AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Skill Account Diagnosis

skill-zju-real-easel-skill-account-diagnosis · by ZJU-REAL

账号诊断/起号体检:读取已完善的画像 Profile + 近期内容数据,诊断垂直度、定位清晰度、限流降权信号、流量池阶段,给出病因→证据→处方式的起号意见与发布建议。当用户说账号诊断/起号体检/为什么没流量/是不是被限流了/账号定位诊断/起号建议/怎么起号时使用

No reviews yet
0 installs
0 views
view→install

Install

$ agentstack add skill-zju-real-easel-skill-account-diagnosis

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-zju-real-easel-skill-account-diagnosis)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Skill Account Diagnosis? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

账号诊断 / 起号体检

> 对着一个具体账号做归因式体检并开处方。读 [profile-builder](../skill-profile-builder/SKILL.md) 生成的画像 + 用户近期内容/数据 → 诊断账号健康 → 给分阶段起号意见与发布建议。与画像强相关:没有完善的 Profile 就先去跑 profile-builder。

前置条件

  • 必须有已完善的 Profile(profiles// 六维基本填好)。若 Profile 缺失或大面积 [待补充]先让用户跑 skill-profile-builder,不要在信息不全时硬诊断。

输入

| 项 | 必需 | 说明 | |----|------|------| | 画像名 | 是 | 指向 profiles// | | 近期内容数据 | 否 | 近 10-30 条内容的标题/题材/曝光/互动(有则诊断更准;无则基于 Profile + 追问) | | 具体困惑 | 否 | 如"播放上不去""是不是被限流了" |

输出

一份诊断报告 + 分阶段行动清单:

  1. 五维诊断(每维:现状 → 证据 → 结论),见 [diagnosis-framework.md](references/diagnosis-framework.md):

垂直度 / 定位清晰度 / 限流降权信号 / 流量池阶段 / 内容-受众匹配。

  1. 病因→证据→处方:每个问题都要三段式,不给空泛建议。
  2. 分阶段起号意见:按当前所处阶段(0-500 / 500-5k / 5k-1w / 1w+)给这一档该做什么。
  3. 发布建议:内容方向优先级、发布节奏、需要补强的能力(可指向下游 SKILL:选题→content-matrix、脚本→video-script、合规→quality-gate 等)。
  4. 信息缺口 → Plan:诊断依赖但缺失的信息(如没有近期数据),列成 plan 向用户提问,不要编造数据下结论。

执行步骤

  1. 读 Profile 六维(identity/style/audience/platforms/preferences/memory),评估完整度。缺口过大 → 建议先跑 profile-builder 并停止。
  2. 收集近期数据:有用户提供则用;没有则说明"缺数据会影响诊断精度",并在需要处追问(近期几条内容的题材与互动)。
  3. 逐维诊断:按 diagnosis-framework.md 的标尺给每一维打现状 + 找证据 + 下结论。限流信号按清单逐项自检。
  4. 判定流量池阶段:结合粉丝量级 + 近期互动率,定位当前档位。
  5. 开处方:把诊断出的问题按"病因→证据→处方"组织,处方要具体可执行(不是"多互动"这种废话)。
  6. 给分阶段动作清单:当前档 + 下一档的关键动作。
  7. 列信息缺口 plan:把不确定、需用户确认或补数据的点做成清单,交给用户回答后再细化。
  8. 回流建议:诊断中发现的可复用洞察,建议用户确认后写入 profiles//memory.md(本 SKILL 不自动改 Profile,只建议)。

Profile 感知

  • 有 Profile:全程以该画像的定位/风格/受众/红线为基准做诊断——垂直度是"离该定位有多远",而非通用标准。
  • Profile 不完整:先导向 profile-builder,不硬诊断。
  • 诊断结论只建议回写 memory,由用户确认,避免污染画像。

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.