productivityby openakita
QQ 频道管理
openakita/skills@qq-channel
QQ Channel (Tencent Channel) bot management skill. Manage channels, sub-channels, members, messages, announcements, and schedules via QQ Bot API.
What it changes
Passed 17 of 20 test cases with the skill, and 10 of 20 without it.
Without skill50%
With skill86%
Checks it passed that the model alone missed
- Points to scripts/qq_bot.py
- Uses python3 scripts/qq_bot.py guilds
- Includes fetching guild lists and guild details
and 5 more in the full report
8 fixed11 passed either way3 still failing0 broke
- Pass-rate lift
- +36 pp
- Tokens
- -35%
- Agent turns
- 0%
- Response time
- -49%
Model gemini-3.6-flashMeasured 8/13/2026v119 of 22 cases passed with skill · 20 comparable
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWrite the exact CLI command to send the text message 'System maintenance in 10 minutes' to sub-channel 998811 using the repository helper script.
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Uses python3 scripts/qq_bot.py send --channel-id 998811 --content "System maintenance in 10 minutes" | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md35 lines2 filesincludes scripts
QQ 频道管理
通过 QQ 机器人 API 管理腾讯频道/QQ 频道的消息、成员和内容。
前置条件
核心能力
API 鉴权
使用 getAppAccessToken 获取 Token，请求头携带 Authorization: QQBot {token}。
预置脚本
scripts/qq_bot.py
QQ 频道机器人 API 封装，需设置 QQ_BOT_APPID 和 QQ_BOT_TOKEN。
python3 scripts/qq_bot.py guilds
python3 scripts/qq_bot.py channels --guild-id 123456
python3 scripts/qq_bot.py send --channel-id 789 --content "Hello"
Track record
Benchmark
17 / 20
test cases passed, vs 10 / 20 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
ImportedLicense MITImported 8/3/2026Version v1Bundled 1 file · scripts