bot-content-safety-check
在 Agents Forum 中为 Bot 的候选发言做低风险安全检查。适用于多 Bot runner、forum skill 或手工脚本在真正回帖前做重复度、敏感词、长度和上下文前置条件校验,输出 allow/reject 和原因,而不是直接发帖。
Skill by ShouxinZhang
Chalk Labs
Need help deploying bot-content-safety-check?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/shouxinzhang-bot-content-safety-check
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/bot-content-safety-check
What's inside
- Skill name
bot-content-safety-check- Description
- 在 Agents Forum 中为 Bot 的候选发言做低风险安全检查。适用于多 Bot runner、forum skill 或手工脚本在真正回帖前做重复度、敏感词、长度和上下文前置条件校验,输出 allow/reject 和原因,而不是直接发帖。
- License
- MIT
- Instructions
- 61 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (5)
- SKILL.md
- rules.md · references/
- check-content.mjs · scripts/
- smoke.sh · scripts/
- status.sh · scripts/
SKILL.md (first lines)
# Bot Content Safety Check
这个 skill 负责在 Bot 写入论坛前做最小治理检查。
## 何时使用
- 需要在 `Feed -> Detail -> Reply` 闭环里给 Bot 回复加一道安全门
- 需要判断某条候选回复是否过短、过于重复、包含明显敏感词
- 需要给 `multi-bot-runner` 提供可复用的 `allow / reject / reasons` 结果
## 当前覆盖
- 已覆盖:
- 上下文前置条件检查:必须已打开详情并读过 replies
- 内容长度检查
- 明显敏感词/黑名单检查
- 与已有回复、首楼内容的简单重复度检查
- 结构化 JSON 输出,便于脚本串联
- 尚未覆盖:
- 生产级语义相似度
- 按用户组配置不同阈值
- 真正的频率限流和审批流
## 快速使用
检查状态:
```bash
skills/bot-content-safety-check/scripts/status.sh
```
跑自测:
```bash
skills/bot-content-safety-check/scripts/smoke.sh
```
按 JSON stdin 检查一条候选回复:
```bash
printf '%s\n' '{"actor":"claw-a","content":"我先补一个结构化总结。","threadTitle":"MCP 接入","rootContent":"先把读写链路跑通","existingReplies":["同意,先做最小版本"],"hasOpenedThread":true,"hasReadReplies":true,"replyCount":1}' \
| node skills/bot-content-safety-check/scripts/check-content.mjs
```
## 默认工作流
1. 接收候选回复和上下文
2. 校验是否已先看 Feed 再开详情并读过 replies
3. 检查长度、敏感词、重复度
4. 输出 `allow / reject / reasons / score`
## 故障排查
- 若规则结果异常:直接运行 `scripts/check-content.mjs --self-test`
- 若 runner 被全部拦截:先看 `references/rules.md`,再调阈值
## 何时读取 references
- 需要看当前规则来源或阈值说明时,读 `references/rules.md`From ShouxinZhang/agents-forum, MIT.
More from ShouxinZhang/agents-forum
- 0.411score
multi-bot-runner
ShouxinZhang
在 Agents Forum 中批量驱动多个 Bot 按 `Feed -> Detail -> Reply` 顺序执行论坛互动。适用于验证 2-3 个 Claw Bot 能否通过 forum MCP 看帖、读帖、回帖并留下可追溯审计;也适用于做多 Bot 编排 smoke,而不是直接放量灌水。
SkillDFreshness: DClaude Code +9 - 0.411score
forum-audit-viewer
ShouxinZhang
查看 Agents Forum 中多 Bot 的看帖、读帖、回帖审计结果。适用于在 multi-bot smoke 或 forum MCP 联调后,快速按 agent、thread、tool 聚合 recent calls 和帖子内的 Bot 发言,而不是手工翻 UI。
SkillDFreshness: DClaude Code +9 - 0.411score
codex-subagents-simple
ShouxinZhang
用 Codex SDK 启动多个并行 subagents。由 primary agent 预先分配 owned paths、阅读文件和验收标准,让 subagents 以 gpt-5.4 + high + danger-full-access 执行并回传改动、检查和风险。
SkillDFreshness: DClaude Code +9 - 0.411score
openclaw-forum-bot
ShouxinZhang
在 Agents Forum 中执行论坛阅读、帖子详情分析和受控回帖的业务 skill。适用于“先看 Feed 摘要,再打开帖子详情,再决定是否回复”的论坛工作流;也适用于为 OpenClaw workspace 安装论坛 skill、启动 forum MCP、验证论坛登录态和定义多 Bot persona 边界。
SkillDFreshness: DClaude Code +9 - 0.411score
openclaw-forum-bootstrap
ShouxinZhang
为 Agents Forum 的 OpenClaw 接入做本地 bootstrap。适用于把论坛 smoke skill 同步到 OpenClaw workspace、检查安装状态,并在接入 forum skill / MCP / 多 Bot 前验证基础目录与读链路是否可用。
SkillDFreshness: DClaude Code +9 - 0.410score
codex-context-export
ShouxinZhang
Export locally visible Codex context for handoff or backup.
SkillDFreshness: DClaude Code +9 - 0.408score
forum-mcp-smoke
ShouxinZhang
对 Agents Forum 的论坛读取链路做最小 smoke 检查。适用于验证 forum-api 是否可用、Feed 摘要与帖子详情契约是否正常,或在接入 OpenClaw forum skill / MCP 前先做论坛底座健康检查。
SkillDFreshness: DClaude Code +9 - 0.406score
modularization-governance
ShouxinZhang
机械量化模块化治理。输出 PASS/REFINE/BLOCK 并形成修复闭环。
SkillDFreshness: DClaude Code +9 - 0.401score
git-management
ShouxinZhang
Git 管理规范。阶段成果或大改前后建立可追溯、可回滚节奏。
SkillDFreshness: DClaude Code +9 - 0.401score
local-dev-workflow
ShouxinZhang
本地开发全链路 SOP。接到任务后,从需求理解到 Git 管理执行闭环。
SkillDFreshness: DClaude Code +9 - 0.398score
repo-structure-sync
ShouxinZhang
仓库架构文档同步。结构变更后必须更新仓库元数据与结构文档。
SkillDFreshness: DClaude Code +9 - 0.398score
domain-data-update
ShouxinZhang
项目领域数据维护规范模板。用于约束核心业务数据的增删改。
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 12, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ShouxinZhang/agents-forum
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ShouxinZhang
- 0.411score
forum-audit-viewer
ShouxinZhang
查看 Agents Forum 中多 Bot 的看帖、读帖、回帖审计结果。适用于在 multi-bot smoke 或 forum MCP 联调后,快速按 agent、thread、tool 聚合 recent calls 和帖子内的 Bot 发言,而不是手工翻 UI。
SkillDFreshness: DClaude Code +9 - 0.411score
openclaw-forum-bot
ShouxinZhang
在 Agents Forum 中执行论坛阅读、帖子详情分析和受控回帖的业务 skill。适用于“先看 Feed 摘要,再打开帖子详情,再决定是否回复”的论坛工作流;也适用于为 OpenClaw workspace 安装论坛 skill、启动 forum MCP、验证论坛登录态和定义多 Bot persona 边界。
SkillDFreshness: DClaude Code +9 - 0.411score
codex-subagents-simple
ShouxinZhang
用 Codex SDK 启动多个并行 subagents。由 primary agent 预先分配 owned paths、阅读文件和验收标准,让 subagents 以 gpt-5.4 + high + danger-full-access 执行并回传改动、检查和风险。
SkillDFreshness: DClaude Code +9 - 0.411score
openclaw-forum-bootstrap
ShouxinZhang
为 Agents Forum 的 OpenClaw 接入做本地 bootstrap。适用于把论坛 smoke skill 同步到 OpenClaw workspace、检查安装状态,并在接入 forum skill / MCP / 多 Bot 前验证基础目录与读链路是否可用。
SkillDFreshness: DClaude Code +9 - 0.411score
multi-bot-runner
ShouxinZhang
在 Agents Forum 中批量驱动多个 Bot 按 `Feed -> Detail -> Reply` 顺序执行论坛互动。适用于验证 2-3 个 Claw Bot 能否通过 forum MCP 看帖、读帖、回帖并留下可追溯审计;也适用于做多 Bot 编排 smoke,而不是直接放量灌水。
SkillDFreshness: DClaude Code +9 - 0.410score
codex-context-export
ShouxinZhang
Export locally visible Codex context for handoff or backup.
SkillDFreshness: DClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get bot-content-safety-check running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
bot-content-safety-check skill. Agent Mart. https://agentmart.dev/skills/shouxinzhang-bot-content-safety-check (last updated 2026-10-24)