Explore skills
Showing 47611–47640 of 77104 skills
Default silent entry for questions, research, artifacts, code, coordination and persistent projects. When available to the host, infer the relevant evidence path from each direct request, including real-world, pre-build engineering, or linked hybrid research; choose proportionate Light-to-Ultra workflow depth and load only relevant guidance. Keep the host-selected default model unless the user or host explicitly changes it. The direct user phrase “调用我的 workflow skills” explicitly selects this workflow.
zy839971925-zyy/Agent--deep-research-Workflow-Skills
Stars: 10Claude CodeCodexUse when a material result needs contract verification, independent or orthogonal review, evaluator-validity checks, effectiveness review, or defensible closure.
zy839971925-zyy/Agent--deep-research-Workflow-Skills
Stars: 10Claude CodeCodexUse when the deliverable is a choice, recommendation, prioritization, trade-off, resource allocation, or robustness-sensitive decision.
zy839971925-zyy/Agent--deep-research-Workflow-Skills
Stars: 10Claude CodeCodexUse when a scenario calls for real-world evidence, pre-build engineering/architecture research, or a linked hybrid; infer the route without requiring the user to label it. Keep the host-selected default model; infer proportionate workflow depth, honoring explicit depth requests such as Ultra.
zy839971925-zyy/Agent--deep-research-Workflow-Skills
Stars: 10Claude CodeCodexUse when work creates durable artifacts or external side effects, delegates execution, needs authorization, or must preserve state/checkpoint/recovery semantics.
zy839971925-zyy/Agent--deep-research-Workflow-Skills
Stars: 10Claude CodeCodexUse when a task needs problem framing, representation choice, decomposition, relationships, causal chains, hypotheses, or careful interpretation.
zy839971925-zyy/Agent--deep-research-Workflow-Skills
Stars: 10Claude CodeCodex钉钉 AI 表格(多维表格)操作。当用户提到"钉钉AI表格"、"AI表格"、"多维表格"、"工作表"、"字段"、"记录"、"新增记录"、"查询记录"、"更新记录"、"删除记录"、"新建字段"、"删除字段"、"dingtalk AI table"、"dingtalk notable"、"able文件"时使用此技能。支持工作表管理、字段管理、记录的增删改查等全部操作。
breath57/dingtalk-skills
Stars: 102Claude CodeCodex网页搜索与实时信息检索。需要查找最新资讯、实时数据、技术文档、热点事件,或用户说"搜一下"、"帮我查"、"查资料"、"web search"等时使用。基于小宿AI智能搜索,支持关键词搜索、时间范围过滤(一天/一周/一月/一年)、自定义结果数量、JSON 输出。
breath57/dingtalk-skills
Stars: 102Claude CodeCodex钉钉日程与日历。当用户提到"钉钉日程"、"日历"、"创建日程"、"新建会议"、"视频会议"、"钉钉会议"、"会议室"、"约会议室"、"会议室忙闲"、"空闲会议室"、"签到"、"签退"、"签到链接"、"签退链接"、"循环日程"、"重复日程"、"recurrence"、"查日程"、"日程列表"、"修改日程"、"删除日程"、"闲忙"、"忙闲"、"querySchedule"、"calendar"、"dingtalk schedule"、"日程提醒"时使用此技能。支持:主日历下日程 CRUD、用户闲忙、视频会议、会议室忙闲与绑定日程、签到/签退与链接、循环规则(recurrence);订阅公共日历等需 Calendar.Calendar.Write 的能力见 api.md。
breath57/dingtalk-skills
Stars: 102Claude CodeCodex钉钉通讯录与联系人查询。当用户提到"钉钉通讯录"、"查找员工"、"搜索用户"、"查用户信息"、"获取用户详情"、"用户手机号"、"员工姓名"、"员工工号"、"查部门"、"搜索部门"、"部门成员"、"部门列表"、"部门详情"、"子部门"、"父部门"、"部门路径"、"员工总数"、"通讯录搜索"、"userId 转 unionId"、"unionId 转 userId"、"dingtalk contact"、"dingtalk directory"、"find user"、"get user info"、"department members"时使用此技能。支持:按关键词搜索用户/部门、获取用户完整信息(姓名/手机/工号/部门/职位/unionId)、获取部门成员列表、获取部门树结构、查询用户所在部门路径、员工总人数统计等全部通讯录操作。
breath57/dingtalk-skills
Stars: 102Claude CodeCodex钉钉知识库和文档管理操作。当用户提到"钉钉文档"、"知识库"、"新建文档"、"查看文档目录"、"读取文档内容"、"写入文档"、"更新文档"、"文档成员"、"dingtalk doc"、"knowledge base"时使用此技能。支持:创建知识库、查询知识库列表、新建文档/文件夹、读取/写入文档正文内容、管理成员权限等全部文档类操作。
breath57/dingtalk-skills
Stars: 102Claude CodeCodex钉钉知识库搜索与读取。用于在钉钉沉淀知识里快速查资料、理解项目背景、梳理团队/部门信息、回答制度问题、整理新人入门材料、读取文档正文、导出 Markdown、下载文件,并可带图片和 diagram。
breath57/dingtalk-skills
Stars: 102Claude CodeCodex钉钉消息发送。当用户提到"钉钉消息"、"发消息"、"发通知"、"群通知"、"群消息"、"Webhook"、"机器人消息"、"机器人发消息"、"工作通知"、"单聊消息"、"群聊消息"、"撤回消息"、"消息已读"、"发送Markdown"、"发卡片消息"、"ActionCard"、"@某人"、"@员工"、"at某人"、"提醒某人"、"dingtalk message"、"send message"、"robot message"、"work notification"时使用此技能。支持:群自定义 Webhook 机器人(文本/Markdown/ActionCard/Link/FeedCard + 加签 + @某人)、企业内部应用机器人单聊和群聊发送、消息撤回、已读查询、工作通知等全部消息类操作。
breath57/dingtalk-skills
Stars: 102Claude CodeCodex创建新的钉钉技能(dingtalk skill)。当用户提到"创建新技能"、"新建技能"、"开发钉钉技能"、"新增钉钉功能"、"添加钉钉接口支持"、"我需要一个钉钉 xxx 技能"、"钉钉待办"、"钉钉签到"、"钉钉考勤"、"钉钉审批"、"钉钉日程"等希望将某个钉钉 API 领域封装成可复用 skill 时,必须使用此技能。此技能包含完整的技能创建流程:SDK 探索 → SDK Python 测试 → 纯 HTTP Python 测试(两步全通过)→ SKILL.md 编写。测试未全部通过不得创建 skill。
breath57/dingtalk-skills
Stars: 102Claude CodeCodex钉钉待办管理。当用户提到"钉钉待办"、"待办任务"、"创建待办"、"新增待办"、"查看待办"、"完成待办"、"标记完成"、"删除待办"、"待办列表"、"我的待办"、"设置截止时间"、"指派待办"、"dingtalk todo"、"todo task"、"task management"时使用此技能。支持:创建待办(含描述/截止时间/优先级/参与者)、获取详情、查询列表(按完成状态过滤)、更新待办、标记完成、删除待办等全部待办类操作。
breath57/dingtalk-skills
Stars: 102Claude CodeCodexCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
breath57/dingtalk-skills
Stars: 102Claude CodeCodexBuild PX4 firmware or SITL natively on a Linux host, in the current checkout, without flashing hardware.
naorwaiss/PX4-Autopilot-private
Stars: 0Claude CodeCodexBuild PX4 board firmware on macOS in the px4-dev Docker container, including git worktrees, and stage commit-labeled artifacts without flashing hardware.
naorwaiss/PX4-Autopilot-private
Stars: 0Claude CodeCodexRebase a branch onto main, handling squash-merged parent branches cleanly
naorwaiss/PX4-Autopilot-private
Stars: 0Claude CodeCodexDesign and scaffold multi-agent squads/swarms using the graph orchestration pattern (nodes = agents, edges = dependencies/data flow). USE FOR: designing a coordination topology for a multi-agent squad (sequential pipeline, parallel fan-out/aggregation, branching, feedback loop, cyclic); building an orchestrator agent that delegates to specialist agents; setting up an adversarial/tribunal code or document review with independent reviewers; scaffolding a squad's agent files for a target coding-agent harness (e.g. Copilot CLI or Claude Code custom agents). DO NOT USE FOR: authoring a single agent's frontmatter/prompt body (use copilot-cli-custom-agents, claude-code-custom-agents, or the target harness's own skill); SKILL.md authoring (use create-skill); ad-hoc multi-agent chat with no explicit topology.
NetFabric/intelligentium
Stars: 2Claude CodeCodexFind, inspect, query, redact, and troubleshoot logs, transcripts, sessions, and OpenTelemetry data from coding-agent harnesses on Windows, macOS, Linux, and WSL. USE FOR: GitHub Copilot in VS Code; Copilot CLI; Claude Code; OpenAI Codex; Gemini CLI; OpenCode; Cursor, Windsurf, Kiro, or other VS Code-family editors; locating log files; diagnosing tool or model failures; correlating turns, subagents, and tool calls; querying JSONL, plaintext, or SQLite without spending model tokens; preparing sanitized diagnostics. DO NOT USE FOR: application logs unrelated to coding agents; uploading raw logs; treating unstable transcript schemas as public APIs.
NetFabric/intelligentium
Stars: 2Claude CodeCodexALWAYS use when writing or reviewing agent-facing Markdown, including project instructions, skills and references, and custom-agent definitions. Covers only their shared content style: compact executable instructions, scannable information, active language, factual precision, and token efficiency. DO NOT USE FOR: artifact-specific structure, routing descriptions, metadata schemas, or prompt-body requirements; general Markdown documents; Markdown syntax or rendering rules.
NetFabric/intelligentium
Stars: 2Claude CodeCodexChoose and tune which AI model a custom agent, subagent, or squad node should use. USE FOR: picking a model by task capability tier (general-purpose coding/writing, fast/cheap, deep reasoning/debugging, multimodal); efficiency-first vs. capability-first starting strategies; tuning an effort/reasoning-effort parameter instead of switching models; call cadence vs. provider prompt-cache TTL; cost-tier ranking and cost ceilings; cross-provider or cross-model-family diversity for independent/adversarial review; per-harness model field syntax and resolution order (GitHub Copilot CLI, Claude Code, VS Code custom agents); extending this framework to a new harness. DO NOT USE FOR: authoring the rest of an agent's frontmatter or prompt body (use copilot-cli-custom-agents, claude-code-custom-agents, or the target harness's own skill); designing squad topology (use agent-graph-orchestration); SKILL.md authoring (use create-skill).
NetFabric/intelligentium
Stars: 2Claude CodeCodexProduce, consume, validate, and navigate Open Knowledge Format (OKF) bundles. Use when: creating an OKF knowledge bundle; converting catalogs, wikis, schemas, metrics, runbooks, or APIs to OKF; parsing or indexing OKF; designing an OKF producer or consumer; validating OKF v0.2 conformance; traversing index.md files and concept links; minimizing agent context while reading OKF documentation; handling provenance, trust, lifecycle, sources, or Attested Computation concepts. DO NOT USE FOR: OpenAPI schemas; generic Markdown documentation with no OKF bundle; knowledge graphs that do not use OKF files; runtime packaging or serving protocols not defined by OKF.
NetFabric/intelligentium
Stars: 2Claude CodeCodexCreate polished Python terminal user interfaces and skill scripts with Textual and Rich. Use when: building TUI apps; adding interactive terminal workflows; designing tabs, progress bars, checkboxes, radio buttons, tables, charts, forms, status views, keyboard navigation, color, or responsive terminal layouts; making Python scripts visually appealing and informative. Every skill script defaults to a TUI on an interactive terminal and provides --no-tui for deterministic stream output. DO NOT USE FOR: browser GUIs; desktop-native GUIs; plain shell commands with no interactive workflow; non-Python applications.
NetFabric/intelligentium
Stars: 2Claude CodeCodexOpen specification (ARD v0.9) for publishing, discovering, and verifying AI capabilities (MCP servers, A2A agents, skills, APIs) across federated networks. USE FOR: creating ai-catalog.json manifests; catalog entry schema; URN identifier format (urn:air:<publisher>:<namespace>:<name>); hosting at /.well-known/ai-catalog.json; DNS discovery (TXT/SRV records); Agentmap robots.txt directive; POST /search API; POST /explore API; GET /agents list API; federation modes (auto, referrals, none); trustManifest with SPIFFE/DID/attestations; representativeQueries for semantic search; building ARD registry clients; querying discovery services at runtime. DO NOT USE FOR: implementing MCP server tools (use MCP docs); implementing A2A agent cards (use A2A spec); OAuth/OIDC authentication.
NetFabric/intelligentium
Stars: 2Claude CodeCodexManage APM packages as a consumer: install, update, remove agent context (skills, prompts, agents, instructions, MCP/LSP servers). Use when: apm init; apm install packages; apm update / outdated; apm uninstall / prune; private or org packages; local bundles; authentication (GITHUB_APM_PAT); apm run scripts; apm audit; drift detection; governance ramp; apm doctor; troubleshooting install failures; managing apm.yml dependencies; lockfile (apm.lock.yaml) semantics; MCP server wiring; LSP server config. Covers: targets (copilot, claude, cursor, codex, gemini, windsurf, kiro), harness auto-detection, what to commit. DO NOT USE FOR: authoring or publishing packages (use apm-producer); writing apm-policy.yml.
NetFabric/intelligentium
Stars: 2Claude CodeCodexDesign, implement, migrate, debug, review, and test ReactiveUI 24+ applications. USE FOR: ReactiveObject; WhenAnyValue; ObservableAsPropertyHelper/ToProperty; ReactiveCommand; WhenActivated; Bind/OneWayBind/BindCommand; Interaction; routing and view location; RxAppBuilder; source generators; ReactiveUI.Primitives vs *.Reactive distributions; schedulers; DynamicData; validation; WPF, Avalonia, MAUI, WinUI, WinForms, Blazor. DO NOT USE FOR: generic Rx.NET pipelines without MVVM (use dotnet-rx); unrelated MVVM frameworks; visual UI design.
NetFabric/intelligentium
Stars: 2Claude CodeCodexModern .NET and C# best practices for code quality, performance, and correctness. USE FOR: choosing struct/class/record/readonly-record-struct; nullable reference types; pattern matching; primary constructors; collection expressions; required members; init-only properties; file-scoped namespaces; global usings; async/await patterns; ConfigureAwait; ValueTask vs Task; CancellationToken propagation; IAsyncEnumerable; Span<T>/Memory<T> usage; avoiding boxing; readonly struct; ArrayPool<T>; FrozenDictionary/FrozenSet; LINQ vs loops in hot paths; ArgumentNullException.ThrowIfNull; ThrowIfNegative; ThrowIfZero; IReadOnlyList return types; error handling patterns; GeneratedRegex; LoggerMessage; source generators for regex and logging; avoiding Math/MathF in favor of static methods on the numeric type. DO NOT USE FOR: generic math interfaces (use dotnet-generic-math); ASP.NET Core middleware; EF Core modeling.
NetFabric/intelligentium
Stars: 2Claude CodeCodexBuild, run, and publish .NET applications from a single C# file without a .csproj, using .NET 10 SDK file-based apps. USE FOR: dotnet run file.cs; dotnet run --file; shebang/shell-executable C# scripts; colon-prefixed directives (sdk, package, project, property, include); converting a file-based app to a project with dotnet project convert; publishing file-based apps with native AOT; packaging a file-based app as a .NET tool (PackAsTool); user secrets for file-based apps; flat *.run.json launch profiles; dotnet build/clean/publish/pack/restore on a .cs file; build caching behavior and dotnet clean file-based-apps; folder layout to avoid project-file cone conflicts. DO NOT USE FOR: traditional .csproj solution scaffolding (use dotnet-solution-setup); C# language idioms unrelated to the SDK/CLI (use csharp-best-practices); benchmarking (use dotnet-benchmarking).
NetFabric/intelligentium
Stars: 2Claude CodeCodex