Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Tencent-RTC/agent-skills --skill trtc-conferencegit clone --depth 1 https://github.com/Tencent-RTC/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tencent-rtc/agent-skills/trtc-conference)<a href="https://agentmods.dev/skills/tencent-rtc/agent-skills/trtc-conference"><img src="https://agentmods.dev/badge/skills/tencent-rtc/agent-skills/trtc-conference/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tencent-rtc/agent-skills/trtc-conference"><img src="https://agentmods.dev/badge/skills/tencent-rtc/agent-skills/trtc-conference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00153 | $0.04427 |
| Opus 5 | $0.00077 | $0.02214 |
| Sonnet 5 | $0.00031 | $0.00885 |
| Haiku 4.5 | $0.00015 | $0.00443 |
Grade A, and why
trtc-conference scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
trtc-conference — Conference 集成域技能
前置说明
你的角色:协同开发者。你扫描用户项目、按 slice 最佳实践生成代码。代码写入在
flows/onboarding.md → topic 的 slice 循环中完成,每步通过 python3 -m tools.apply 静默结构门控——
用户不感知这个过程,也不要主动提起。
调用入口:本文件由 trtc/SKILL.md 在 product=conference 时 Read。
当前支持范围:Conference × Web。其他平台进入本文件后应告知用户暂不支持并给出官方文档链接。
Python tools:执行任何 python3 -m tools.* 命令时,必须从当前 trtc
skill 根目录执行(例如先 cd "<当前 trtc skill 目录>")。不要依赖客户项目根目录
存在 tools/ 包。
Reporting boundary:Root/host bootstrap 统一处理本轮 Prompt、路由和 Host Stop notice;若本 Skill 被直接调用且 Host 未记录本轮,才用 stdin Prompt 入口补一次。普通失败继续业务流程;不得恢复旧 MCP 或独立 send 路径。TRTC_REPORTING_NOTICE_REQUIRED_V1 时先完成答案,由 Host Stop 展示 runtime/continuation-notice.md,模型不得自行附加或改写。
动态澄清问题前保留 context --question;固定选项仍使用标准选项 UI。Root/Host 负责路由与 notice 展示,业务 Skill 不得恢复旧 MCP 或独立 send 路径。
Direct-Route Bootstrap
当 dispatcher 识别到 Conference Web 的 direct walkthrough 请求(例如用户明确说 “直接带我一步一步搭 1v1 视频会议”)时,本文件承担 topic bootstrap,并负责把会话引导到 conference topic flow。
bootstrap 规则:
- 若 session 不存在:先通过
python3 -m tools.session create --product conference --platform web --intent integrate-scenario --project-root "<projectRoot>"创建会话;随后在进入 topic 前,按当前 state_version 用python3 -m tools.session write-batch --project-root "<projectRoot>"补齐最小 bootstrap 字段集(至少包含active_flow=topic、coverage_decided=false,以及已知的scenario/active_domain_skill/flow_entered)。不要手动编辑.trtc-session.yaml。 - 若 session 已存在且
active_flow = topic:直接恢复 topic 路径。 - 若用户已明确给出 Conference Web 场景:允许跳过 capability overview,但必须把
scenario写入 session,并显式写coverage_decided = false,让flows/topic.md的 Step 1.5 正常接手 coverage 决策;bootstrap 不负责猜最终 coverage。 - 若 scenario 仍不明确:继续走本文件的 A2-Q0 场景确认;不要猜测。
- bootstrap 完成后,Conference Web topic 一律通过
python3 -m tools.flow enter --phase topic --product conference --platform web进入flows/topic.md。
Conference 以外产品暂不在这里暴露 direct topic bootstrap。
入口:读取 session 状态
读取 {project_root}/.trtc-session.yaml:
- 文件存在且
status = active:优先看integration_path(topic / medical-quickstart / official-roomkit),若缺失再兼容回退到active_flow:integration_path = medical-quickstart(或兼容态active_flow = medical-quickstart)→ 续接playbooks/medical-quickstart.md,STOPintegration_path = official-roomkit(或兼容态active_flow = official-roomkit)→ 续接playbooks/official-roomkit.md,STOPintegration_path = topic且active_flow = onboarding→ 续接flows/onboarding.md,STOP- 其他值或为空 → 记录当前 session 数据(
scenario、ui_mode、capability_overview_shown、project_state、intent),继续向下执行,不清空 session
- 文件不存在或
status = completed:按新会话流程向下执行
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- flows/onboarding.md 9.5 KB
- flows/topic.md 27 KB
- flows/troubleshoot.md 4.6 KB
- hooks/pretooluse_require_business_decisions.py 6.9 KB runs code
- playbooks/medical-quickstart.md 2.6 KB
- playbooks/official-roomkit.md 4.7 KB
- references/execution-units.yaml 1.6 KB
- references/local-usersig/basic-info-config.ts 1.2 KB runs code
- references/local-usersig/lib-generate-test-usersig-es.min.d.ts 162 B runs code
- references/local-usersig/lib-generate-test-usersig-es.min.js 147 KB runs code
- references/usersig-handling.md 4.2 KB
- templates/medical-consultation/.gitignore 30 B
- templates/medical-consultation/docs/backend-contract.zh-CN.md 3.4 KB
- templates/medical-consultation/docs/integration.zh-CN.md 4.7 KB
- templates/medical-consultation/docs/theme.zh-CN.md 2.6 KB
- templates/medical-consultation/index.html 302 B
- templates/medical-consultation/package.json 724 B
- templates/medical-consultation/postcss.config.js 72 B runs code
- templates/medical-consultation/src/App.vue 549 B
- templates/medical-consultation/src/components/ConsultationManagePanel.vue 25 KB
- templates/medical-consultation/src/components/LanguageSwitch.vue 2.7 KB
- templates/medical-consultation/src/components/LoadingSpinner.vue 182 B
- templates/medical-consultation/src/components/MedicalAlert.vue 943 B
- templates/medical-consultation/src/components/MedicalBusinessPanel.vue 5.3 KB
- templates/medical-consultation/src/components/MedicalButton.vue 1.5 KB
- templates/medical-consultation/src/components/MedicalConfirmDialog.vue 1.8 KB
- templates/medical-consultation/src/components/MedicalDataPanel.vue 6.2 KB
- templates/medical-consultation/src/components/MedicalRecordPanel.vue 9.5 KB
- templates/medical-consultation/src/components/PrescriptionPanel.vue 13 KB
- templates/medical-consultation/src/config/basic-info-config.ts 715 B runs code
- templates/medical-consultation/src/config/lib-generate-test-usersig-es.min.d.ts 162 B runs code
- templates/medical-consultation/src/config/lib-generate-test-usersig-es.min.js 147 KB runs code
- templates/medical-consultation/src/config/runtime-config.ts 499 B runs code
- templates/medical-consultation/src/env.d.ts 751 B runs code
- templates/medical-consultation/src/features/consultation/components/ConsultationChatPanel.vue 4.2 KB
- templates/medical-consultation/src/features/consultation/components/ConsultationMembersPanel.vue 8.6 KB
- templates/medical-consultation/src/features/consultation/components/ConsultationTranscriptionPanel.vue 5.1 KB
- templates/medical-consultation/src/features/consultation/components/ConsultationVideoStage.vue 3.6 KB
- templates/medical-consultation/src/features/consultation/components/InviteDoctorDialog.vue 4.7 KB
- templates/medical-consultation/src/features/consultation/components/KickMemberConfirmDialog.vue 1.6 KB
- templates/medical-consultation/src/features/consultation/types.ts 1.5 KB runs code
- templates/medical-consultation/src/features/consultation/useConsultationChat.ts 2.6 KB runs code
- templates/medical-consultation/src/features/consultation/useConsultationDevices.ts 1.4 KB runs code
- templates/medical-consultation/src/features/consultation/useConsultationParticipants.ts 3.4 KB runs code
- templates/medical-consultation/src/features/consultation/useConsultationPermissions.ts 735 B runs code
- templates/medical-consultation/src/features/consultation/utils.ts 2.0 KB runs code
- templates/medical-consultation/src/i18n/en-US/index.ts 29 KB runs code
- templates/medical-consultation/src/i18n/index.ts 555 B runs code
- templates/medical-consultation/src/i18n/medicalTranslate.ts 3.5 KB runs code
- templates/medical-consultation/src/i18n/state.ts 1.4 KB runs code
- templates/medical-consultation/src/i18n/zh-CN/index.ts 27 KB runs code
- templates/medical-consultation/src/main.ts 300 B runs code
- templates/medical-consultation/src/mock/appointments.ts 2.8 KB runs code
- templates/medical-consultation/src/mock/users.ts 2.0 KB runs code
- templates/medical-consultation/src/router/index.ts 1.5 KB runs code
- templates/medical-consultation/src/services/adapters/index.ts 1.1 KB runs code
- templates/medical-consultation/src/services/adapters/integration/appointmentService.ts 2.5 KB runs code
- templates/medical-consultation/src/services/adapters/integration/authService.ts 1.1 KB runs code
- templates/medical-consultation/src/services/adapters/integration/launchContext.ts 1008 B runs code
- templates/medical-consultation/src/services/adapters/integration/userService.ts 718 B runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago Changed ae4668f04d86
- 11d ago First seen · 312 lines · 153 tokens per session scan A 949c567d8f1c
trtc-conference is a skill published in the GitHub repository Tencent-RTC/agent-skills (13 stars, last pushed yesterday), licensed MIT. It adds 153 tokens to every session and 4,427 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
stream
Stream router for Chat, Video, Feeds, and Moderation. Use when the user wants to build a new app with Stream, scaffold a project, add Chat/Video/Feeds/Moderation to an existing app, integrate Stream, audit or migrate an integration, build for Swift/SwiftUI/UIKit/iOS/Xcode/Android/Kotlin/React Native/Expo/Flutter…
cometchat-nextjs-patterns
Framework-specific patterns for integrating CometChat React UI Kit v6 into Next.js projects (App Router and Pages Router). Covers SSR prevention, provider setup, route placement, API routes, and common pitfalls.
cometchat-angular-calls
CometChat Calls integration for Angular UI Kit v5 (@cometchat/chat-uikit-angular@5). Covers enabling calling via UIKitSettingsBuilder().setCallingEnabled(true), the kit's standalone call components ( , , , , ), the @Input-callback-vs-@Output binding split, app-wide incoming-call mounting, the…
cometchat-angular-production
Production-readiness for CometChat Angular UI Kit v5 (@cometchat/chat-uikit-angular@5) — server-minted auth tokens via CometChatUIKit.loginWithAuthToken(authToken), user management CRUD, environment.prod.ts hardening (no authKey, no REST API Key), external-backend recipes (Express / Hono / Firebase Functions /…
cometchat-react-patterns
Framework-specific patterns for integrating CometChat React UI Kit v6 into React projects (Vite or CRA). Covers provider setup, routing, layout integration, env vars, and common pitfalls.
cometchat-react-push
Push notifications for CometChat React UI Kit v6 in Vite / Next.js / React Router / Astro projects. Recommended path is CometChat-native web push via Firebase Cloud Messaging for Web — CometChatNotifications.registerPushToken(token, PushPlatforms.FCMWEB) + a dashboard FCM provider, so CometChat's own backend delivers…