Transparent ranking signals

Agent Skills rankings: trends, quality, and new repositories

These five boards answer different discovery questions. Trend boards use daily GitHub repository snapshots; quality uses deterministic documentation and repository signals. Neither is a substitute for an independent Skill test.

weekly

Weekly trend

Ordered by 7-day repository star change, with total stars used only when snapshot history is incomplete.

Read the full methodology
  1. 01brainstorming by obraYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.Cold start7-day repo stars
  2. 02dispatching-parallel-agents by obraUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesCold start7-day repo stars
  3. 03executing-plans by obraUse when you have a written implementation plan to execute in a separate session with review checkpointsCold start7-day repo stars
  4. 04finishing-a-development-branch by obraUse when implementation is complete, all tests pass, and you need to decide how to integrate the workCold start7-day repo stars
  5. 05receiving-code-review by obraUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationCold start7-day repo stars
  6. 06requesting-code-review by obraUse when completing tasks, implementing major features, or before merging to verify work meets requirementsCold start7-day repo stars
  7. 07subagent-driven-development by obraUse when executing implementation plans with independent tasks in the current sessionCold start7-day repo stars
  8. 08systematic-debugging by obraUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesCold start7-day repo stars
  9. 09test-driven-development by obraUse when implementing any feature or bugfix, before writing implementation codeCold start7-day repo stars
  10. 10using-git-worktrees by obraUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackCold start7-day repo stars
  11. 11using-superpowers by obraUse when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questionsCold start7-day repo stars
  12. 12verification-before-completion by obraUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysCold start7-day repo stars
  13. 13writing-plans by obraUse when you have a spec or requirements for a multi-step task, before touching codeCold start7-day repo stars
  14. 14writing-skills by obraUse when creating new skills, editing existing skills, or verifying skills work before deploymentCold start7-day repo stars
  15. 15accessibility by affaan-mWCAG 2.2 レベル AA 標準を用いてインクルーシブなデジタルプロダクトを設計・実装・監査します。Web 用のセマンティック ARIA および Web・ネイティブプラットフォーム（iOS/Android）のアクセシビリティトレイトを生成するために使用します。Cold start7-day repo stars
  16. 16accessibility by affaan-m使用 WCAG 2.2 Level AA 标准设计、实施和审计包容性数字产品。运用此技能为 Web 生成语义 ARIA，并为 Web 和原生平台（iOS/Android）生成无障碍特性。Cold start7-day repo stars
  17. 17accessibility by affaan-mDesign, implement, and audit inclusive digital products using WCAG 2.2 Level AA standards. Use this skill to generate semantic ARIA for Web and accessibility traits for Web and Native platforms (iOS/Android).Cold start7-day repo stars
  18. 18agent-architecture-audit by affaan-mエージェントおよび LLM アプリケーション向けのフルスタック診断。12 層のエージェントスタックにおけるラッパーリグレッション、メモリ汚染、ツール規律の失敗、隠れた修復ループ、レンダリング破損を監査します。重要度順の発見事項とコードファーストの修正を生成します。エージェントアプリケーション、自律ループ、または LLM を活用した機能を構築する開発者に必須です。Cold start7-day repo stars
  19. 19agent-architecture-audit by affaan-mFull-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.Cold start7-day repo stars
  20. 20agent-eval by affaan-mカスタムタスクでコーディングエージェント（Claude Code、Aider、Codex など）をヘッドツーヘッドで比較し、合格率、コスト、時間、一貫性のメトリクスを測定しますCold start7-day repo stars

monthly

Monthly momentum

Ordered by 30-day repository star change. This measures repository attention, not individual Skill quality.

Read the full methodology
  1. 01brainstorming by obraYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.Cold start30-day repo stars
  2. 02dispatching-parallel-agents by obraUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesCold start30-day repo stars
  3. 03executing-plans by obraUse when you have a written implementation plan to execute in a separate session with review checkpointsCold start30-day repo stars
  4. 04finishing-a-development-branch by obraUse when implementation is complete, all tests pass, and you need to decide how to integrate the workCold start30-day repo stars
  5. 05receiving-code-review by obraUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationCold start30-day repo stars
  6. 06requesting-code-review by obraUse when completing tasks, implementing major features, or before merging to verify work meets requirementsCold start30-day repo stars
  7. 07subagent-driven-development by obraUse when executing implementation plans with independent tasks in the current sessionCold start30-day repo stars
  8. 08systematic-debugging by obraUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesCold start30-day repo stars
  9. 09test-driven-development by obraUse when implementing any feature or bugfix, before writing implementation codeCold start30-day repo stars
  10. 10using-git-worktrees by obraUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackCold start30-day repo stars
  11. 11using-superpowers by obraUse when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questionsCold start30-day repo stars
  12. 12verification-before-completion by obraUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysCold start30-day repo stars
  13. 13writing-plans by obraUse when you have a spec or requirements for a multi-step task, before touching codeCold start30-day repo stars
  14. 14writing-skills by obraUse when creating new skills, editing existing skills, or verifying skills work before deploymentCold start30-day repo stars
  15. 15accessibility by affaan-mWCAG 2.2 レベル AA 標準を用いてインクルーシブなデジタルプロダクトを設計・実装・監査します。Web 用のセマンティック ARIA および Web・ネイティブプラットフォーム（iOS/Android）のアクセシビリティトレイトを生成するために使用します。Cold start30-day repo stars
  16. 16accessibility by affaan-m使用 WCAG 2.2 Level AA 标准设计、实施和审计包容性数字产品。运用此技能为 Web 生成语义 ARIA，并为 Web 和原生平台（iOS/Android）生成无障碍特性。Cold start30-day repo stars
  17. 17accessibility by affaan-mDesign, implement, and audit inclusive digital products using WCAG 2.2 Level AA standards. Use this skill to generate semantic ARIA for Web and accessibility traits for Web and Native platforms (iOS/Android).Cold start30-day repo stars
  18. 18agent-architecture-audit by affaan-mエージェントおよび LLM アプリケーション向けのフルスタック診断。12 層のエージェントスタックにおけるラッパーリグレッション、メモリ汚染、ツール規律の失敗、隠れた修復ループ、レンダリング破損を監査します。重要度順の発見事項とコードファーストの修正を生成します。エージェントアプリケーション、自律ループ、または LLM を活用した機能を構築する開発者に必須です。Cold start30-day repo stars
  19. 19agent-architecture-audit by affaan-mFull-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.Cold start30-day repo stars
  20. 20agent-eval by affaan-mカスタムタスクでコーディングエージェント（Claude Code、Aider、Codex など）をヘッドツーヘッドで比較し、合格率、コスト、時間、一貫性のメトリクスを測定しますCold start30-day repo stars

yearly

Yearly momentum

Ordered by 365-day repository star change when enough daily snapshots are available.

Read the full methodology
  1. 01brainstorming by obraYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.Cold start365-day repo stars
  2. 02dispatching-parallel-agents by obraUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesCold start365-day repo stars
  3. 03executing-plans by obraUse when you have a written implementation plan to execute in a separate session with review checkpointsCold start365-day repo stars
  4. 04finishing-a-development-branch by obraUse when implementation is complete, all tests pass, and you need to decide how to integrate the workCold start365-day repo stars
  5. 05receiving-code-review by obraUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationCold start365-day repo stars
  6. 06requesting-code-review by obraUse when completing tasks, implementing major features, or before merging to verify work meets requirementsCold start365-day repo stars
  7. 07subagent-driven-development by obraUse when executing implementation plans with independent tasks in the current sessionCold start365-day repo stars
  8. 08systematic-debugging by obraUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesCold start365-day repo stars
  9. 09test-driven-development by obraUse when implementing any feature or bugfix, before writing implementation codeCold start365-day repo stars
  10. 10using-git-worktrees by obraUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackCold start365-day repo stars
  11. 11using-superpowers by obraUse when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questionsCold start365-day repo stars
  12. 12verification-before-completion by obraUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysCold start365-day repo stars
  13. 13writing-plans by obraUse when you have a spec or requirements for a multi-step task, before touching codeCold start365-day repo stars
  14. 14writing-skills by obraUse when creating new skills, editing existing skills, or verifying skills work before deploymentCold start365-day repo stars
  15. 15accessibility by affaan-mWCAG 2.2 レベル AA 標準を用いてインクルーシブなデジタルプロダクトを設計・実装・監査します。Web 用のセマンティック ARIA および Web・ネイティブプラットフォーム（iOS/Android）のアクセシビリティトレイトを生成するために使用します。Cold start365-day repo stars
  16. 16accessibility by affaan-m使用 WCAG 2.2 Level AA 标准设计、实施和审计包容性数字产品。运用此技能为 Web 生成语义 ARIA，并为 Web 和原生平台（iOS/Android）生成无障碍特性。Cold start365-day repo stars
  17. 17accessibility by affaan-mDesign, implement, and audit inclusive digital products using WCAG 2.2 Level AA standards. Use this skill to generate semantic ARIA for Web and accessibility traits for Web and Native platforms (iOS/Android).Cold start365-day repo stars
  18. 18agent-architecture-audit by affaan-mエージェントおよび LLM アプリケーション向けのフルスタック診断。12 層のエージェントスタックにおけるラッパーリグレッション、メモリ汚染、ツール規律の失敗、隠れた修復ループ、レンダリング破損を監査します。重要度順の発見事項とコードファーストの修正を生成します。エージェントアプリケーション、自律ループ、または LLM を活用した機能を構築する開発者に必須です。Cold start365-day repo stars
  19. 19agent-architecture-audit by affaan-mFull-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.Cold start365-day repo stars
  20. 20agent-eval by affaan-mカスタムタスクでコーディングエージェント（Claude Code、Aider、Codex など）をヘッドツーヘッドで比較し、合格率、コスト、時間、一貫性のメトリクスを測定しますCold start365-day repo stars

quality

Documentation quality

A deterministic score based on documentation, specificity, maintenance, license, and static risk signals.

Read the full methodology
  1. 01ab-testing by coreyhaines31When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program100/100Automated quality
  2. 02churn-prevention by coreyhaines31When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers o100/100Automated quality
  3. 03design-intelligence by event4u-appGrounded design brief from the adopted corpus — style, WCAG-checked color tokens, typography, layout pattern, anti-patterns. Use on ui-design-brief or any which-style/palette/font/chart decision.100/100Automated quality
  4. 04design-system-capture by event4u-appWrite and maintain DESIGN.md + PRODUCT.md — captures visual decisions and interaction patterns so design tasks stay consistent across sessions without re-scanning past work.100/100Automated quality
  5. 05existing-ui-audit by event4u-appUse BEFORE writing or editing any non-trivial UI — inventories components, design tokens, shadcn primitives, and reusable patterns into state.ui_audit. Hard gate for the ui directive set.100/100Automated quality
  6. 06testing-anti-patterns by event4u-appUse BEFORE writing/changing tests, adding mocks, or test-only methods on production classes — vs mocking-the-mock, production pollution, partial mocks, and overfit/tautological assertions100/100Automated quality
  7. 07emil-design-eng by nexu-ioThis skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.99/100Automated quality
  8. 08design-review by event4u-appUse when the user says "review the design", "check the UI", or wants a comprehensive UI/UX review. Uses a 7-phase methodology covering interaction, responsiveness, accessibility, and more.99/100Automated quality
  9. 09agent-payment-x402 by affaan-mAdd x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol.98/100Automated quality
  10. 10codehealth-mcp by affaan-mReal-time structural Code Health via CodeScene MCP — review before edits, verify score deltas after changes, gate commits and PRs. Use when reviewing code quality, refactoring, checking if AI changes degraded a file, or before commit/PR.98/100Automated quality
  11. 11vite-patterns by affaan-mVite build tool patterns including config, plugins, HMR, env variables, proxy setup, SSR, library mode, dependency pre-bundling, and build optimization. Activate when working with vite.config.ts, Vite plugins, or Vite-based projects.98/100Automated quality
  12. 12gsap-scrolltrigger by nexu-ioOfficial GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is specified.98/100Automated quality
  13. 13dask by k-dense-aiDistributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.98/100Automated quality
  14. 14imaging-data-commons by k-dense-aiQuery and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.98/100Automated quality
  15. 15medchem by k-dense-aiMedicinal chemistry filters for compound triage. Apply drug-likeness rules (Lipinski, Veber, CNS), structural alert catalogs (PAINS, NIBR, ChEMBL), complexity metrics, and the medchem query language for library filtering.98/100Automated quality
  16. 16neurokit2 by k-dense-aiUse NeuroKit2 to build or audit reproducible research workflows for physiological time-series preprocessing, event/interval analysis, multimodal alignment, variability, and complexity. Trigger when code imports neurokit2 or needs its current APIs, schemas, and method-aware validation—not for diagnosis or device validation.98/100Automated quality
  17. 17higgsfield-generate by MoizIbnYousafUse when the user wants to generate an image or video via Higgsfield AI. Covers 30+ models: Soul V2, Seedance 2.0, Kling 3.0, Veo 3.1, GPT Image 2, Nano Banana 2. Also covers Marketing Studio — branded ad video/image with avatars and products. Use whenever: "generate an image", "make a video", "animate this photo", "image-to-video", "img2vid", "edit this image with AI", "produce a clip", "create an ad", "make a UGC video", "marketing video", "brand video", "TV spot", "import product from URL", "98/100Automated quality
  18. 18authz-review by event4u-appUse when reviewing authorization end-to-end — route → gate → policy → query scope → response filter — before changes to permissions, tenants, ownership, or admin flows.98/100Automated quality
  19. 19dependency-upgrade by event4u-appUse when upgrading dependencies — 'update framework X', 'bump runtime version', or 'upgrade packages'. Covers changelog review, breaking-change detection, and verification. Stack-agnostic.98/100Automated quality
  20. 20pest-testing by event4u-appUse when writing, generating, or improving Pest tests for Laravel — clear intent, good coverage, maintainable structure, and alignment with project testing conventions.98/100Automated quality

rising

New repositories

Recently created source repositories, ordered with the automated quality score as a secondary signal.

Read the full methodology
  1. 01ci-speedup by starslingdevAudits a repository's GitHub Actions workflows for CI optimization opportunities — missing caches, redundant setup, sleep-based readiness, long test jobs without sharding, full-history checkout, dead env vars, build-cache misconfig, and ~60 more patterns across caching, redundancy, parallelization, conditional execution, trigger scope, and hidden failures. Use when: (1) analyzing a repo's CI for optimization opportunities, (2) producing a prioritized report with measured wall-clock and runner-mi2026-07-22Repository created
  2. 02prompt-injection-auditor by screem500Security audit of LLM system prompts, agent instruction files (SKILL.md, AGENTS.md, CLAUDE.md), and agent configurations against prompt injection attacks. Use when the user wants to (1) audit or harden a system prompt or agent instructions against prompt injection, (2) review an agent skill or system prompt for security weaknesses before publishing, (3) generate a prompt-injection risk report with severity ratings and fixes, (4) run authorized red-team tests against an LLM agent they own or are 2026-07-19Repository created
  3. 03compute-env-setup by xuzhougengSet up and validate a reproducible Python or R environment on a Wisp execution context. Use for a selected local, WSL, or direct SSH context when installing scientific packages, configuring caches, recording interpreter activation, or producing an environment smoke test. Do not use for scheduler clusters or managed cloud providers that Wisp cannot track yet.2026-07-01Repository created
  4. 04skill-creator by xuzhougengCreate, update, validate, and evaluate Wisp skills. Use when authoring a project-local or installable skill, refining its trigger description, adding deterministic scripts or Python sidecars, or testing whether another Agent can follow the workflow.2026-07-01Repository created
  5. 05remote-compute-ssh by xuzhougengSubmit recoverable SSH-direct research Runs with live progress cards and model-free monitoring.2026-07-01Repository created
  6. 06browser-use by xuzhougengUse this skill to drive the user's real, persistent Chrome/Chromium session — open pages, read them, click, fill and submit forms, navigate, switch tabs, or scrape content that needs the user's existing cookies and login state. Triggers when the user asks to do something in their browser, log into a site and act inside it, fill out a web form, click through a flow, or extract data from a page that requires being signed in. Tools: browser_setup (check/connect the extension), web_open_tab (open a 2026-07-01Repository created
  7. 07figure-style by xuzhougengPublication-grade figure correctness and legibility rules. Load before drawing any plot 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), colour threading, chart-choice-by-data-shape, layout, and a render-then-verify QA loop (bbox collision + per-panel 2026-07-01Repository created
  8. 08journal-club-ppt by xuzhougengUse this skill whenever the user provides a scientific paper PDF and asks for a group-meeting literature report, journal-club slides, 文献汇报PPT, 组会PPT, paper presentation, article walkthrough, or to explain a paper with PowerPoint. The skill first reconstructs the paper's scientific logic, then builds author/background sections, chooses an evidence-driven slide outline, crops only main-text figure panels from the PDF, and creates an academic PPT with 10–30 slides including title and conclusion/dis2026-07-01Repository created
  9. 09esmfold2 by xuzhougengBiohub 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) P2026-07-01Repository created
  10. 10diffdock by xuzhougengPredict 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.2026-07-01Repository created
  11. 11self-awareness by xuzhougengWisp-science's actual agent tool surface and runtime boundaries. Load this when deciding which Wisp tool can perform a task, checking whether Python can reach agent or desktop capabilities, choosing between interactive analysis and persisted Runs, or answering questions about delegation, images, skills, memory, artifacts, lineage, credentials, session history, and other self-introspection capabilities.2026-07-01Repository created
  12. 12boltz by xuzhougengStructure 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.2026-07-01Repository created
  13. 13openfold3 by xuzhougengStructure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab. Use this skill when predicting protein/nucleic-acid/ligand complex structures with an Apache-2.0-licensed AF3 reimplementation.2026-07-01Repository created
  14. 14ligandmpnn by xuzhougengInverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be respected, or to get threaded designed-sequence PDBs out of any MPNN run.2026-07-01Repository created
  15. 15alphafold2 by xuzhougengPredict 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.2026-07-01Repository created
  16. 16local-env-setup by xuzhougengConfigure the local wisp-science runtime — uv/Python bootstrap, Node+scimaster-cli for bear-* literature skills, pixi for bioinformatics multi-env analysis. Detect mainland-China network and apply mirrors. Use when Capabilities shows missing Python/uv/Node/sci/pixi, bootstrap errors, or the user asks to 配置环境 / install Python / uv / Node / pixi / set up the local environment. Not for remote GPU/SSH compute (use compute-env-setup).2026-07-01Repository created
  17. 17proteinmpnn by xuzhougengInverse-fold a protein backbone (PDB structure) into amino-acid sequence with ProteinMPNN (Dauparas et al. 2022, github.com/dauparas/ProteinMPNN). Reach for this skill to run sequence design on RFdiffusion backbones, to redesign one chain of a PDB while holding interface residues fixed, or to generate a temperature-swept set of sequences for downstream folding.2026-07-01Repository created
  18. 18chai1 by xuzhougengStructure 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.2026-07-01Repository created
  19. 19evo2 by xuzhougengScore, 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.2026-07-01Repository created
  20. 20figure-composer by xuzhougengCompose or improve a publication-grade multi-panel scientific figure from a claim, concrete data paths, or an existing image. Use for figure outlining, parallel panel rendering, exact-grid composition, visual inspection, and adversarial figure review. Use figure-style for one standalone plot and paper-narrative for whole-paper figure ordering.2026-07-01Repository created

How to interpret these rankings

Star changes belong to the source repository, which may contain many Skills. “New” means the repository creation date, not the publication date of an individual SKILL.md. Quality is an automated screening score and does not claim that SkillSignal ran the Skill. Snapshot gaps fall back to total repository stars only as a cold-start ordering signal.