Claude skills and agent skills

JimLiuSkill

release-skills

JimLiu/baoyu-skills/.claude/skills/release-skills/SKILL.md

Universal release workflow. Auto-detects version files and changelogs. Supports Node.js, Python, Rust, Claude Plugin, GitHub Releases, annotated tags, historical release backfill, and generic projects. Use when user says "release", "发布", "new version", "bump version", "push", "推送", "release notes", "GitHub Release", or "回填 Release".

JimLiuSkill

claude-dashboard

JimLiu/baoyu-design/skills/claude-dashboard/SKILL.md

Use this for a local, data-backed dashboard, metrics page, KPI tracker, scorecard, data visualization or recurring report that opens in the bundled live editor: a page or scroll story of charts, numbers and tables over datasets (a CSV/TSV/JSON file the user has, or data you gather and attach), with a Sources panel that shows where every number comes from. Read it when creating, filling, refreshing or revising one. You write the datasets, then the page as plain HTML, into the dashboard's own store with this skill's script. Not for a static HTML mockup or a picture of a dashboard: that is the baoyu-design skill.

JimLiuSkill

claude-design

JimLiu/baoyu-design/skills/claude-design/SKILL.md

Make and revise designs in the Design (canvas) artifact format (project/canvas.json plus one .dc.html Design Component file per artboard) as local files, then open them in a local canvas editor where the user can view the artboards side by side, retype copy and adjust tweaks. Use when the user asks for an editable canvas of artboards in this format, names claude-design or the Design (canvas) type, or wants to revise a folder that holds project/canvas.json. A one-off HTML prototype or design exploration outside this format is baoyu-design's.

Often used withtouchdesigner-mcp·popular-web-designs·sdlc-review

JimLiuSkill

claude-design-system

JimLiu/baoyu-design/skills/claude-design-system/SKILL.md

Create and revise design systems in the Design System artifact format (project/design-system.json, tokens.json, a README brand book, component previews, fonts and asset groups) as local files, then open them in a local design-system page where the user can browse and edit tokens, type, components and assets. Use when the user asks for a design system or brand kit in this format, built from a code repository, a design tool or scratch, names claude-design-system or the Design System type, or wants to revise a folder that holds project/design-system.json. claude-slides and claude-design install these systems. A free-form HTML style guide, UI kit or token page is baoyu-design's.

JimLiuSkill

claude-slides

JimLiu/baoyu-design/skills/claude-slides/SKILL.md

Make and revise slide decks in the Slides artifact format (project/deck.json plus one HTML file per slide) as local files, then open them in a local slide editor where the user can present, retype, drag, and export PDF, HTML or PowerPoint. Use when the user asks for an editable slide deck or presentation in this format, names claude-slides or the Slides type, or wants to revise a folder that holds project/deck.json. A one-off single-file HTML deck or prototype is baoyu-design's.

JimLiuSkill

dataviz

JimLiu/baoyu-design/skills/dataviz/SKILL.md

Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium (HTML/React artifact, inline SVG, matplotlib/plotly/d3/Recharts, PNG). Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / KPI row, or laying out a dashboard. Teaches a design-system-agnostic method - form heuristic, color formula with a runnable validator, mark specs, interaction rules. Default palette in references/palette.md.

JimLiuSkill

bcut-release

JimLiu/baocut/.agents/skills/bcut-release/SKILL.md

Release BaoCut Electron desktop apps through GitHub Actions tags by default; use local/manual packaging only when explicitly requested. Also handles App version bumps, release continuation and portable signing backups; excludes craft skills and legacy standalone CLI releases.

No other project uses it yet

JimLiuSkill

baocut

JimLiu/baocut/skills/baocut/SKILL.md

用 BaoCut 处理视频与音频：转录、字幕、翻译、配音、剪口播、切短视频、分章、总结写稿、从链接下载、压缩转码、导出成片，或从零做一条成片。有媒体文件、视频链接、字幕文件或 BaoCut 视频时用；只翻译纯文本、与视频无关的写作或作图、别的剪辑器与 FFmpeg 的用法、BaoCut 源码开发不用。

JimLiuSkill

alphafold2

JimLiu/science-skills/skills/alphafold2/SKILL.md

Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022, github.com/sokrypton/ColabFold; AlphaFold2 Jumper et al. 2021). Reach for this skill to fold a sequence or complex with the AF2/AF2-Multimer evoformer, to validate designed sequences by self-consistency pLDDT, ipTM, and RMSD, or to run a quick MSA-backed prediction using the public MMseqs2 server.

JimLiuSkill

boltz

JimLiu/science-skills/skills/boltz/SKILL.md

Structure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend et al. 2025, github.com/jwohlwend/boltz). Reach for this skill to validate designed binders against a target, to co-fold a protein with a SMILES or CCD ligand, or to get an open-source AlphaFold3 alternative with optional binding-affinity prediction.

JimLiuSkill

borzoi

JimLiu/science-skills/skills/borzoi/SKILL.md

Predict genome-wide functional tracks (RNA-seq, CAGE, DNase, ChIP) from DNA sequence with Borzoi. Use this skill when: (1) Scoring the regulatory effect of a variant on expression/accessibility, (2) Generating predicted coverage tracks for a locus, (3) Prioritizing non-coding variants by predicted track delta.

JimLiuSkill

chai1

JimLiu/science-skills/skills/chai1/SKILL.md

Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model (Chai Discovery 2024, github.com/chaidiscovery/chai-lab). Reach for this skill to predict an antibody-antigen or protein-ligand complex from a single FASTA, to re-fold designed binders as an AlphaFold-multimer alternative, or to drive co-folding from Python for batched campaigns on a GPU.

JimLiuSkill

compute-env-setup

JimLiu/science-skills/skills/compute-env-setup/SKILL.md

Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its own software stack, or wiring weight caches. Triggers on "new compute provider", "set up env on", "port env to", "build GPU image", "weight cache", "compute_details", "conda env on the box", "apptainer on slurm".

JimLiuSkill

customize

JimLiu/science-skills/skills/customize/SKILL.md

Create, configure, and maintain custom agent profiles and author new skills via the `repl` tool. Use when the user wants to create an agent profile, build a custom agent, modify agent capabilities, attach or detach skills/connectors on a profile, author a skill, or inspect which connectors and tools are available. Also use whenever you need the `host.agents.*` or `host.skills.*` Python SDK.

Often used withadd-discord·add-telegram-swarm·add-anydoc

JimLiuSkill

diffdock

JimLiu/science-skills/skills/diffdock/SKILL.md

Predict small-molecule binding poses with DiffDock-L (Corso et al. 2023/2024, github.com/gcorso/DiffDock) — blind diffusion docking that places a ligand into a protein pocket without a predefined search box and ranks the samples with a learned confidence model. Reach for this skill to dock a SMILES or SDF against a PDB, to generate ranked 3D poses for a small fragment library, or to get a starting pose for downstream rescoring. DiffDock predicts geometry, not affinity.

JimLiuSkill

esmfold2

JimLiu/science-skills/skills/esmfold2/SKILL.md

Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and MSA modes; protein, DNA, RNA, ligand (CCD/SMILES), modified residues. FoldBench Ab-Ag 50-55%, PPI 70-77% DockQ-pass. Also covers the ESMC-{300M,600M,6B} protein language models from the same release: masked-LM logits, hidden states, mutation scoring, contact prediction, and the SAE interpretability head. MIT-licensed weights on HuggingFace org `biohub`. Use this skill when: (1) Predicting complex structures with single-sequence input, (2) Validating designed binders with ESMFold2-Fast, (3) Running ESMFold2 with MSA input, (4) Getting ESMC embeddings or per-residue mutation scores, (5) Choosing kernel backend and sampling-step settings for paper-faithful throughput.

JimLiuSkill

evo2

JimLiu/science-skills/skills/evo2/SKILL.md

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring regulatory or coding regions across species.

JimLiuSkill

fair-esm2

JimLiu/science-skills/skills/fair-esm2/SKILL.md

Embed proteins with Meta AI's ESM-2 (`fair-esm` package). Use this skill when: (1) Extracting per-residue or per-sequence embeddings for downstream ML, (2) Masked-LM likelihood / mutation effect scoring, (3) Contact prediction from a sequence.

JimLiuSkill

figure-composer

JimLiu/science-skills/skills/figure-composer/SKILL.md

Compose one publication-grade multi-panel figure. Entry from a one-line claim + data refs, OR from an existing figure via `derive_outline(png)`. Runs a per-figure loop: outline (12-col grid, per-panel ask + label_budget) → fan-out one sub-agent per panel (each loads `figure-style`) → tile + stamp letters → adversarial composite review with two-tier feedback (Tier-1 outline_revisions / Tier-2 per-panel violations) → regen affected panels, ≤3 rounds. Loads panel_task / compose_figure / compose_crops / composite_review_task / derive_outline into the kernel. For one standalone plot use `figure-style`; for whole-paper figure ordering use `paper-narrative`.

JimLiuSkill

figure-style

JimLiu/science-skills/skills/figure-style/SKILL.md

Publication-grade figure correctness and legibility rules for final-deliverable figures — not every plot. Quick look or iterating on the analysis (EDA scatters, sanity-check histograms)? Plot plainly without this skill. Producing a figure that ships — report, paper, export, or kept artifact — load this skill first and call `apply_figure_style()` — sets a role-mapped font-size ladder, outward ticks, frameless legends, and 300-dpi output. The skill is a checklist, not a house look: data fidelity (claim-titles tested against every row, excluded data never enters summaries), label economy (floor and ceiling), color threading, chart-choice-by-data-shape, layout, and a render-then-verify QA loop (bbox collision + per-panel perceptual check). Ships helpers: focal_palette, bar_with_points, strip_with_median, end_of_line_labels, panel_letter, set_frame, panel_crops. For multi-panel figures load `figure-composer`; for whole-paper figure arc load `paper-narrative`.