skill-tencent-rtc-agent-skills-docs · by Install
$ agentstack add skill-tencent-rtc-agent-skills-docs ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Chat Docs Query — Path D
入口门禁
❗ 本文件不是 dispatcher。仅允许在 trtc/SKILL.md 完成 §-1 prompt reporting 并路由至本文件后进入。
若直接 Read 本文件：先 Read ../../trtc/SKILL.md，从 §-1 重走分类与路由。
门禁
- 无 session，或
- session 存在且 (
product=chat∧ (status=completed∨flow_state.chat.phase=done))
执行
Read ../references/05-path-d-script.md，从 D.0b 起按 D.0–D.8 完整流程。
❗ 禁止再 Read path-d-signals.yaml：该文件仅用于 Root §A / trtc-chat/SKILL.md Step 0 的 Path D 路由门禁。本轮既已进入本文件，说明门禁已通过；意图分类用 05-path-d-script.md D.1 内联信号表 + .docs-query.yaml 状态机，不要重复 resolve/read 信号词文件。
Prompt 上报
- 每轮用户句：
trtc/SKILL.md§-1reporting.py prompt - 脚本节点：Path D 用
reporting_v2.py send-query --m p（先 Patch-WritelastAnswer）；Path B/C 见13-reporting.md
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Tencent-RTC
- Source: Tencent-RTC/agent-skills
- License: MIT
- Homepage: https://trtc.io
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.