智能体

Agent 规划、多步流程与编排

显示 337-360 / 共 5671 个技能
K-Dense-AI

ginkgo-cloud-lab

K-Dense-AI

Submit and manage protocols on Ginkgo Bioworks Cloud Lab (cloud.ginkgo.bio), a web-based interface for autonomous lab execution on Reconfigurable Automation Carts (RACs). Use when the user wants to run cell-free protein expression (validation or optimization), generate fluorescent pixel art, or interact with Ginkgo Cloud Lab services. Covers protocol selection, input preparation, pricing, and ordering workflows.

智能体 5.4万 7个月前
affaan-m

enterprise-agent-ops

affaan-m

Operate long-lived agent workloads with observability, security boundaries, and lifecycle management.

智能体 28.7万 7个月前
affaan-m

claude-devfleet

affaan-m

Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.

智能体 28.7万 7个月前
affaan-m

agent-sort

affaan-m

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

智能体 28.7万 6个月前
Weizhena

research

Weizhena

对目标话题进行初步调研,生成调研outline。用于学术调研、benchmark调研、技术选型等场景。

学术 2414 6个月前
obra

writing-skills

obra

Use when creating new skills, editing existing skills, or verifying skills work before deployment

智能体 30.4万 8个月前
borghei

senior-prompt-engineer

borghei

Expert prompt engineering for LLM applications including prompt design, optimization, RAG systems, agent architectures, and AI product development.

智能体 973 9个月前
mattpocock

loop-me

mattpocock

Grill me about specs for the workflows I want to build, within this workspace.

智能体 30.2万 2个月前
Donchitos

sprint-plan

Donchitos

"Generates a new sprint plan or updates an existing one based on the current milestone, completed work, and available capacity. Pulls context from production documents and design backlogs."

智能体 2.7万 8个月前
mattpocock

zoom-out

mattpocock

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

智能体 30.2万 5个月前
mattpocock

design-an-interface

mattpocock

Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

智能体 30.2万 5个月前
Donchitos

onboard

Donchitos

"Generates a contextual onboarding document for a new contributor or agent joining the project. Summarizes project state, architecture, conventions, and current priorities relevant to the specified role or area."

智能体 2.7万 8个月前
petekp

agent-native-architecture

petekp

Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.

智能体 48 8个月前
obra

verification-before-completion

obra

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

智能体 30.4万 12个月前
microsoft

owasp-agentic

microsoft

OWASP Agentic Security Top 10 knowledge base for identifying, assessing, and remediating AI agent system security risks.

智能体 1565 4个月前
microsoft

supply-chain-security

microsoft

Software supply chain security reference for OpenSSF Scorecard, SLSA, Sigstore, SBOM, and posture/backlog taxonomies.

智能体 1565 3个月前
microsoft

dt-coaching-foundation

microsoft

"Design Thinking coaching foundation knowledge: coach identity and philosophy, quality and fidelity constraints, method sequencing, coaching state schema, and the canonical deck workflow"

智能体 1565 3个月前
superset-sh

orchestrate

superset-sh

Coordinate several coding agents in parallel through Superset, each in its own workspace, with follow-ups, progress reads, dependency tracking, and structured results. Use when the user asks to delegate, parallelize, fan out, or split up coding work across agents, workspaces, or hosts, hand work between agents, or monitor workers, including "spin up agents for each of these", "run these in parallel", "what are my workers doing". Not for ordinary single-agent workspace, task, or automation management.

智能体 1.6万 10天前
wshobson

workflow-orchestration-patterns

wshobson

Design durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.

智能体 4.2万 9个月前
nirholas

okx-dex-signal

nirholas

"Use this skill for smart-money/whale/KOL/大户 activity tracking, aggregated buy signal/信号 alerts, and leaderboard/牛人榜 rankings. Covers: (1) address tracker — raw DEX transaction feed for smart money, KOL, or custom wallet addresses; (2) aggregated buy-only signal alerts — tokens bought collectively by smart money/KOL/whales; (3) leaderboard — top traders by PnL, win rate, volume, or ROI. Use when the user asks 'what are smart money buying', '聪明钱最新交易', 'KOL交易动态', '追踪聪明钱', 'track address trades', '大户在买什么', 'whale signals', 'smart money alerts', '信号', '大户信号', 'top traders', '牛人榜', or wants to monitor notable wallet activity. Also handles Market API payment/计费/x402/402, Basic/Premium tier/quota/额度 questions, and MARKET_API_*_OVER_QUOTA / confirming:true responses on signal, leaderboard, or tracker endpoints. NOTE: if the user wants to write a WebSocket script/脚本/bot, use okx-dex-ws instead."

智能体 247 3个月前
bitget-wallet-ai-lab

bitget-wallet

bitget-wallet-ai-lab

"Interact with Bitget Wallet API for crypto market data, token info, swap quotes, and security audits. Use when the user asks about token prices, market data, swap/trading quotes, token security checks, K-line charts, or token rankings on supported chains (ETH, SOL, BSC, Base, etc.)."

智能体 253 7个月前
tjboudreaux

thinking-via-negativa

tjboudreaux

Use when the reflex is to add a feature, layer, or process. Prefer removing harmful or nonessential elements first, with an irreversibility guard before deletion.

智能体 1664 3个月前
deanpeters

epic-breakdown-advisor

deanpeters

Break down epics into user stories using Richard Lawrence's Humanizing Work methodology—a flowchart-driven approach that applies 9 splitting patterns sequentially.

智能体 7647 8个月前
deanpeters

finance-based-pricing-advisor

deanpeters

Evaluate pricing changes using financial impact analysis - ARPU/ARPA, conversion, churn risk, NRR, and payback. Recommends go/no-go on pricing decisions.

智能体 7647 8个月前