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。

01 /

按职业浏览 Agent Skills

为不同岗位挑选的高频技能

全部职业
02 /

按使用场景浏览 Agent Skills

从你要完成的任务出发

全部场景
03 /

按创作者浏览 Agent Skills

按 GitHub Stars 排序的优秀创作者

全部创作者

全部 Skills 482556

AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

tools-creusot-init

Prepare an existing Cargo project to use Creusot formal verification

★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

tools-creusot-extract-spec-prop

Build and maintain a simplified spec-to-proof documentation set for Creusot by extracting properties from component specs, tracking assumptions/trusted boundaries, and generating drift/coverage reports.

★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

tools-creusot-coq-install

Add Coq 8.20 as an additional prover to an existing Creusot installation, for verification conditions that SMT solvers cannot discharge

★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

tools-creusot-annotate-interfaces

Formally verify a component's properties with Creusot and annotate its interface definitions

★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

tools-count-sloc

Present a summary of the code base including lines of source code and complexity metrics.

★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

tools-codex-bridge-setup

Set up the claude-codex-bridge so Claude Code can talk to OpenAI Codex CLI (and vice versa) via MCP.

Skill与智能体开发
★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

tools-aggregate-coverage-by-interface

Render the ONE combined per-component scoring page (`<component>_scoring.html`) from the reconciled `unified_properties.yaml` — per-tool KPI cards, a combined Creusot|Kani scorecard over the public-method bundles, property-bundle and spec-vs-each-tool tables, unproved-causes, measurement, anti-vacuity, and provenance. Consumes the Role-1 property set + Role-2 per-tool status blocks that already live in `unified_properties.yaml`; attaches nothing new. Does NOT extract, bundle, or prove — the inventory owns the property set and the bundles, Role 2 owns the status. This is Role 3.

★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

save

Save current session transcript to markdown with per-turn token counts, cost breakdown, and context usage.

★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

refute-tool-boundary

暂无简介

★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

profile-performance-certus-api-bench

Measure system performance of this platform using

后端与接口
★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

profile-kvoffload-replay-all

Run all four KV-offload benchmark variants (NoOffload, CPUOffload, SharedStorage, Certus-SPDK) against the same 12-turn ShareGPT replay and present throughput in one side-by-side table. Use when the user wants to compare offload backends end-to-end.

★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

profile-hardware-ceiling

Measure raw hardware bandwidth ceilings for all data paths (NVMe, GPU, memory, P2P, GDS, GDRCopy) on the current platform

★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

profile-connector-benches

Run certus-connector-bench, cputier-connector-bench, lmcache-connector-bench and 3fs-connector-bench with identical workload parameters, then write an HTML report comparing the KV-offload backends side by side (throughput, IOPS, per-phase latency, parameter parity).

前端开发
★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

profile-compare-with

Compare performance of the current branch against another branch (default unstable)

★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

extract-verifiable-properties

Extract verifiable correctness properties from ONE component artifact — a spec, the source code, or a verification harness/verif — at a fixed, comparable granularity, with coverage by construction.

★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

design-artifacts-update

Update or create design artifacts for a certus-server-yaml profile

设计师视觉设计
★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

component-verify

One-command, repeatable formal-verification pipeline for a single Certus component — new or already-verified. Pulls a fresh tree off origin/unstable, extracts the tool-independent property inventory (Role 1), proves it with Creusot AND Kani (Role 2), renders one combined scoring HTML (Role 3), then commits to two per-component verif branches (overwrite-in-place, component-folder-only gate) — each branch carrying the FULL metadata bundle (spec_properties + code_properties + unified_properties YAML AND the combined scoring HTML) plus that one tool's proof artifacts (Kani harnesses / Creusot verif crate). No PR and nothing to unstable; the two verif branches are the only homes. Use this as the top-level entry point so Cornel, Daniel, or a colleague can verify a component independently and reproducibly.

★ 3
AI-native-Systems-Research
AI-native-Systems-Research/ai-native-storage-certus

component-update-docs

Ensure the per-component README.md are up to date and correctly reflect the code.

★ 3