Borrowing it
Nothing to install: this file belongs to CHENyiru3/AI-Skills-Collections. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CHENyiru3/AI-Skills-Collections/master/CLAUDE.mdgit clone --depth 1 https://github.com/CHENyiru3/AI-Skills-CollectionsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/chenyiru3/ai-skills-collections/claude-md)<a href="https://agentmods.dev/instructions/chenyiru3/ai-skills-collections/claude-md"><img src="https://agentmods.dev/badge/instructions/chenyiru3/ai-skills-collections/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/chenyiru3/ai-skills-collections/claude-md"><img src="https://agentmods.dev/badge/instructions/chenyiru3/ai-skills-collections/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02629 | $0.02629 |
| Opus 5.5 | $0.01052 | $0.01052 |
| Sonnet 5.5 | $0.00526 | $0.00526 |
| Haiku 4.5 | $0.00263 | $0.00263 |
Grade A, and why
AI-Skills-Collections CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is an AI Skills repository — a collection of skills for AI agents organized around a four-layer architecture. The repo serves as a skills-market (what skills exist), registry (stable identity), deployments (machine install plans), and taskpacks (workflow-specific bundles).
Skills cover document workflows, website maintenance, Python library development, AI/ML, computational biology, and writing tools.
Core Design Principle
Do not use folder path as the real identity. Folder paths are human-readable organization only. The registry is the source of truth.
# Bad: path as identity
skills:
- compbio-skills/single-cell/analysis/scanpy
# Good: stable ID resolves through registry
skills:
- scanpy
# registry/skills.yaml
scanpy:
id: scanpy
canonical_path: skills-market/compbio/single-cell/analysis/scanpy
domain: compbio
status: active
This decoupling lets you reorganize folders without breaking deployments.
Architecture: Four Layers
skills-market/ ← canonical skill library (human-readable org)
registry/ ← source of truth: stable IDs, paths, metadata
deployments/ ← machine/profile install plans
taskpacks/ ← project/workflow-specific skill bundles
Repository Structure
ai_skills/
README.md
CLAUDE.md
pyproject.toml
skills-market/
core/
dev/
skill-creator/
skill-seekers/
documentation/
security/
security-audit/
bitwarden/
performance/
performance/
usage/
programming/
python/
project-setup/
code-quality/
testing-strategy/
api-design/
documentation/
packaging/
release-management/
cli-development/
community/
library-review/
jupyter/
sqlite/
ai-ml/
deep-learning/
pytorch/
llm/
transformers/
huggingface-hub/
peft/
trl/
bitsandbytes/
cursor-usage-checker/
training/
pytorch-lightning/
accelerate/
datasets/
deepspeed/
utility/
token-usage-checker/
provider-usage-checker/
compbio/
single-cell/
analysis/
scanpy/
seurat/
scvi-tools/
anndata/
integration/
seurat-v5/
harmony/
scanorama/
bbknn/
visualization/
cellxgene/
cellxgene-census/
spatial-omics/
analysis/
squidpy/
giotto/
spatialdata/
visualization/
vitessce/
platforms/
stereo-seq/
visium/
multiomics/
scRNA-seq/
pydeseq2/
scATAC-seq/
archr/
signac/
integration-tools/
scribble/
metabolomics/
metabolomics-workbench/
proteomics/
uniprot/
databases/
kegg/
reactome/
geo/
human-cell-atlas/
ensembl/
workflows/
snakemake/
nextflow/
writing/
academic/
academic-writing-editor/
humanizer/
humanizer-zh/
literature/
zotpilot/
latex/
latex-writing/
compile-latex/
obsidian/
obsidian-markdown/
obsidian-cli/
obsidian-bases/
json-canvas/
defuddle/
wiki-keeper/
documents/
office/
officecli/
officecli-docx/
officecli-pptx/
officecli-xlsx/
formats/
xlsx/
docx/
pptx/
pdf/
design/
algorithmic-art/
brand-guidelines/
canvas-design/
frontend-design/
theme-factory/
web-artifacts-builder/
webapp-testing/
collaboration/
doc-coauthoring/
internal-comms/
media/
imgur-cli/
slack-gif-creator/
agents/
claude-code/
codex/
hermes-agent/
opencode/
ag-ui/
mcp/
mcp-builder/
guidelines/
karpathy-guidelines/
frontend/
site-maintenance/
page-keeper/
chen-academic-page-maintainer/
projects/
codebti/
experimental/
incubating/
deprecated/
unregistered/
registry/
skills.yaml # every skill: id, canonical_path, domain, status, tags, profiles, taskpacks
aliases.yaml # old_path → skill id (for backward compatibility)
deprecated.yaml # deprecated skills with replacement IDs
missing.yaml # expected-but-absent skills with proposed paths
schema.skill.yaml # JSON Schema for skill entries
schema.profile.yaml # JSON Schema for deployment profiles
deployments/ # machine profiles
base.yaml
macos-personal.yaml
research-server.yaml
gpu-server.yaml
hpc.yaml
writing-workstation.yaml
frontend-workstation.yaml
agent-coding.yaml
taskpacks/ # workflow/project bundles
paper-writing.yaml
document-export.yaml
zotpilot-literature-map.yaml
pytorch-model-dev.yaml
llm-finetuning.yaml
single-cell-analysis.yaml
spatial-omics-analysis.yaml
bio-databases.yaml
workflow-engineering.yaml
codebti.yaml
feast.yaml
thesis-defense.yaml
scripts/
migrate_skills.py
validate_registry.py
validate_profiles.py
install_profile.py
list_skills.py
resolve_alias.py
docs/
architecture.md
migration-plan.md
naming-conventions.md
profile-design.md
skill-authoring.md
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 494 lines · 2,629 tokens per session scan A e6666b6ff2aa
AI-Skills-Collections CLAUDE.md is an instructions file published in the GitHub repository CHENyiru3/AI-Skills-Collections (1 stars, last pushed 7d ago), licensed MIT. It adds 2,629 tokens to every session, about $0.0105 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
generative-ai-for-beginners AGENTS.md
AGENTS.md instructions for microsoft/generative-ai-for-beginners, covering agents.md, project overview, setup commands, initial repository setup and clone the repository.