Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Tencent-RTC/agent-skillsnpx agentmods add skills/tencent-rtc/agent-skills/trtc-ai-serviceWrote 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-ai-service)<a href="https://agentmods.dev/skills/tencent-rtc/agent-skills/trtc-ai-service"><img src="https://agentmods.dev/badge/skills/tencent-rtc/agent-skills/trtc-ai-service/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-ai-service"><img src="https://agentmods.dev/badge/skills/tencent-rtc/agent-skills/trtc-ai-service.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00115 | $0.13943 |
| Opus 5 | $0.00057 | $0.06971 |
| Sonnet 5 | $0.00023 | $0.02789 |
| Haiku 4.5 | $0.00012 | $0.01394 |
Grade B, and why
trtc-ai-customer-service-skill scanned grade B with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- `chmod 600` `.env` after writing Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Tool: `execute_command("sleep 8 && curl -sS http://localhost:3000/api/v1/health")` How it starts
The opening of the file, as written. The whole thing — 977 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Customer Service Skill (v1.2)
This document is the Coding Agent's execution SOP. It also serves as a user-friendly guide reference. For any natural-language intent involving "build / integrate AI customer service," the AI must read this file first before taking action. All script calls must strictly follow §10 Tool Whitelist.
0. Path Baseline (SKILL_ROOT / PROJECT_ROOT) —— 🔴 Top Priority — Read First
All runtime assets of this Skill (capabilities/, scripts/, scenarios/, auto_adapters/,
start.sh) reside in the Skill's own directory and are not necessarily at the user's workspace root.
The Skill can be installed in arbitrary locations: a project subdirectory, .agents/skills/, .codebuddy/skills/,
and will work across IDEs (Claude Code / Codex / Cursor) in the future. Therefore, never assume "Skill root == Workspace root."
0.1 Definition of the Two Roots
| Variable | Meaning | How to Obtain |
|---|---|---|
SKILL_ROOT |
Skill's own directory (contains SKILL.md / scripts/ / capabilities/ …) |
= The absolute path of the Base directory injected by the system when this Skill is loaded. The Agent must remember it. |
PROJECT_ROOT |
User's current project root (= workspace root; the integration target for Path B) | = The absolute path of the current workspace root. |
Demo path (A) uses
SKILL_ROOT(fetch capability sources + start core) andPROJECT_ROOT(where demo artifacts land); Integration path (B) usesSKILL_ROOT(fetch capability sources + start core) andPROJECT_ROOT(integration target). These two may or may not be the same — do not mix them up.
0.2 Hard Rules for Path Usage
- All commands that call Skill-bundled scripts / assets must use the absolute path of
SKILL_ROOT, e.g.:
Do not write bare relative paths (e.g.,cd "$SKILL_ROOT" && python3 scripts/add-capability.py ... # or python3 "$SKILL_ROOT/scripts/add-capability.py" ...python3 scripts/...) assuming they resolve against the workspace root — that was the root cause of bugs in previous versions. - For all command templates in this document that contain
$SKILL_ROOT/$PROJECT_ROOT, the Agent must substitute them with actual absolute paths before execution. - The scripts themselves (
start.sh/add-capability.py/post-install-patch.py) already self-locate (via__file__/BASH_SOURCE), so as long as you invoke them with their absolute path, they work regardless of cwd. - If
SKILL_ROOTcannot be determined immediately, fall back to a one-shot detection (do not ask the user to move directories):
If still not found, ask the user where the Skill is installed. Never ask the user to move the Skill directory to the workspace top level.find "$PWD" -maxdepth 4 -name SKILL.md -path '*ai-service*' 2>/dev/null | head -1
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.
- auto_adapters/frontend-spa/angular/voice-agent.component.ts.tpl 3.8 KB
- auto_adapters/frontend-spa/manifest.yaml 2.0 KB
- auto_adapters/frontend-spa/react/VoiceAgent.tsx.tpl 4.2 KB
- auto_adapters/frontend-spa/README.md 1.2 KB
- auto_adapters/frontend-spa/vue/VoiceAgent.vue.tpl 3.5 KB
- auto_adapters/integration_templates/generic-backend.md 1.8 KB
- auto_adapters/integration_templates/generic-frontend.md 1.5 KB
- auto_adapters/integration_templates/generic-rest-api.md 2.5 KB
- auto_adapters/java-backend/manifest.yaml 1.0 KB
- auto_adapters/java-backend/quarkus/VoiceAgentFilter.java.tpl 2.4 KB
- auto_adapters/java-backend/README.md 875 B
- auto_adapters/java-backend/springboot/VoiceAgentFilter.java.tpl 3.5 KB
- auto_adapters/manifest.yaml 1.6 KB
- auto_adapters/node-backend/express.js.tpl 1.6 KB
- auto_adapters/node-backend/fastify.js.tpl 1.0 KB
- auto_adapters/node-backend/koa.js.tpl 1.2 KB
- auto_adapters/node-backend/manifest.yaml 1.5 KB
- auto_adapters/node-backend/README.md 1.2 KB
- auto_adapters/python-backend/django.py.tpl 1.2 KB
- auto_adapters/python-backend/fastapi.py.tpl 1.3 KB
- auto_adapters/python-backend/flask.py.tpl 1.1 KB
- auto_adapters/python-backend/manifest.yaml 1.2 KB
- auto_adapters/python-backend/README.md 911 B
- auto_adapters/README.md 1.7 KB
- capabilities/__init__.py 1.2 KB runs code
- capabilities/conversation-core/.env.example 1001 B
- capabilities/conversation-core/INTEGRATION.md 5.8 KB
- capabilities/conversation-core/INTERFACE_ADAPT.md 4.5 KB
- capabilities/conversation-core/manifest.yaml 9.4 KB
- capabilities/conversation-core/QUICK_START.md 1.9 KB
- capabilities/conversation-core/requirements.txt 109 B
- capabilities/conversation-core/src/__init__.py 402 B runs code
- capabilities/conversation-core/src/_capability_loader.py 7.6 KB runs code
- capabilities/conversation-core/src/agent.py 9.4 KB runs code
- capabilities/conversation-core/src/credentials.py 3.9 KB runs code
- capabilities/conversation-core/src/health.py 13 KB runs code
- capabilities/conversation-core/src/log_filter.py 2.4 KB runs code
- capabilities/conversation-core/src/modality.py 4.0 KB runs code
- capabilities/conversation-core/src/server.py 11 KB runs code
- capabilities/conversation-core/src/trtc_client.py 12 KB runs code
- capabilities/conversation-core/src/usersig.py 2.6 KB runs code
- capabilities/conversation-core/tests/__init__.py 0 B runs code
- capabilities/conversation-core/tests/test_skeleton.py 7.4 KB runs code
- capabilities/conversation-core/web-demo/app.js 14 KB runs code
- capabilities/conversation-core/web-demo/index.html 2.6 KB
- capabilities/conversation-core/web-demo/README.md 1.8 KB
- capabilities/conversation-core/web-demo/styles.css 4.1 KB
- capabilities/digital-human/manifest.yaml 2.2 KB
- capabilities/digital-human/README.md 1.2 KB
- capabilities/digital-human/src/__init__.py 108 B runs code
- capabilities/digital-human/src/router.py 1.3 KB runs code
- capabilities/human-handoff/INTERFACE_ADAPT.md 11 KB
- capabilities/human-handoff/manifest.yaml 8.4 KB
- capabilities/human-handoff/README.md 1.5 KB
- capabilities/human-handoff/src/__init__.py 102 B runs code
- capabilities/human-handoff/src/adapters/__init__.py 210 B runs code
- capabilities/human-handoff/src/adapters/default_rest.py 8.2 KB runs code
- capabilities/human-handoff/src/adapters/factory.py 2.8 KB runs code
- capabilities/human-handoff/src/adapters/local_queue.py 9.4 KB runs code
- capabilities/human-handoff/src/adapters/mock.py 5.0 KB 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 4cc515ecc0bc
- 11d ago First seen · 977 lines · 115 tokens per session scan B c767574de7ee
trtc-ai-customer-service-skill is a skill published in the GitHub repository Tencent-RTC/agent-skills (13 stars, last pushed yesterday), licensed MIT. It adds 115 tokens to every session and 13,943 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
claude-code-dmwork
Connect to DMWork messaging platform as an AI bot via the OpenClaw DMWork adapter plugin.
vs-chat
Conversational search runtime: send messages, keep sessions consistent, and verify retrieval behavior and responses.
stream-flutter
Build and integrate Stream Chat, Video, and Feeds in Flutter apps. Use for Flutter/Dart project work with Stream package setup, auth wiring, and widget blueprints. Supports streamchatflutter (pre-built Chat UI), streamchatfluttercore (custom Chat UI), streamvideoflutter (Video calling and livestreaming), and…
audit-tracking
Audit Waniwani event tracking across an MCP project. Does an in-depth overview check of the whole app (server, flows, tools, widgets, chat embed), verifies that only events defined in the Waniwani taxonomy are sent, and identifies missing events worth adding at each funnel stage (identify, leadqualified, priceshown…
github-flow-for-claude-on-web
Complete GitHub workflow for Claude Code on the web. ALL GitHub operations MUST use REST API (never gh CLI). Includes branch naming (claude/-sessionId), push retry logic, PR/issue management via API, and complete workflows. Use for all GitHub interactions in Claude Code web environment.
stream-unreal
Build, integrate, and answer how-to questions for Stream Chat in Unreal Engine games and apps. Use for Unreal Engine / UE5 / C++ / Blueprint / UMG project work - plugin install per engine version, StreamChatClientComponent wiring on the HUD, ConnectUser and tokens, channels and messages, the shipped WBP chat widgets…