智能体

Agent 规划、多步流程与编排

显示 625-648 / 共 4793 个技能
pedronauck

agent-browser

pedronauck

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

智能体 594 5个月前
chujianyun

qoder-wiki

chujianyun

Qoder 官方文档知识库,包含产品介绍、用户指南、功能配置、扩展能力、账户定价和故障排查。当用户询问 Qoder 相关问题(如安装、使用、功能、定价、快捷键、MCP、Skills、Quest Mode、Repo Wiki 等)时使用此 skill。

智能体 731 7个月前
hhszzzz

divination

hhszzzz

Structured fortune-telling workflow skill using MCP tools. Use when users ask for divination, 八字/四柱, 六爻, 紫微斗数, 塔罗, 大运, 运势/流年, or want standardized解读流程 (e.g., 八字先看身强弱与喜用神再看大运流年). Enforce fixed analysis order, call the right MCP tool, and produce actionable interpretations.

智能体 492 6个月前
feiskyer

autonomous-skill

feiskyer

'Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Claude Code headless mode with auto-continuation. Trigger phrases: "autonomous", "long-running task", "multi-session", "自主执行", "长时任务", "autonomous skill".'

智能体 1638 7个月前
StacDev

stac-quickstart

StacDev

Help initialize and validate a Stac-enabled Flutter project and ship a first server-driven screen. Use when users ask to set up Stac CLI, run stac init/build/deploy, verify project prerequisites, or troubleshoot first-run setup and missing configuration files.

智能体 916 7个月前
dmmulroy

overseer

dmmulroy

Manage tasks via Overseer codemode MCP. Use when tracking multi-session work, breaking down implementation, or persisting context for handoffs.

智能体 245 7个月前
boshu2

swarm

boshu2

'Spawn isolated agents for parallel task execution. Local mode auto-selects runtime-native teams (Claude Native Teams in Claude sessions, Codex sub-agents in Codex sessions). Distributed mode uses tmux + Agent Mail (process isolation, persistence). Triggers: "swarm", "spawn agents", "parallel work", "run in parallel", "parallel execution".'

智能体 430 6个月前
boshu2

recover

boshu2

'Post-compaction context recovery. Detects in-progress RPI and evolve sessions, loads knowledge, shows recent work and pending tasks. Triggers: "recover", "lost context", "where was I", "what was I working on".'

智能体 430 6个月前
boshu2

learn

boshu2

'Capture knowledge manually into the flywheel. Save a decision, pattern, lesson, or constraint for future sessions. Triggers: "learn", "remember this", "save this insight", "I learned something", "note this pattern".'

智能体 430 6个月前
boshu2

implement

boshu2

'Execute a single issue with full lifecycle. Triggers: "implement", "work on task", "build this", "start feature", "pick up next issue", "work on issue".'

智能体 430 6个月前
boshu2

ratchet

boshu2

'Brownian Ratchet progress gates for RPI workflow. Check, record, verify. Triggers: "check gate", "verify progress", "ratchet status".'

学术 430 6个月前
boshu2

handoff

boshu2

'Create structured handoff for session continuation. Triggers: handoff, pause, save context, end session, pick up later, continue later.'

智能体 430 6个月前
boshu2

quickstart

boshu2

'Interactive onboarding for new users. Guided RPI cycle on your actual codebase in under 10 minutes. Triggers: "quickstart", "get started", "onboarding", "how do I start".'

智能体 430 6个月前
boshu2

provenance

boshu2

'Trace knowledge artifact lineage and sources. Find orphans, stale citations. Triggers: "where did this come from", "trace this learning", "knowledge lineage".'

智能体 430 6个月前
boshu2

complexity

boshu2

'Analyze code complexity and find refactor targets using radon/gocyclo. Triggers: "complexity", "analyze complexity", "find complex code", "refactor targets", "cyclomatic complexity", "code metrics".'

智能体 430 6个月前
boshu2

council

boshu2

'Multi-model consensus council. Spawns parallel judges with configurable perspectives. Modes: validate, brainstorm, research. Triggers: "council", "get consensus", "multi-model review", "multi-perspective review", "council validate", "council brainstorm", "council research".'

学术 430 6个月前
boshu2

inbox

boshu2

'Agent Mail inbox monitoring. Check pending messages, HELP_REQUESTs, and recent completions. Triggers: "inbox", "check mail", "any messages", "show inbox", "pending messages", "who needs help".'

智能体 430 6个月前
boshu2

product

boshu2

'Interactive PRODUCT.md generation. Interviews you about mission, personas, value props, and competitive landscape, then generates a filled-in PRODUCT.md. Triggers: "product", "create product doc", "product definition", "who is this for".'

智能体 430 6个月前
boshu2

doc

boshu2

'This skill should be used when the user asks to "generate documentation", "validate docs", "check doc coverage", "find missing docs", "create code-map", "sync documentation", "update docs", or needs guidance on documentation generation and validation for any repository type. Triggers: doc, documentation, code-map, doc coverage, validate docs.'

智能体 430 6个月前
boshu2

codex-team

boshu2

'Use when you have 2+ tasks that Codex agents should execute. Runtime-native: Codex sub-agents when available, Codex CLI fallback otherwise. Handles file conflicts via merge/wave strategies. Triggers: "codex team", "spawn codex", "codex agents", "use codex for", "codex fix".'

智能体 430 6个月前
boshu2

shared

boshu2

Shared reference documents for distributed mode skills (not directly invocable)

智能体 430 6个月前
boshu2

status

boshu2

'Single-screen dashboard showing current work, recent validations, flywheel health, and suggested next action. Triggers: "status", "dashboard", "what am I working on", "where was I".'

智能体 430 6个月前
boshu2

retro

boshu2

'Extract learnings from completed work. Trigger phrases: "run a retrospective", "extract learnings", "what did we learn", "lessons learned", "capture lessons", "create a retro".'

智能体 430 6个月前
boshu2

research

boshu2

'Deep codebase exploration. Triggers: research, explore, investigate, understand, deep dive, current state.'

学术 430 6个月前