GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills，按职业与使用场景整理，复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoft
openclaw
@openclaw
OpenAI
@openai
The Apache Software Foundation
@apache
GitHub
@github
Anthropic
@anthropics
AutoGPT
@Significant-Gravitas
Garry Tan
@garrytan全部 Skills 196628
no-evals
Fixture without an evals/ directory.
evaluating-cosmos-policy
Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.
empty-evals
Fixture with an empty evals array.
valid
Fixture with a valid evals.json.
non-sequential-ids
Fixture whose evals.json ids are not sequential.
evaluating-cosmos-policy
Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.
name-mismatch
Fixture whose evals.json skill_name doesn't match SKILL.md.
missing-field
Fixture whose evals.json is missing a required eval field.
transformer-lens-interpretability
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
duplicate-ids
Fixture whose evals.json has duplicate ids.
gtb-eslint-config
ESLint configuration guidance for projects using @gtbuchanan/eslint-config. Covers the configure() API and options, pre-commit isolated-environment setup via createRequire, the bundled plugin set, suppression conventions, the two-plugin Markdown lint split, gitignore-derived ignores, and the per-package vs. workspace-root config split. Trigger keywords - @gtbuchanan/eslint-config, eslint.config.ts, configure, ESLintConfigureOptions, eslint-disable, eslint-disable-next-line, gitignore, defaultIgnores, eslint-config-flat-gitignore, markdownlint-disable, --max-warnings, dist/.eslintcache, lint:eslint, ESLint flat config, ESLint suppression.
transformer-lens-interpretability
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
gtb-build-pipeline
Build pipeline guidance for projects using @gtbuchanan/cli. Covers the Turborepo task graph, gtb sync and verify, the gtb hk pre-commit runner, the gtb changeset catalog gate, the gtb turbo wrapper (with the Android/Termux escape hatch), consumer script customization, and test-bucket strategy. Trigger keywords - @gtbuchanan/cli, @gtbuchanan/pnpm-termux-shim, turbo.json, gtb sync, gtb verify, gtb turbo, gtb task, gtb hk, gtb changeset check, hk:all, hk:base, mise.tasks.toml, pnpm catalog, compile:ts, pack:npm, deploy:skills, task graph, transit.
systems-paper-writing
Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.
systems-paper-writing
Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
pyvene-interventions
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.