Beautiful log
Skill BioTender-max/awesome-bio-agent-skills/skills/neuroclaw/beautiful-log
A curated collection of AI agent skills for biomedical research, covering genomics, proteomics, single-cell analysis, clinical AI, and protein design.
npx -y skills add BioTender-max/awesome-bio-agent-skills --skill beautiful-logAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
What its author says it does
Copied from the file, not written here
Use this skill after a conversation or task is completed when the user wants a clean, beautiful HTML chat log. It keeps only direct NeuroClaw <-> User dialogue, filters out tool calls / internal traces / SKILL.md reading notes, and renders distinct colored message cards for each side.
The file declares its own license as MIT License (NeuroClaw custom skill - freely modifiable within the project). That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.6 KB, as published. Nobody here has run it
Beautiful Log (Dialogue-to-HTML)
Overview
beautiful-log converts a conversation transcript into a clean, shareable HTML report.
It is designed for research logging and progress tracking, while removing noisy execution traces.
This skill:
- Keeps only direct dialogue between User and NeuroClaw.
- Filters out tool/system/internal content (for example: tool calls, file-read traces, SKILL.md parsing notes, hidden reasoning traces).
- Renders a polished HTML page with different background colors for User and NeuroClaw messages.
- Preserves message order and basic formatting (line breaks, code blocks as plain text).
When to Call This Skill
- A task is finished and the user wants a readable conversation archive.
- The user asks for an exportable discussion record.
- Weekly or daily research summary requires clean chat evidence.
Core Workflow (Never Bypassed)
- Receive input transcript file path (JSON, JSONL, or simple Markdown text export).
- Parse and normalize messages to a unified schema:
role,content,timestamp(optional). - Keep only
userandassistant/neuroclawroles. - Remove internal/tool/system traces.
- Generate HTML cards:
- User: warm light background card.
- NeuroClaw: cool light background card.
- Save output HTML to user-specified location.
- Return summary: kept messages, filtered messages, output path.
Input / Output
- Input: conversation export file (recommended JSON/JSONL).
- Output: standalone HTML file (no external assets required).
Recommended Script
Use:
scripts/beautiful_log.py
Example:
python skills/beautiful-log/scripts/beautiful_log.py \
--input logs/session_2026-04-05.jsonl \
--output logs/session_2026-04-05_beautiful.html \
--title "NeuroClaw Session Log"
Safety and Data Rules
- Do not include hidden reasoning or tool internals in final export.
- Keep only direct dialogue content.
- If sensitive information appears in user messages, recommend manual redaction before sharing externally.
Complementary / Related Skills
claw-shell(safe command execution)
Created At: 2026-04-05 23:26 HKT Last Updated At: 2026-04-05 23:26 HKT Author: chengwang96