Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
49,415 skills from 2,407 repositories · updated 2 hours ago
10,666 skills
- asset-passportmachina-exm/film-studio-skillsCreate film-asset passports before generation. Use for characters, locations, props, and state variants that need repeatable visual identity.OtherNo warnings★ 172↓ —
- distributed-trace-analysisnaodeng/awesome-qa-skillsUse this skill when you need to analyze distributed traces for call paths, latency, errors, and evidence gaps; triggers include distributed trace analysis.OtherNo warnings★ 297↓ —
- regression-scope-analysisnaodeng/awesome-qa-skillsUse this skill when you need to define risk-based regression scope after a change or release; triggers include regression scope analysis.OtherNo warnings★ 297↓ —
- regression-optimizationnaodeng/awesome-qa-skillsUse this skill when you need evidence-bounded tradeoffs among regression selection, ordering, parallelism, caching, and risk preservation; triggers include 回归范围 and regression scope.OtherNo warnings★ 297↓ —
- regression-optimizationnaodeng/awesome-qa-skillsUse this skill when you need evidence-bounded tradeoffs among regression selection, ordering, parallelism, caching, and risk preservation; triggers include 回归范围 and regression scope.OtherNo warnings★ 297↓ —
- quality-risk-analysisnaodeng/awesome-qa-skillsUse this skill when you need to identify and prioritize quality risks from product, change, and evidence inputs; triggers include 质量风险分析 and quality risk analysis.OtherNo warnings★ 297↓ —
- quality-debt-analysisnaodeng/awesome-qa-skillsUse this skill when you need evidence-bounded quality-debt items, origins, impact, age, priority, ownership, and paydown tradeoffs; triggers include 质量债务 and quality debt.OtherNo warnings★ 297↓ —
- quality-debt-analysisnaodeng/awesome-qa-skillsUse this skill when you need evidence-bounded quality-debt items, origins, impact, age, priority, ownership, and paydown tradeoffs; triggers include 质量债务 and quality debt.OtherNo warnings★ 297↓ —
- tu-youyou-perspectiveBioTender-max/awesome-bio-agent-skills诺贝尔医学奖得主屠呦呦（Tu Youyou, 2015）的思维框架蒸馏。 核心镜片：从传统智慧中提取科学灵感的"古今转化"思维；低温突破决策。 警告：信息密度低（公开演讲/访谈极少），心智模型基于有限素材推断，诚实边界篇幅大。 触发词：「屠呦呦视角」「青蒿素思维」「古今转化」「传统中药现代化」。OtherNo warnings★ 215↓ —
- pytdcBioTender-max/awesome-bio-agent-skillsTherapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.OtherNo warnings★ 215↓ —
- anndataBioTender-max/awesome-bio-agent-skillsData structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.OtherNo warnings★ 215↓ —
- icaBioTender-max/awesome-bio-agent-skillsUse this model doc whenever the user wants to perform resting-state network decomposition using ICA. This is a non-deep-learning unsupervised route focused on extracting intrinsic connectivity networks, component maps, and subject-level time series from resting-state fMRI.OtherNo warnings★ 215↓ —
- scanpyBioTender-max/awesome-bio-agent-skillsStandard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use anndata.OtherNo warnings★ 215↓ —
- ci-failure-triageproflead/codex-skills-libraryDiagnose CI failures and stabilize pipelines. Use when a mid-level developer needs to resolve flaky or failing builds.OtherNo warnings★ 167↓ —
- ca-releasearbiterForge/codeArbiterPrepare a declared release target, or preview it with --dry-run. Derive its version and require authorization before publication.OtherReview first★ 151↓ —
- deepchemBioTender-max/awesome-bio-agent-skillsMolecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.OtherNo warnings★ 215↓ —
- repo-newTserenTserenov/FMT-exocortex-templateГейт создания любого нового репозитория IWE (экосистемного или личного пространства). Проводит запрос через: классификацию намерения (Pack / SpacePlan / именованный проект / экосистемный DS), проверку имени и класса, разметку данных (типы 2.1-2.4, карантин), объявление писатель/владелец/читатели, решение о публичности, обязательный Decision Gate (по умолчанию — одобрение пилота, для CI — ограниченное делегирование), затем исполнение (создание, регистрация, развёртывание скелета). Используй когда пилот хочет создать новый репозиторий, или спрашивает, куда и как разместить новый вид данных. Не для расширения существующего репозитория (→ Repo-Touch/Residency Gate) и не для Pack-репозиториев (делегируется `/pack-new`).OtherReview first★ 63↓ —
- bntBioTender-max/awesome-bio-agent-skillsUse this model doc whenever the user wants to run BrainNetworkTransformer for fMRI phenotype prediction, including data loading, training, and evaluation. BNT uses dense FC matrices (no PyG dependency) with DEC pooling + interpretable transformer encoder.OtherNo warnings★ 215↓ —
- longgraphlevi-qiao/longgraph-skillUse only when the user explicitly invokes /longgraph or names this skill. Routes and authors a durable longgraph run. Do not use unless named. Do not execute or resume generated runtime node files.OtherNo warnings★ 78↓ —
- xigong-funk-hikarialicewe1/alice_skillEvidence-driven Hikari-LLVM/OLLVM deobfuscation and plaintext recovery for ELF/SO, especially Android/Linux AArch64 PIE executables that use MBA, BCF/opaque predicates, relocation-backed BR/BLR dispatch, function wrappers/FCO, runtime string decoding, high-entropy containers, flat anonymous RX/RO/RW inner images without a primary ELF magic, embedded auxiliary ELFs, and custom mmap/mprotect loaders. Use when the user asks for Hikari identification, complete deobfuscation, lossless plaintext restoration, searchable strings, runtime payload dumping/rebuilding, an IDA-ready inner ELF, a directly runnable plaintext-bearing single file, or a loader-free rebuild. Produces hash-bound layer artifacts, reversible register-preserving patch manifests, runtime materialization evidence, and structure/semantic/runtime/equivalence verification.OtherNo warnings★ 62↓ —
- quality-risk-analysisnaodeng/awesome-qa-skillsUse this skill when you need to identify and prioritize quality risks from product, change, and evidence inputs; triggers include quality risk analysis.OtherNo warnings★ 297↓ —
- umap-learnBioTender-max/awesome-bio-agent-skillsUMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.OtherNo warnings★ 215↓ —
- bio-atac-seq-atac-qcBioTender-max/awesome-bio-agent-skillsATAC-seq library quality control -- TSS enrichment, FRiP, fragment-size periodicity, library complexity (NRF/PBC1/PBC2), mitochondrial fraction, and ENCODE 4 thresholds. Use when assessing whether an ATAC-seq library passes ENCODE acceptance criteria, diagnosing transposition artefacts, comparing Omni-ATAC vs standard prep quality, or selecting which replicates to drop before peak calling.OtherNo warnings★ 215↓ —
- scvi-toolsBioTender-max/awesome-bio-agent-skillsDeep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy.OtherNo warnings★ 215↓ —
alice
alicewe1/alice_skill
OtherUpdated Sep 29, 2026
From the author
Alice 六类技能总路由。用户输入 Alice 或要求查看 Alice 技能菜单时，严格输出固定菜单；输入攻/防模式、六类入口或直接描述任务时，按类别→领域→模块渐进路由。
Install
npx skills add alicewe1/alice_skill --skill alice -a claude-code
Installs to .claude/skills/alice/ · Each command fetches the skill straight from GitHub with the open skills CLI.
No download: this skill’s licence (GPL-3.0) does not let us redistribute its files. The install commands fetch them from GitHub instead.
What it can touch
Runs bundled scriptsNo network use seenLicence: GPL-3.0
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 74
Security85
Provenance61
Maintenance100
Licence80
Adoption31
Files (85)
- SKILL.md
- config/alice_dynamic.json
- config/authorization.json
- config/command_aliases.json
- config/system_objects.json
- config/task_guard.json
- config/word_filter.json
- contracts/alice_contract.json
- guard/armor_state.json
- guard/baseline.json
- guard/fortress_state.json
- guard/router_state.json
- +73 more