“capa”的搜索结果

Plan a sprint by refining backlog items, defining a sprint goal, calculating team capacity, selecting items, and decomposing them into tasks. Produces a SPRINT-PLAN.md with goal, selected items, task breakdown, and capacity allocation. Use when starting a new sprint in a Scrum or agile project, re-planning after significant scope change, transitioning from ad-hoc work to structured sprint cadence, or after backlog grooming when items are ready for inclusion.

中文简介正在准备中。当前显示原文说明。

Forecast infrastructure and application metrics using Prophet or statsmodels for capacity planning, cost optimization, and proactive scaling. Visualize predictions in Grafana and set up alerts for projected resource exhaustion. Use when forecasting infrastructure capacity needs for CPU, memory, or disk, planning hardware procurement for next quarter, predicting cost trends to optimize cloud spending, or setting up proactive scaling policies based on predicted load.

中文简介正在准备中。当前显示原文说明。

Design an A2A Agent Card (.well-known/agent.json) manifest describing agent capabilities, skills, authentication requirements, and supported content types. Use when building an agent that must be discoverable by other A2A-compliant agents, exposing capabilities for multi-agent orchestration, migrating an existing agent to the A2A protocol, defining the public contract for an agent before implementation, or integrating with agent registries that consume Agent Cards.

中文简介正在准备中。当前显示原文说明。

Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydantic_ai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents from YAML, or test agent behavior.

中文简介正在准备中。当前显示原文说明。

Assesses agent capabilities by analyzing agent files and determining what tasks they can handle. Use when you need to evaluate if an existing agent can handle a task or if a new agent is needed. Reviews agent descriptions, skills, and workflows to determine capability match.

中文简介正在准备中。当前显示原文说明。

"Apply the Dynamic Capabilities framework (Teece et al., 1997) — sensing, seizing, and transforming — to analyze how firms adapt, integrate, and reconfigure competences in rapidly changing environments. Use this skill when the user needs to explain why some firms sustain advantage while others decline, evaluate organizational agility, distinguish operational from strategic capabilities, or when they ask 'how do we stay competitive as the market shifts', 'why did this firm fail to adapt', or 'what capabilities do we need to build'.".

中文简介正在准备中。当前显示原文说明。

"Calculate Cpk process capability index to assess whether a process meets specification requirements. Use this skill when the user needs to evaluate process capability, compare processes, or determine if quality targets are achievable — even if they say 'can our process meet spec', 'process capability', or 'Cpk calculation'.".

中文简介正在准备中。当前显示原文说明。

Analyzes a PE file's import and export tables to infer capability: mapping imported APIs to behaviors (networking, crypto, injection, persistence), spotting dynamic-resolution stubs, and reading exports of malicious DLLs. Activates for requests to analyze PE imports, inspect the IAT/exports, or infer capability from API usage.

中文简介正在准备中。当前显示原文说明。

Analyzes remote access trojan command-and-control by mapping the RAT command set, identifying the C2 transport and beacon parameters, and cataloging operator capabilities from static strings and config. Activates for requests to analyze RAT C2, map a trojan command handler, or identify remote-access capabilities and C2 transport.

中文简介正在准备中。当前显示原文说明。

Research one agent harness's release (docs, source, runtime) and fill its capability cells in scripts/harness_capabilities.py with cited evidence. Use after a harness version bump, when just harness-probe reports re-research, or when capability cells read unknown.

中文简介正在准备中。当前显示原文说明。

Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability to an existing Convex app.

中文简介正在准备中。当前显示原文说明。

Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability to an existing Convex app.

中文简介正在准备中。当前显示原文说明。

Designs, reconciles, and reviews an end-to-end Drydock program for safely staging agent runtimes: immutable worktree provenance, disposable VM containment, typed effect brokerage, global body accounting, resurrection, subscription-capacity economics, context compaction, operator control, evidence, and promotion. Use when several Drydock contracts must compose into one architecture, implementation hypertree, diagram set, or release plan. NOT for launching Port Daddy, running an untrusted subject, replacing focused containment/resurrection/capacity audits, or treating a design packet as runtime authority.

中文简介正在准备中。当前显示原文说明。

Ranks eligible skill candidates with explicit retrieval evidence, capability coverage, and uncertainty. NOT for discovery, authorization, or execution planning.

中文简介正在准备中。当前显示原文说明。

Design discovery, directories, and guilds for agent swarms at scale. Use when agents need to find each other on a shared surface: capability indices, yellow-pages directories, whois/phonebook routing, reputation-aware discovery, and guild structures that scope trust. Covers the canonical prior art (FIPA Directory Facilitator, Contract Net, Chord/DHT, DNS-SD/Consul, EigenTrust, Greif's merchant guilds) and the failure modes (read-poverty, Sybil reset, Goodhart on rank, directory staleness, cold-start). Triggers: "agents can't find each other", "who owns this file/skill", "route a question to the right agent", "capability registry", "agent reputation", "guild / federation of fleets". NOT for issuing identities, granting authority, or automatically assigning work from a directory entry.

中文简介正在准备中。当前显示原文说明。

Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability to an existing Convex app.

中文简介正在准备中。当前显示原文说明。

调查OpenClaw CI的排队和运行环境不足问题，根据测量结果调整运行器注册预算、并行数量、测试分组、运行器规格及任务分配位置。

• 调查OpenClaw CI排队原因
• 估算高峰期运行器注册数量
• 调整并行数量和测试拆分

读取仓库设置和智能体运行环境，盘点已连接工具与可用功能，区分缺少工作流程和缺少外部集成的情况，并按优先级提出三至五项ECC后续建议。

• 检查Claude Code设置
• 盘点已连接工具及其功能
• 判断是否需要添加插件

将产品需求和规划文档整理为可供开发使用的具体要求，明确业务规则、数据归属、服务间接口及待定事项，形成可交接的资料。

• 将产品需求文档转为开发要求
• 梳理跨服务功能的需求
• 记录评审中反复确认的前提

将尚未实现的新功能从调研、规划推进到测试先行的开发、审查和提交。各阶段交由对应的ECC智能体负责，并在计划批准和提交前暂停确认。

• 添加产品尚未支持的功能
• 先写测试再实现新功能
• 审查身份验证功能的安全性

查询H100或H200的GPU库存，提交固定费率报价请求并查看报价与采购进度；也支持撤销设备认证，以及在明确授权后验证指定节点。

• 查询H100或H200库存
• 请求固定费率报价
• 查看报价及采购进度

在AI开发前定义成功条件，使用代码、规则、模型或人工评估新功能并检查既有功能是否正常，再记录多次尝试的可靠性指标与报告，用于比较提示词、代理或模型版本的变化。

• 在AI实现前确定成功条件
• 检查提示词或代理变更后的回归问题
• 通过多次尝试衡量可靠性

将模糊想法整理为明确目标、工作范围和验收条件的规格文档，梳理多个功能的划分与依赖，并经人工审批逐步进入规划、任务拆分和实现。

• 在实现前明确想法
• 编写包含验收条件的需求文档
• 将大型需求拆分为独立功能

为现有OD Next计划准备所需图片等素材，复用已确认可用的功能和合适素材，完成获取、尺寸检查及异步结果收集，同时保留内容、许可与质量要求。

• 收集现有计划所需的素材
• 在多个页面复用已有素材
• 检查用于排版的素材尺寸