A guide for operating Knowledge Planet, a Chinese community platform, through its command-line tool and underlying interface.

Use it to manage Knowledge Planet communities and posts, review comments, answer questions, create reports or media, monitor risky content, and handle supported payment tasks.

It organizes authentication, content management, comments, questions, tags, reports, scheduled publishing, and payment-related tasks into defined workflows.

zsxq — Skill for Claude Code and Codex by unnoo/zsxq-skill

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add unnoo/zsxq-skill --skill zsxq

Clone the repo

git clone --depth 1 https://github.com/unnoo/zsxq-skill

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/unnoo/zsxq-skill/zsxq/github.svg)](https://agentmods.dev/skills/unnoo/zsxq-skill/zsxq)

Your own site

<a href="https://agentmods.dev/skills/unnoo/zsxq-skill/zsxq"><img src="https://agentmods.dev/badge/skills/unnoo/zsxq-skill/zsxq/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/unnoo/zsxq-skill/zsxq"><img src="https://agentmods.dev/badge/skills/unnoo/zsxq-skill/zsxq.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 553 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,554 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

Socket warn 5 Nov 2026
Snyk warn 5 Nov 2026
NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00553	$0.06554
Opus 5.5	$0.00221	$0.02622
Sonnet 5.5	$0.00111	$0.01311
Haiku 4.5	$0.00055	$0.00655

Measured yesterday against content hash 4a121ffeae34, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zsxq scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/scenarios/generate-video/record.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/zsxq/SKILL.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

知识星球操作指南（CLI / MCP 双通道）

本 Skill 覆盖通过 zsxq-cli（CLI 通道）或底层接口工具 call_zsxq_api（MCP 通道）操作知识星球的所有场景：认证、星球管理、主题管理、用户信息、笔记管理，以及 Skill Pay 微信支付。

默认假设 zsxq-cli 已安装且已登录，无需每次主动检查。只在命令执行报错时才按需处理（见 references/auth-errors.md）。

本 Skill 所有示例中的 ID、订单号、支付码等标识均为模拟数据，不对应真实资源。执行操作时必须通过查询结果或用户输入取得并核对真实标识，不得直接复用示例值。

执行通道

本 Skill 的所有能力有两条执行通道，先判定通道再路由：

宿主可执行 zsxq-cli → CLI 通道（优先；shortcut 有参数校验与本地编排，行为最可控）
否则宿主工具列表中存在 call_zsxq_api → MCP 通道
两者都没有 → 停止并提醒用户：安装 CLI（见 references/auth-errors.md）或在宿主中接入知识星球 MCP（密钥管理页创建 api-key 后复制链接接入），由用户选择

通道判定是一次性环境探测；选定后一致使用，不混用。仅当某操作标注「仅 CLI 通道」/「仅 MCP 通道」时，对该操作单独切换或告知用户。
MCP 通道下所有调用都通过底层接口工具 call_zsxq_api（参数 {method, path, query?, body?}）；不得臆造未文档化的 method/path——能力底表见 references/endpoint-catalog.md，未覆盖即视为不支持。
「执行模式」路由（场景 → 原子 → 探索）在两条通道下相同；通道只决定各 reference「## 命令」节使用哪一组调用块。

执行模式

按以下顺序路由用户请求，命中即执行，不再往下走：

场景模式 — 请求命中已注册场景：读场景入口文档，按流程编排原子操作
原子操作 — 请求明确对应一个常用操作：读对应 reference，直接调用推荐命令
探索模式 — 都未命中：按 references/cli-exploration.md 通过 CLI 帮助和 API 列表发现能力

原子操作和场景执行时不得预先运行无关的 doctor、--help 或 api list。仅在能力不匹配或调用失败时回退到探索模式。

快速索引

根据用户意图，直接跳转到对应小节或 reference：

用户想要…	去哪看
登录 / 查看登录状态 / 排查认证或 HTTP 错误	→ `references/auth-errors.md`
每日巡场：查今天需要关注/处理的新内容	→ `scenarios/daily-patrol.md`
整理评论区、找未回复评论并起草回复	→ `scenarios/triage-comments.md`
处理别人向我提的、还没回答的问题	→ `scenarios/manage-inbound-questions.md`
整理精华与标签（加精 / 打标签建议）	→ `scenarios/curate-digest-and-tags.md`
生成运营日报 / 周报 / 复盘	→ `scenarios/compose-operations-report.md`
把星球内容做成日报海报图片（PNG）	→ `scenarios/generate-daily-poster.md`
把星球帖子做成竖版动画视频（MP4）	→ `scenarios/generate-video.md`
巡查监控负面 / 风险内容	→ `scenarios/monitor-risky-content.md`
按给定标签批量给主题打标	→ `scenarios/batch-tag-topics.md`
到期成员续费关怀（识别即将到期成员、分层写话术）	→ `scenarios/care-expiring-members.md`
把最新主题批量收录进专栏	→ `scenarios/archive-topics-to-column.md`
问产品规则/功能/常见问题（退款、费率、开票、认证、审核、封禁…）	→ `references/scenarios/answer-product-docs.md`
检查/迁移/清理旧版 zsxq skill	→ `references/scenarios/migrate-legacy-skills.md`
使用 Skill Pay 付费加入 / 续期 / 购买 / 付费提问 / 赞赏	→ `references/scenarios/purchase-with-skill-pay.md`
创建知识星球微信订单 / 处理支付挑战与安全恢复	→ `references/wechat-order-create.md`
查询加入、礼品卡、续费、轻读或星球邀请码价格	→ `references/wechat-order-create.md#下单前查询价格`
直接调底层 API / 探索未封装能力	→ `references/cli-exploration.md`
拼接知识星球分享链接	→ `references/share-links.md`
了解安全规则（写入/删除确认）	→ 安全规则
列出我加入的星球 / 获取 group_id	→ `references/group-list.md`
修改星球名称 / 简介 / 背景图 / 亮点图	→ `references/group-settings.md`
浏览星球内最新主题	→ `references/group-topics.md`
查看星球标签	→ `references/group-hashtags.md`
在星球内搜索内容	→ `references/topic-search.md`
把星球内搜索结果做成 AI 总结	→ `scenarios/summarize-search-results.md`
查看帖子详情	→ `references/topic-detail.md`
发帖（普通 / 投票 / 提问 / 关联打卡任务 / markdown / AI 声明）	→ `references/topic-create.md`
查询星球打卡任务 / 获取 checkin_id	→ `references/group-checkins.md`
编辑帖子	→ `references/topic-edit.md`
评论 / 楼中楼回复	→ `references/topic-reply.md`
回答提问（立即 / 定时 / 静默）	→ `references/topic-answer.md`
删除主题	→ `references/topic-delete.md`
定时发布主题 / 修改或取消定时任务	→ `references/topic-schedule.md`
查看待执行的定时任务与配额	→ `references/topic-scheduled.md`
设为精华 / 置顶（星主）	→ `references/topic-set.md`
取消精华（底层接口 api call）	→ `references/topic-digest.md`
给主题设置标签	→ `references/topic-tags.md`
读取 / 设置主题所属专栏（收录到专栏）	→ `references/topic-attached-columns.md`
查看自己的用户信息	→ `references/user-info.md`
查看自己发过的帖子（跨星球）	→ `references/user-footprints.md`
提交 NPS 反馈	→ `references/user-nps.md`
创建/查看/编辑/删除笔记	→ `references/note-create.md` 等
写入前需要确认哪些事项	→ 对应 reference 的 `> [!CAUTION]` 块 + 安全规则

Read the full file on GitHub · 257 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday Changed · +2 lines · +11 tokens per session 4a121ffeae34
17d ago Changed · +2 lines · +26 tokens per session 2c2f1c2fbdd2
1mo ago Changed · +12 lines · +9 tokens per session fe08bb88af9b
1mo ago Changed · +2 lines · +83 tokens per session cfe91931c35c
2mo ago First seen · 239 lines · 424 tokens per session scan A 38c5376cdd23

Subscribe to this mod's changes

zsxq is a skill published in the GitHub repository unnoo/zsxq-skill (323 stars, last pushed yesterday), licensed MIT. It adds 553 tokens to every session and 6,554 once invoked, about $0.0022 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

zsxq next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
zsxqunnoo/zsxq-skill	Skill	323	yesterday	MIT	A	553	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code