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 192262
evaluating-llms-harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
evaluating-llms-harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
evaluating-code-models
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
evaluating-code-models
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
openspec-propose
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
special-order
Cook a slice with the customer's specifications on the spot: add new features mid-flight to an existing project. Auto-detects project type and extends the master checklist with new stages.
setup-shop
Start the oven, check ingredients, prep the shop. Bootstrap a new project or configure ByTheSlice in an existing one. First-time install, system-wide config, or per-project setup.
set-display-case
Build the display case the pies will sit in, bootstrap your design system: tokens, Tailwind config, design rules, and the operator-only /library preview route. Run once before /sell-slice; also invocable standalone on any project.
sell-slice
Sell a customer their slice - the high-touch single-slice delivery loop. Execute one slice from your master checklist as an interactive spine (prep gate · recon · build-plan auth · /goal · branch) + Workflow A (produce) + library gate + Workflow B (verify-once). Run me repeatedly, one fresh chat per slice. For autonomous whole-pie baking use /sell-pie.
sell-pie
Bake a whole Pie autonomously - the v5 forefront delivery loop. A /loop-driven baker that drives ONE Pie (a coherent chapter, usually 3 to 8 slices) to "ready for review" without per-slice prompting; each slice runs the context-separated build→test→verify→fix Workflow, commits + pushes (no PR), and advances; when every slice is [x] it stops at the pie boundary and opens one PR via /box-it-up. Refuses flat v4 checklists (points you at /cook-pizzas --repie). For a continuous-review pie (review=continuous) it runs in high-touch /sell-slice mode. Opt-in merge-per-slice delivery (delivery.mode, or an explicit autonomous-delivery run instruction) instead gives each slice its own branch, PR and green-CI merge; opt-in ship-once delivery (delivery.mode, set by /pizza-party) merges each pie into one local ship branch on local gates only and ships one PR at the end. The four blocking HITL categories halt the loop instead of rescheduling (an unattended ship-once run defers the slice instead). Use when the user runs /sell-pie, says "sell a pie", "bake the pie", "run the next pie", "loop the pie", or wants one whole chapter delivered hands-off. For a single careful slice use /sell-slice; for the whole app end to end use /pizza-party.
pizza-party
Cater a whole app, start to finish: from a short brief to a finished, deployed app with a URL. One interview up front (AskUserQuestion), then no human stops: /setup-shop, /create-menu, /cook-pizzas, the Prep pie, every pie through /sell-pie in ship-once delivery (all gates local), one PR that ships the app, a deploy to whatever host the operator has authorized (or an artifact or localhost link), and a run record for comparing runs over time. Every decision a sub-skill would normally ask about is decided, recorded in the order ticket, and the run continues. Use when the user runs /pizza-party, sets a /goal to build an app end to end, or says "build me this app end to end", "from scratch to production", "pizza party", "bake the whole roadmap" or "run all pies".
open-the-shop
Doors unlocked, lights flipped, OPEN sign up - scan environment requirements and verify all external service credentials are populated. The most HITL-heavy prep step; the operator personally stocks the cash drawer. Run once before /sell-slice; also invocable standalone.
open-kitchen
Open the project's approved 3D kitchen in the native Browser pane with a verified localhost state connection, or with --lobby the machine-level lobby of every ByTheSlice project.
inspect-display
Walk the display tray and eyeball every pie that's already on display: a cross-cutting, platform-wide visual walkthrough of a running web app. Catches what's broken, mocked, or empty across the WHOLE product, not just the latest slice. Read-only. Use before UAT, before a demo, after a batch of `/box-it-up` runs, or any time the checklist and reality have drifted.
final-quality-check
Install the quality line every pie passes through before going on display: wire CI/CD, E2E testing, design-system compliance, and visual-regression gates. Run once before /sell-slice; also invocable standalone on any project.