跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。

全部技能

38,472 Skills

搜索范围为本次公开目录;榜单和数量均为记录时的数据。

搜索与研究

competitive-intel-agent

michaelboeding

Use this skill to analyze competitors, find competitive gaps, and develop competitive strategy. Triggers: "competitor analysis", "competitive analysis", "analyze competitor", "competitive intel", "competitive intelligence", "competitive landscape", "competitor comparison", "beat

价格待确认
效率与协作

copywriter-agent

michaelboeding

Use this skill to create marketing copy, ad copy, product descriptions, and sales content. Triggers: "write copy", "marketing copy", "ad copy", "product description", "sales page", "landing page copy", "email copy", "tagline", "headline", "slogan", "brand copy", "website copy", "

价格待确认
开发与测试

debug-council

michaelboeding

Research-aligned self-consistency for debugging. Spawns independent solver agents that each explore and debug the problem from scratch. Uses majority voting. Based on "Self-Consistency Improves Chain of Thought Reasoning" (Wang et al., 2022). Use for critical bugs, algorithms, or

价格待确认
设计与 UI

feature-council

michaelboeding

Multi-agent feature implementation. Spawns independent solver agents that each implement the feature from scratch, then synthesizes the best elements from each. Use when building complex features where you want diverse approaches and comprehensive edge case coverage.

价格待确认
开发与测试

ios-to-android

michaelboeding

Use iOS/Swift code as the source of truth and implement the equivalent feature in Android/Kotlin. Understands the feature behavior, data structures, and logic from iOS, then creates idiomatic Android code that matches the target codebase's existing patterns. Use when porting feat

价格待确认
其他技能

commit-and-pr

rknightion

Write commit messages, pull request titles and pull request bodies that release-please can version and the acceptance evidence check accepts. Use when committing, drafting or fixing a commit message, choosing a pull request's squash title, or writing or refreshing a pull request

价格待确认
开发与测试

diagnosing-bugs

rknightion

Diagnosis loop for hard bugs and performance regressions. Use when asked to diagnose or debug something, or when something is reported broken, throwing, failing, stuck, wrong or slow. Builds a fast, red-capable feedback loop before any theory, then reproduces, minimises, tests ra

价格待确认
其他技能

find-state-machines

rknightion

Find implicit state machines, where one lifecycle's state, transitions, and ownership are scattered across flags, effects, callbacks, and async work, and make them explicit. Use when auditing lifecycle coordination, async flows, impossible states, or a proposed stateful refactor.

价格待确认
演示文稿

pyramid-presentation

tyroneross

Builds a presentation storyline with slide-by-slide assertion headlines using the pyramid principle. Use when the user wants a deck, slides, ghost deck, or talk structured or outlined. Not for critiquing an existing deck without rewriting it; use `pyramid-audit` instead.

价格待确认
开发与测试

platform-cli

ultralytics

Use when operating Ultralytics Platform from a terminal or script with the ul cloud CLI (ul cloud RESOURCE OPERATION key=value, PyPI package ultralytics-platform) — listing, creating, updating, cloning, or moving projects, datasets, and models; inspecting dataset images, statisti

价格待确认
部署与云服务

yolo

ultralytics

Use for ANY task involving Ultralytics Platform, the ultralytics Python package, yolo CLI, YOLO model weights (.pt), dataset annotation, training, validation, prediction, tracking, export, deployment, or the detect / segment / semantic / depth / classify / pose / OBB vision tasks

价格待确认
其他技能

yolo-datasets

ultralytics

Use when uploading, annotating, building, converting, analyzing, or debugging datasets in Ultralytics Platform or local YOLO — Platform dataset management and Smart Annotation, data.yaml, YOLO label .txt formats, COCO/DOTA/mask conversion, auto-labeling, splits, validation, and e

价格待确认
开发与测试

yolo-export

ultralytics

Use when exporting or deploying Ultralytics YOLO models in Platform or code — the Platform Export tab and yolo export/model.export() for ONNX, TensorRT, CoreML, Core AI, OpenVINO, LiteRT, NCNN, ExecuTorch, and NPUs (RKNN, QNN, Hailo, Ascend, IMX, Axelera, DeepX, Xilinx), FP16/INT

价格待确认
开发与测试

yolo-models

ultralytics

Use when choosing or comparing Ultralytics models in Platform or code — picking a model family (YOLO26/YOLO11/YOLOv8, YOLO-World, YOLOE, SAM/SAM2/FastSAM, RT-DETR, YOLO-NAS), size (n/s/m/l/x), task variant (-seg, -sem, -cls, -pose, -obb, -depth), pretrained checkpoint, open-vocab

价格待确认
开发与测试

yolo-training

ultralytics

Use when training, fine-tuning, or validating Ultralytics YOLO models in Platform, cloud GPUs, or local code — model.train(), yolo train/val, remote metric streaming, epochs, batch, imgsz, devices, augmentation, multi-GPU, resumes, results, and fixing OOM, NaN loss, low mAP, or o

价格待确认
开发与测试

yolo-tuning

ultralytics

Use when improving or comparing Ultralytics YOLO models in Platform or code, or running hyperparameter search/autotraining — Platform experiment comparison, the systematic improvement playbook, model.tune() genetic evolution, Ray Tune, search spaces, and deciding whether tuning i

价格待确认

目录记录日期:2026-11-21