GitHub Gist publishing workflow

Criteria

Without context

With context

Uses save_transcript.py

100%

--gist flag used

100%

gh CLI prerequisite

100%

gh auth login step

100%

gh install command

100%

uv/uvx prerequisite

100%

uv install command

100%

Preview URL documented

80%

100%

Missing CLI handling

100%

python invocation

100%

Without context: $0.2639 · 1m 22s · 11 turns · 14 in / 5,091 out tokens

With context: $0.3882 · 1m 20s · 18 turns · 271 in / 4,429 out tokens

66%

40%

Complete Session Archive with Raw Data

Specific session export with raw data inclusion

Criteria

Without context

With context

Uses save_transcript.py

83%

--session-id flag used

--include-json flag used

53%

--output flag used

62%

~/.claude/projects/ referenced

100%

JSONL format mentioned

100%

Error on missing session

100%

index.html in output docs

100%

Page files in output docs

100%

python invocation

uv/uvx referenced

60%

Without context: $0.4330 · 1m 44s · 22 turns · 93 in / 6,561 out tokens

With context: $0.4824 · 1m 32s · 22 turns · 26 in / 5,460 out tokens

Evaluated: about 13 hours ago
Agent: Claude Code

Table of Contents

Session Archival Automation Public Transcript Sharing Workflow Complete Session Archive with Raw Data

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.