智能体

Agent 规划、多步流程与编排

显示 1753-1776 / 共 5671 个技能
scitix

deep-investigation

scitix

Structured hypothesis-driven investigation for complex infrastructure issues. Triggered by /dp command or [Deep Investigation] UI toggle.

智能体 238 7个月前
wshuyi

deep-research

wshuyi

深度调研方法论(8步法):将模糊主题转化为高质量调研报告。 触发词:/deep-research、深度调研、帮我调研、调研一下、对比分析 注意:如果用户需要的是可视化图谱而非报告,请使用 research-to-diagram skill。

学术 355 8个月前
neurofoo

wardley

neurofoo

Wardley Mapping strategic analysis—map value chains against evolution to reveal build vs buy decisions and competitive dynamics. Use for technology strategy or investment decisions.

智能体 122 9个月前
franalgaba

grimoire-uniswap

franalgaba

Retrieves Uniswap router metadata using the Grimoire venue CLI. Use when you need router addresses, adapter information, or Uniswap V3/V4 details.

智能体 6 8个月前
valkryhx

agent_team

valkryhx

Enables the agent to act as a Swarm Leader, dispatching tasks to remote workers, managing sessions, and handling concurrency.

智能体 6 8个月前
block

rp-why

block

Gas Town × DOK Framework - A two-dimensional model for analyzing AI collaboration maturity and cognitive complexity to reveal growth opportunities.

智能体 25 8个月前
itsmostafa

context-engineering

itsmostafa

Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended interactions.

智能体 24 9个月前
itsmostafa

agents

itsmostafa

Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or orchestration of LLM-driven tasks.

智能体 24 9个月前
DeevsDeevs

chain-system

DeevsDeevs

"Create, list, and load multi-session chain links that capture work context for later continuation. Use when you want to save current progress, resume a project from a prior session, or inspect chain history. Triggers: chain link, chain load, chain list, save context, resume work, continue later, session handoff."

智能体 41 8个月前
andrelandgraf

ai-agent-workflow

andrelandgraf

Build resumable multi-agent workflows with durable execution, tool loops, and automatic stream recovery on client reconnection.

智能体 22 9个月前
fmschulz

bio-workflow-methods-docwriter

fmschulz

Generate reproducible Methods documentation from workflow run artifacts (Nextflow/Snakemake/CWL), including exact commands, versions, parameters, QC gates, and outputs.

智能体 11 8个月前
fmschulz

agent-browser

fmschulz

Browser automation via agent-browser CLI for web navigation, form filling, screenshots, scraping, login flows, and UI testing.

智能体 11 8个月前
Mitscherlich

commit-push

Mitscherlich

当用户要求"提交代码"、"commit"、"推送代码"、"push"、"提交并推送"、"提交变更"、"推送到远程"、"帮我提交一下"、"把代码推上去"时,应使用此技能。此技能提供规范化的 git 提交与推送工作流,自动分析变更内容、生成符合规范的提交信息并执行相应操作。

智能体 3 8个月前
SpillwaveSolutions

documentation-specialist

SpillwaveSolutions

This skill should be used when creating professional software documentation (SRS, PRD, OpenAPI, user manuals, tutorials, runbooks) from templates (greenfield) or reverse-engineering documentation from existing code like Spring Boot or FastAPI (brownfield). Also handles documentation audits/reviews, format conversion (Markdown, DOCX, PDF), and diagram generation (C4, Mermaid, PlantUML, ER, sequence). Use when asked to "create documentation", "document my code", "write SRS", "generate PRD", or "documentation specialist".

智能体 50 10个月前
keep-starknet-strange

huginn-onboard

keep-starknet-strange

Bridge to Starknet from any EVM chain and register with Huginn agent registry. Enables cross-chain agent onboarding with AVNU bridge integration.

智能体 81 7个月前
keep-starknet-strange

starknet-network-facts

keep-starknet-strange

Starknet network-level constraints and protocol facts that impact contract safety and agent reasoning.

智能体 81 7个月前
edmundmiller

autonomous-agent-loop

edmundmiller

Use when a task is broad, multi-step, cross-session, or the user says agents need too many re-prompts/kicks, asks to use createGoal/goals, says continue/keep going, or wants rough Pi/agent sessions improved. Keeps work moving from objective to evidence-backed completion.

智能体 80 2个月前
edmundmiller

dotfiles-agent-workflow

edmundmiller

Use this skill to apply the canonical risk-gated dotfiles workflow when work is broad, autonomous, high-risk, or multi-session; when the user tags AGENT_WORKFLOW.md; or when repeated agent friction needs durable guidance.

智能体 80 3个月前
edmundmiller

oracle

edmundmiller

Use Oracle to bundle prompts + files for another AI (GPT 5 Pro, etc.) when stuck, debugging, or reviewing. Also covers self-improvement — codifying learnings into agent memory and noting tool improvement ideas.

智能体 80 7个月前
edmundmiller

agent-ci

edmundmiller

Run GitHub Actions CI locally with Agent CI only when explicitly requested.

智能体 80 2个月前
SpillwaveSolutions

web-browser-automation

SpillwaveSolutions

Comprehensive macOS browser automation using PyXA, Playwright, Selenium, and Puppeteer for desktop web testing, scraping, and workflow automation. Use when asked to "automate web browsers", "Selenium Chrome automation", "Playwright testing", "Puppeteer scraping", or "cross-browser automation". Supports Chrome, Edge, Brave, Arc browsers.

智能体 46 9个月前
edmundmiller

nix-darwin-reference

edmundmiller

This skill should be used when editing nix-darwin or Darwin-specific Nix configuration in this dotfiles repo, troubleshooting darwin-rebuild failures, looking up macOS module options, bootstrapping a Mac with Lix/Nix, or using legacy nix-build during nix-darwin work.

智能体 80 3个月前
edmundmiller

amoxide-project-aliases

edmundmiller

Use amoxide for project-local .aliases and optional profiles when commands are simple, trusted, and useful to agents without shadowing zsh aliases.

智能体 80 5个月前
edmundmiller

omp-model-config

edmundmiller

Configure OMP model roles, providers, fallback chains, and per-host overrides in this nix-darwin dotfiles repo. Use when changing which models OMP uses, shifting providers, fixing fallback chains, or troubleshooting why a model change didn't take effect after rebuild.

智能体 80 2个月前