Pinvou/pinvou-agent / pinvou3-app/src-tauri/resources/common/bundle/tmeet-skills/tmeet-skill
tmeet-skill
Verified何时用:用户明确要通过命令行操作腾讯会议(tmeet),或 Agent 遇到工具缺失/调用失败/能力不足想反馈平台时。OAuth 登录/登出/状态、会议管理(创建/更新/取消/查询/搜索/受邀者)、录制管理(列表/播放地址/智能纪要/转写/权限申请)、元宝纪要(按关键词/时间搜索、稳态/瞬态详情)、会议报告(参会人/等候室/导出明细/异步任务)、通讯录(仅限会议邀请/呼叫入会前置解析,严禁单独查人)、会中控制(呼叫/踢出/等候室)、CLI 应用配置、实时事件订阅、问题排查。泛指需求默认走本地工具。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 34.8 KB |
| references/tmeet-app.md | markdown | 10.7 KB |
| references/tmeet-auth.md | markdown | 4.0 KB |
| references/tmeet-contact.md | markdown | 10.9 KB |
| references/tmeet-control.md | markdown | 9.3 KB |
| references/tmeet-event.md | markdown | 27.2 KB |
| references/tmeet-meeting.md | markdown | 28.8 KB |
| references/tmeet-minutes.md | markdown | 15.5 KB |
| references/tmeet-record.md | markdown | 24.3 KB |
| references/tmeet-report.md | markdown | 8.6 KB |
| references/tmeet-tshoot.md | markdown | 5.3 KB |
| scripts/agent_init.py | script | 3.2 KB |
scripts/agent_init.py
View on GitHub#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""Initialize tmeet CLI agent.json with the calling AI-Agent and LLM model info.
Usage:
python3 agent_init.py --agent <agent-name> --model <model-name>
Behavior:
1. Resolve config dir from env TMEET_CLI_CONFIG_DIR; fallback to ~/.tmeet/.
2. Ensure the directory exists (permission 0700).
3. Atomically write <config_dir>/agent.json in the AgentConfig JSON shape:
{"agent": "...", "model": "..."}
Empty fields are omitted (mirrors Go's `omitempty`).
"""
import argparse
import json
import os
import sys
import tempfile
from pathlib import Path
CONFIG_DIR_ENV = "TMEET_CLI_CONFIG_DIR"
DEFAULT_CONFIG_DIR = "~/.tmeet"
AGENT_CONFIG_FILE = "agent.json"
def get_config_dir() -> Path:
"""Return the tmeet config directory.
Priority:
1. Env var TMEET_CLI_CONFIG_DIR (if non-empty).
2. ~/.tmeet/
"""
env_dir = os.environ.get(CONFIG_DIR_ENV, "").strip()
if env_dir:
return Path(env_dir).expanduser()
return Path(DEFAULT_CONFIG_DIR).expanduser()
def save_agent_config(config_dir: Path, agent: str, model: str) -> Path:
"""Atomically write AgentConfig to <config_dir>/agent.json.
Uses tmp-file + os.replace to mirror the Go implementation's atomic write.
Empty fields are omitted from the JSON output.
"""
config_dir.mkdir(parents=True, exist_ok=True)
try:
os.chmod(config_dir, 0o700)
except OSError:
# Best-effort; ignore on filesystems that do not support chmod (e.g. Windows).
pass
payload: dict = {}
if agent:
payload["agent"] = agent
if model:
payload["model"] = model
data = json.dumps(payload, indent=2, ensure_ascii=False)
target = config_dir / AGENT_CONFIG_FILE
# Write to a temp file in the same directory, then atomically rename.
fd, tmp_path = tempfile.mkstemp(
prefix="." + AGENT_CONFIG_FILE + "-",
suffix=".tmp",
dir=str(config_dir),
)
try:
with os.fdopen(fd, "w", encoding="utf-8") as f:
f.write(data)
f.flush()
os.fsync(f.fileno())
try:
os.chmod(tmp_path, 0o600)
except OSError:
pass
os.replace(tmp_path, target)
except Exception:
# Clean up temp file on failure.
try:
os.remove(tmp_path)
except OSError:
pass
raise
return target
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(
description="Write tmeet AgentConfig (agent.json).",
)
parser.add_argument(
"--agent",
default="",
help="AI-Agent name (e.g. Cursor, Claude Desktop, Cline).",
)
parser.add_argument(
"--model",
default="",
help="LLM model name (e.g. Claude 3.5 Sonnet, GPT-4o).",
)
return parser.parse_args()
def main() -> int:
args = parse_args()
config_dir = get_config_dir()
try:
path = save_agent_config(config_dir, args.agent.strip(), args.model.strip())
except OSError as e:
print(f"failed to save agent config: {e}", file=sys.stderr)
return 1
print(f"agent config saved: {path}")
return 0
if __name__ == "__main__":
sys.exit(main())Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |