tencent
- 75 skills
- 0 followers
- last month last updated
- ▌ Browser Skill 3 · tencentUse when the user asks to automate their logged-in Chromium browser: visit and read pages, fill forms, scrape data, click through flows, regression-test a PR's UI, validate a deployed page, or operate a tab they identify. Requires the bsk CLI and browser extension.
- ▌ Tech Design 2 · tencent bundle通用技术方案撰写技能。根据需求输入(需求分析报告或口头描述)自动生成结构完整的技术方案 Markdown 文档。当用户说"帮我写技术方案"、"出一个技术设计文档"、"写一份 design doc"、"给这个需求出方案"时使用本技能。
- ▌ Writing Plans 2 · tencent bundleUse when you have a spec or requirements for a multi-step task, before touching code
- ▌ Knowledge Distillation 3 · tencent通用知识沉淀能力 - 提供从项目交付过程中提炼可复用经验、教训和模式的标准化方法论,包括信息收集、精简提炼、结构化输出。不绑定任何特定工作流或存储方式。当用户说"帮我做知识沉淀"、"总结一下这次需求的经验"、"记录一下踩坑"、"沉淀一下这次的技术决策"、"做个复盘"时使用本技能。
- ▌ Cr 2 · tencent bundleAutomated code review and fix for local branches, PRs, commits, and files. Supports single-agent interactive fix and multi-agent adversarial review with auto-fix.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Knowledge Distillation 2 · tencent通用知识沉淀能力 - 提供从项目交付过程中提炼可复用经验、教训和模式的标准化方法论,包括信息收集、精简提炼、结构化输出。不绑定任何特定工作流或存储方式。当用户说"帮我做知识沉淀"、"总结一下这次需求的经验"、"记录一下踩坑"、"沉淀一下这次的技术决策"、"做个复盘"时使用本技能。
- ▌
- ▌ Tencent Edgeone Skill · tencent bundleA comprehensive skill for Tencent EdgeOne (Edge Security & Acceleration Platform), covering edge acceleration (DNS, certificates, caching, rule engine, L4 proxy, load balancing), edge security (DDoS protection, Web protection, Bot management), edge media (real-time video / image processing), edge development (Edge Functions, EdgeOne Pages), and more. Use this skill whenever a user mentions any EdgeOne / EO-related configuration, operations, querying, or troubleshooting needs.
- ▌ Workrally · tencent bundleWorkRally CLI (workrally) — 面向 AI Agent 的 AIGC 漫剧视频创作全流程工具集。支持 AI 生图、AI 生视频、视频提示词优化、画布生音频/音乐、混元 3D 模型生成、AI 生音频、项目/剧集/场次/分镜的完整 CRUD、资产库、媒资管理、无限画布、文件上传下载等。Use when user asks to generate images, generate videos, generate audio, generate music, generate 3d, optimize video prompts, manage projects, series, shots, upload files, download assets, manage materials, or interact with WorkRally platform via command line.
- ▌ Yolo Master Agent · tencent bundleUse when the user wants to train, validate, predict, track, export, benchmark, tune, inspect, or orchestrate YOLO-Master / Ultralytics experiments in this repository, including LoRA, MoE, multimodal inference/evaluation, and solutions workflows.
- ▌ Pagx · tencent bundleConverts an HTML file/URL or a described visual (poster, card, banner, social post) to a PAGX file, and edits existing PAGX files. Use when the user asks to create a PAGX from a visual description, convert HTML to PAGX, modify/update an existing PAGX, run pagx CLI commands (render, verify, format, layout, bounds, font info/embed, import, resolve, export to SVG/HTML/PPTX, preview in browser, or look up PAGX element attributes and syntax).
- ▌
- ▌ Webapp Testing · tencent bundle使用 Playwright 与本地 Web 应用交互与测试的工具包。支持验证前端功能、调试 UI 行为、捕获浏览器截图以及查看浏览器日志。
- ▌ Tdesign Flutter General · tencentTDesign Flutter 通用协作约定,适用于仓库开发和 PR 工作,涵盖 Spec、更新日志、公开契约、生成产物、双版本及 CI 登记。组件对齐由 Review skill 补充,CNB 平台限制见仓库协作说明。
- ▌ Tdesign Component Align Review · tencentReview TDesign Flutter 组件的公开 Demo、API 收敛、Flutter 设计模式、主题、测试和 Golden 证据。以小程序公开 Demo 作为可见效果参考,但不机械映射其 props/events;适用于组件对齐和 PR Review。
- ▌ Team Wiki Codebase · tencent bundle让 AI 真正理解大型代码库。针对多仓库、多微服务、迭代多年的项目,通过架构逆向 + Graph RAG 图谱 + CLI 多语言 AST, 将海量代码压缩为结构化知识库——每条结论可回溯代码行,每条关系有置信度标注。 适用场景:项目有 10+ 仓库或微服务,AI 直接读代码无法全局理解、回答不准确、token 开销大。 产出:组件设计文档 × N + 架构总览 + 桥梁文档 + Graph RAG 图谱(G1~G9) + _manifest.json + teamai extract graph (teamwiki/)。 Trigger: team-wiki-codebase, code-to-knowledge, 代码知识库, 架构分析, 架构逆向 Prerequisites: 可访问的源码目录(支持多仓库);本 skill 目录下 `references/` 与 `scripts/`
- ▌
- ▌ Browser Skill · tencentUse when the user asks to automate their logged-in Chromium browser: visit and read pages, fill forms, scrape data, click through flows, regression-test a PR's UI, validate a deployed page, or operate a tab they identify. Requires the bsk CLI and browser extension.
- ▌
- ▌ Weknora Shared · tencentUse when driving a WeKnora RAG server through the `weknora` CLI as an agent — authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or interpreting the CLI's JSON envelopes and exit codes. Read this before any other weknora-* skill.
- ▌ Weknora RAG Search · tencent bundleUse when retrieving from or asking questions against a WeKnora knowledge base via the `weknora` CLI — and especially when unsure whether to use `chat`, `session ask`, or `search chunks` for a given goal.
- ▌
- ▌
- ▌
- ▌ Tdesign Pro Component · tencentThis skill should be used when developing or modifying TDesign Pro Components (AIGC/Chat). It provides the ChatEngine architecture, component patterns, AG-UI protocol integration, and Generative UI development guide.
- ▌ Tdesign Test Component · tencentThis skill should be used when writing or maintaining unit tests for TDesign React components. It provides testing patterns, best practices, and SOP for Vitest-based component testing including snapshot tests.
- ▌ Tdesign Component Style · tencentThis skill should be used when developing or modifying styles for TDesign React components. It provides guidance on BEM naming conventions, CSS Variables usage, state classes, and the relationship between component code and common submodule styles.
- ▌ Tdesign Create Component · tencent bundleThis skill should be used when creating a new TDesign React component. It provides a complete SOP for scaffolding components in the packages/components or packages/pro-components directories, including file structure, code patterns, and registration steps.
- ▌ Cr · tencent bundleAutomated code review and fix for local branches, PRs, commits, and files. Supports single-agent interactive fix and multi-agent adversarial review with auto-fix.
- ▌
- ▌
- ▌
- ▌
- ▌ Forgejo · tencent bundleForgejo REST API toolkit — manage issues, pull requests, wikis, and repos on a Forgejo server. Use when the agent needs to file an issue, open / review / merge a PR, read or write a wiki page, or look up repo / branch info. One standalone script per resource type. Reads credentials from environment, `~/.skillhone/settings.json`, or `_data/forgejo_config.txt`.
- ▌ Skillhone · tencent bundleSkillHone — toolkit for evaluating, optimizing, and managing agent skills. Use when asked to "evaluate a skill", "run probe", "optimize/iterate a skill", "create a new skill experiment", "seed a skill repo", or "run skill benchmarks"; also use when the user mentions a Forgejo-hosted skill repo and wants to measure or improve its quality. Wraps standalone scripts: status, eval, optim, new, seed, serve, synth.
- ▌ Skillhone Prd · tencent bundleInteractively gather a PRD (Product Requirements Document) for an agent skill that is about to be built or optimized by SkillHone. Use when the user says things like "I want to write a new skill", "help me spec this skill", "what should <x>-skill do", or before running `skillhone new` / `skillhone optim` on a skill whose requirements aren't fully nailed down. The interview is driven through the `AskUserQuestion` tool — every round is a small set of dependent multi-choice questions, and the skill keeps asking until the user says stop. Final artifacts are three files in the paired `<skill>-eval` repo: `PRD.md` (eval-agent-visible), `PRD.improver_only.md` (improver-agent visible, scoring rubric redacted), and `PRD.choice.md` (the AskUserQuestion transcript). Also mirrors the appropriate pages into Forgejo wiki checkouts when available.
- ▌ Skillhone Synthesis · tencent bundleUse this skill to synthesize closed-form, automatically verifiable benchmark Q/A by exploring a tool environment, building a reusable exploration graph, and mining multiple hard questions from that graph. Use for: building a benchmark, writing eval items, generating evaluation data, closed-form QA, verifiable-answer datasets, synthesising eval data. Applies to any domain with callable tools. Do not use for open-ended writing, subjective scoring, or pure labeling.
- ▌ Skillhone Evaluation · tencent bundleRun and interpret skill evaluations. Use when you need to evaluate a skill, run probe/test/PR-val, check if a PR regresses quality, compare two versions, or diagnose why the score dropped. Handles the full eval lifecycle including solver trajectory diagnosis for tool-level error detection.
- ▌ Skillhone Optimization · tencent bundleOptimize a skill by planning, exploring available tools, diagnosing failures, and implementing fixes via PR. Use this skill as soon as an optimization loop starts, especially on the first iteration when community tools or reference approaches should be explored before implementation.
- ▌ Mas Compiler · tencent bundleCompile a Multi-Agent System (MAS) into a Single-Agent System (SAS) by faithful pipeline compression. Implements the 3-phase compilation from arXiv 2601.04748. Takes a MAS codebase or description as input; produces a compiled SKILL.md with sequential [PHASE] sections and a tools/ directory. Invoke with /mas-compiler.
- ▌ Adaptive Mas Converter · tencentConvert a Multi-Agent System (MAS) into a single-agent skill, adaptively adjusting how much structure to retain based on the target task's evaluation metric. Analyzes task freedom first, then converts accordingly. Invoke with /adaptive_mas_converter.
- ▌ Very Simple Apex · tencent bundleMinimal text2sql skill. Gives you tools and knowledge to generate SQL — no required workflow.
- ▌
- ▌ Adaptive Apex Spider · tencent bundleText-to-SQL for Spider 2.0-Snow (Snowflake cloud databases). Use when you receive a natural-language question plus a Snowflake database schema and need to produce correct, executable Snowflake SQL. Provides SQL execution tools, keyword-based tip selection, and Snowflake-specific domain knowledge.
- ▌ Adaptive Causal Discovery · tencent bundlevery_simple_matmcd: Causal Discovery with Statistical Tools + Domain Knowledge
- ▌ Very Simple Fela · tencentFeature engineering skill for taobao/dia AUC maximization. Provides dataset-specific domain knowledge and code patterns — no forced pipeline.
- ▌ Devflow · tencent bundle在用户明确要求结构化、可恢复、多阶段的软件交付流程,或要求按 devflow 继续已有任务时使用。覆盖任务分级、需求、设计、计划、实现、设计稿还原、代码审查、测试、固定产物归档、知识沉淀和预览部署;适用于不同 Agent、语言、框架和仓库。普通的一次性小改、单独问答或无需流程编排的代码操作不应仅因属于软件开发而自动触发。
- ▌ Tech Design · tencent bundle通用技术方案撰写技能。根据需求输入(需求分析报告或口头描述)自动生成结构完整的技术方案 Markdown 文档。当用户说"帮我写技术方案"、"出一个技术设计文档"、"写一份 design doc"、"给这个需求出方案"时使用本技能。
- ▌ Devflow Codex · tencent在 Codex 中运行 devflow。用户提到 devflow、start/resume/status/abort devflow、多 agent 工作流,或要求“按 Codex devflow 跑”时使用。
- ▌ Writing Plans · tencent bundleUse when you have a spec or requirements for a multi-step task, before touching code
- ▌ Devflow Clarify Requirements · tencent bundle在技术设计前澄清软件交付需求,解决重要产品决策、隐含假设、范围边界、成功标准和未决分支。用于 DevFlow medium/large 的 REQUIREMENT 阶段,或功能请求过于模糊、无法安全设计时。只询问无法从项目证据中回答的问题;不实现、不提交、不写技术方案,也不调用计划类 skill。
- ▌ Knowledge Distillation · tencent通用知识沉淀能力。用于从 devflow 或其他交付过程的需求、设计、实现、审查、测试产物中提炼可复用经验、技术决策、踩坑记录和流程改进。
- ▌ Superpowers Brainstorming · tencent bundleUse during devflow TASK-01 requirement clarification before design or implementation. Explores user intent, requirements, constraints, and success criteria.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Kdit Debug · tencent bundle系统化调试工作流:当现象不明确、根因未知时,强制执行"信息收集 → 假设生成 → 逐层验证 → 定位根因 → 记录结论"的排查流程。 区别于 bugfix(已知问题修代码),debug 侧重于从混沌的现象中找到问题本质。 关键词:debug、调试、排查、诊断、日志分析、二分法、断点、现象不明。
- ▌ Kdit Bugfix · tencent bundleBug 修复工作流:修复 bug 时强制执行"根因分析 → 反思测试缺口 → 修复代码 → 补充单元测试 → 验证"流程。 确保每次 bug 修复都附带回归测试,并反思为什么现有测试没能覆盖到。 关键词:bug fix、修复、regression、回归测试、测试缺口。
- ▌ Kdit Quality · tencent bundlekDiT 质量保障与交付验收:单元测试规范(*_test.py 命名、tests/kdit/ 镜像结构)、 pre-commit 格式检查(black 120字符、ruff)、pytest vs ruff 维度差异、文档同步规则。 关键词:quality、测试、test、pytest、pre-commit、ruff、black、验收。
- ▌ Kdit Standards · tencent bundlekDiT 编码规范:Import 风格(方案 B)、Python 3.10+ 类型注解、Key 类型体系、 Node/Tensor API 开发约束、异常处理规则、类命名规范。 关键词:standards、规范、import、类型注解、Key、异常处理、命名。
- ▌ Kdit Code Review · tencent bundlekDiT 代码评审技能:除常规 CR 项(安全漏洞、格式规范、逻辑正确性)外,重点基于项目 .skills/ 中的架构设计 和编码规范进行评审,确保代码不违背设计原则和约束。 关键词:code review、CR、评审、review、架构合规。
- ▌ Kdit Performance · tencent bundlekDiT 性能调优专家:GPU OOM 排查、推理延迟分析、tensor 内存优化、分布式通信瓶颈诊断。 针对视频生成推理框架的特有性能问题,提供系统化的 profiling → 分析 → 优化 → 验证流程。 关键词:performance、性能、OOM、内存、GPU、延迟、profiling、优化、throughput。
- ▌ Kdit Architecture · tencent bundlekDiT 架构知识库:全局架构图、数据流、Node/Pipeline/Generator/Adapter 子系统设计、 PinHub 沙箱机制、PoolKey 间接寻址、DeviceInfo/NodeContext 规范。 关键词:architecture、架构、Node、Pipeline、Generator、Adapter、Engine、Executor、PinHub、Pool。
- ▌ Kdit Development Spec · tencent bundle在编码或架构设计前强制执行"需求澄清 → 可行性分析 → 结构设计 → 测试设计 → 编码实现 → 校验 → 文档同步"的七步流程。 适用于功能开发、重构、新模块创建、架构讨论与设计评审等需要先设计后实现的场景。 关键词:development spec、先设计后编码、架构讨论、设计评审、需求确认、结构体设计、单元测试先行、vibe testing。
- ▌ Agently Mail · tencent通过 agently-cli 命令行工具操作邮件:发送、回复、转发、搜索、读取、下载附件、管理收件箱。当用户需要进行任何邮件相关操作时使用此 skill。