community-moderation
Skill0 starsChanged 2 months agoMITView on GitHub
当直播社区需要内容审核、风控与举报处置,或发现违规内容滞后处理、处置标准不统一、举报石沉大海、直播实时风控缺位时,启用本技能。它生成审核维度与分级处置标准、举报处理 SOP 与直播合规红线,把"靠人工盯"变成"有标准、有梯度、可追溯"的治理。
1 other project uses a version of this.
Adopted by
Most recently taken up by
- AppFreeticket/freeticket-mcptheir own version, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- AppFreeticket/freeticket-mcp★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- audience-growthSkill
- live-room-opsSkill
- live-show-planSkill
- streamer-onboardingSkill
- my-skillSkill
The file
Files
社区内容审核与风控(Community Moderation)
When to use
- 社区内容(动态 / 评论 / 直播)出现违规,处置滞后或不统一。
- 举报受理后无跟踪、无回访,用户信任下降。
- 直播实时风控缺位(敏感词、图像、引战无人预警)。
- 合规口径分散,运营与审核对"什么算违规"理解不一致。
Steps
- 定义审核维度:内容违规(色情低俗 / 暴力 / 政治敏感)、版权(音乐 / 素材 / 搬运)、未成年人保护、广告导流、引战谩骂、诈骗等,给出判别要点。
- 分级处置:建立「预警 → 提醒 → 限流 → 禁言 → 封禁」五档标准,每档给触发条件、处置动作与话术,避免一刀切。
- 举报处理流:受理 → 核查(取证)→ 处置 → 回访的闭环 SOP,含响应时效与结论告知模板。
- 直播实时风控:给关键词 / 图像识别的巡检建议与预警阈值,输出主播侧实时提示话术与运营侧处置入口。
- 合规红线清单:梳理直播合规口径(内容安全、未成年人、版权、打赏、广告),对齐平台规则与监管要求。
Output
- 一份《审核标准表》Markdown(维度 / 判别要点 / 证据要求)。
- 一套分级处置话术(五档 × 场景)。
- 一份《举报处理 SOP》(闭环 + 时效 + 告知模板)。
- 一份《直播合规红线清单》(给主播与运营双版本)。
Guardrails
- 封禁 / 限流等破坏性处置不自动执行,须人工复核(HITL),保留证据与记录。
- 处置以"纠正 + 梯度"为先,避免误伤与平台规则冲突。
- 用户隐私(举报人、被处置人信息)严格保密,不跨域流转。
Notes
- 与
live-room-ops对齐:直播中的违规判定与处置话术两技能共用一套标准。 - 与
audience-growth互补:风控保障社区健康,增长才有可持续基础。 - 审核口径应随平台规则与监管更新,定期回灌到标准表。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

