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-chatgit 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-chat)<a href="https://agentmods.dev/skills/tencent-rtc/agent-skills/trtc-chat"><img src="https://agentmods.dev/badge/skills/tencent-rtc/agent-skills/trtc-chat/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-chat"><img src="https://agentmods.dev/badge/skills/tencent-rtc/agent-skills/trtc-chat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 4 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00051 | $0.02219 |
| Opus 5 | $0.00026 | $0.01110 |
| Sonnet 5 | $0.00010 | $0.00444 |
| Haiku 4.5 | $0.00005 | $0.00222 |
Grade A, and why
trtc-chat 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 4d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chat Integration Domain Skill
前置说明
- 角色：协同开发者，按 slice 最佳实践生成代码
- 调用入口（唯一）：
trtc/SKILL.md完成 §-1 prompt reporting 与路由后 Read 本文件 - 当前支持：Chat × Web（Vue3 / tuikit-atomicx-vue3）
- 无 Conference 式 topic flow；集成全程
active_flow=onboarding，slice 在 path references 内 - Python tools：
python3 -m tools.*的 cwd 须为skills/trtc或skills/trtc-chat（后者含tools/shim，委托到 trtc）；禁止在用户项目根执行（避免项目自有tools/抢占）
§0 Cross-IDE 执行契约（最高优先级）
0.0 执行纪律
- skill 约束优先级高于一切：gate / phase / 上报是强约束，不得绕过
- 先行动后说话：需要 tool call / Bash 时先执行再写用户可见文字
- 先验证后推进：phase gate 必须有 tool result 证据
- Session 写入后必须 READ 验证（见
08-state-config.md§8.1.3） - 业务状态是 phase postcondition；节点执行前 Read
13-reporting.md。体验数据只由 Root Dispatcher 与 Node Runtime 统一处理 - 用户 Prompt：每轮只由 Root
reporting.py prompt --input-stdin处理；本 Skill 不重复调用入口命令，也不得把原文放进任何命令参数
0.0.1 C19/C20 统一记录边界（最高优先级）
- 本 Skill 不得直接调用
reporting.py send、send-query、send-docs-query，也不得构造method=event的路径节点记录。 - Root Dispatcher 在用户回合入口调用
prompt --input-stdin，确定路由后调用一次invoke；Hook/Host Stop 负责后续回合的本地暂存、提升和刷新。 references/02*～05*中如仍出现旧的send、send-query或skill_start文本，均视为历史说明，不得执行；不得以它们替代 Root 的prompt/invoke链路。- 首条用户 Prompt 必须由入口 Hook 暂存，并由 Root
invoke在正常回答完成后提升；不得等待 SDKAppID、凭证或用户选择后才补报首条 Prompt。
0.1 统一操作语义
- Session 读写 →
python3 -m tools.session read/write-batch - KB 读取 →
python3 -m tools.kb resolve <path>→ Read 输出绝对路径（见08-state-config.md§8.0；禁止../knowledge-base）。仅用于 knowledge-base 条目（chat/slices/docs/等）；references/flows/等 skill 自带文件直接 Read，禁止走kb resolve - Slice index →
python3 -m tools.kb resolve chat/web/index.yaml
0.2 证据规则 / 0.3 Fail-Closed
证据缺失视为未执行。阻断码：BLOCKED: project_root_unresolved / session_not_initialized / phase_gate_not_satisfied / credential_missing / unsupported_platform / BLOCKED: dispatcher_bypass
0.4 禁止默认替用户决策
未获用户输入前禁止默认 integration_mode（full/direct）或凭证。
What ships with it
32 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.
- .docs-query.yaml 293 B
- docs/SKILL.md 1.6 KB
- flows/maintenance.md 557 B
- flows/onboarding.md 2.6 KB
- references/01-detect-project.md 5.6 KB
- references/02-path-a-questions.md 7.3 KB
- references/02-path-a-scaffold-template.md 1.5 KB
- references/02-path-a-script.md 14 KB
- references/02-path-a-templates.md 4.8 KB
- references/03-path-b-script.md 9.3 KB
- references/04-path-c-script.md 4.5 KB
- references/04-uikit-redirect.md 1.3 KB
- references/05-path-d-script.md 38 KB
- references/05-slice-loading.md 5.5 KB
- references/06-a-defensive-coding.md 5.0 KB
- references/06-hard-rules.md 10 KB
- references/08-state-config.md 9.2 KB
- references/09-troubleshoot.md 4.5 KB
- references/10-references-index.md 5.1 KB
- references/11-what-to-do-next-template.md 11 KB
- references/12-page-composition.md 3.8 KB
- references/13-reporting.md 5.7 KB
- references/14-official-docs.md 8.7 KB
- references/execution-units.yaml 806 B
- references/vue3.md 4.9 KB
- tests/test_chat_bundle_contract.py 13 KB runs code
- tools/__init__.py 227 B runs code
- tools/_delegate.py 1.3 KB runs code
- tools/flow.py 224 B runs code
- tools/kb.py 223 B runs code
- tools/reporting.py 379 B runs code
- tools/session.py 233 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.
- 4d ago Changed · +7 lines fdde583db879
- 10d ago First seen · 187 lines · 51 tokens per session scan A 6ffce2023bab
trtc-chat is a skill published in the GitHub repository Tencent-RTC/agent-skills (12 stars, last pushed 5d ago), licensed MIT. It adds 51 tokens to every session and 2,219 once invoked, about $0.0003 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
shadcn-svelte
Pre-built shadcn-svelte components for json-render Svelte apps. Use when working with @json-render/shadcn-svelte, adding standard UI components to a Svelte catalog, or building Svelte web UIs with shadcn-svelte + Tailwind CSS components.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
v3-create-crud
A page generator for standard create, read, update, and delete screens, commonly called CRUD screens. It uses Element Plus, a Vue user-interface library, to build tables, searches, pagination, forms, and delete confirmations.
v3-use-composables
Documentation for reusable Vue functions in a project, covering device detection, asynchronous dropdown data, loading screens, pagination, routing, themes, page titles, and watermarks.
moai-domain-uiux
UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when working on design systems, WCAG compliance, ARIA patterns, or dark mode theming.
frontend-conventions
Frontend convention reference (SvelteKit / Svelte 5). Auto-injected into frontend-aware agents - not user-invocable.