agent-skills
CLAUDE.md4 starsChanged 3 months agoMITView on GitHub
This repository contains AI agent skills for Claude Code. Skills are grouped by category under skills/: Each skill is a self-contained folder with a SKILL.md and optional scripts. When the user asks to install skills from this repository: To install ALL skills:
In this repository12 other files it gives its agents.
- qr-codeSkill
- snu-etl-video-downloaderSkill
- snu-tennis-reserveSkill
- whisper-transcribeSkill
- jcr-if-extractSkill
- paper-figure-pptxSkill
- paper-readingSkill
- pptx-formatterSkill
- pptx-to-pdfSkill
- pre-proofSkill
- scientific-paper-coachSkill
- structure-visualizerSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
When the user asks to install skills from this repository:
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CLAUDE.md
What this repo is
This repository contains AI agent skills for Claude Code. Skills are grouped by category under skills/:
skills/research/— research workflow skills (computational chemistry, papers, slides)skills/life/— everyday-life automation skills
Each skill is a self-contained folder with a SKILL.md and optional scripts.
How to install skills from this repo
When the user asks to install skills from this repository:
- Copy the desired skill folders into
~/.claude/skills/(flat — category folders are for organizing this repo only) - Each skill folder should be copied as-is (preserving its directory structure)
Example:
cp -r skills/research/structure-visualizer ~/.claude/skills/To install ALL skills:
cp -r skills/research/* skills/life/* ~/.claude/skills/- After copying, check the skill's
SKILL.mdfor Python dependencies and first-run setup: every skill asks the user once for any personal settings it needs (paths, author info, companions, conda env) and stores them in local files (e.g.config.local.json,authors.json,members.local.json) next to the installed SKILL.md. These files stay on the user's machine and must never be committed.
Skill list
research/
| Skill | Description |
structure-visualizer | Render atomic/molecular structures as publication-quality PNG using OVITO Tachyon |
pptx-to-pdf | Convert PPTX to PDF by rasterizing each slide as a 7K image — renders identically on any machine regardless of installed fonts |
paper-reading | Deep-read a scientific paper PDF and produce full Korean translation + critical review |
pre-proof | Final proofreading / anomaly hunt for manuscripts before submission (10-pass checker) |
scientific-paper-coach | Review or write scientific manuscripts against a 200+-item academic-writing checklist — PASS/FAIL review mode + checklist-first write mode |
jcr-if-extract | Extract Clarivate JCR Impact Factors for a journal list → multi-year IF database, trend plot, and single-file HTML report with year-over-year movers |
paper-figure-pptx | Paper-figure pipeline: matplotlib draws the ink, every label becomes an editable PowerPoint text box, and PNG + fully vector SVG are regenerated from the hand-edited PPTX |
pptx-formatter | PPT formatter + pre-proof: fixes only pointed-out items with animations verified untouched, audits fonts / sizes / alignment / line breaks / overflow via PowerPoint COM |
life/
| Skill | Description |
snu-tennis-reserve | Auto-grab SNU tennis court reservations the moment they open (Monday 9:30 KST) via Playwright |
snu-etl-video-downloader | Download SNU eTL/LCMS lecture videos by content_id (parallel, with failure detection) |
whisper-transcribe | Transcribe lecture videos to text with OpenAI Whisper (ffmpeg extraction + GPU pipeline, battle-tested pitfalls included) |
qr-code | Generate print/slide-ready QR code PNGs (860×860, high error correction, black frame) from URLs/phone/text and verify each by decoding it back |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.