跳到正文
cccskills
免费在 GitHub 公开

scan-usr

Use when: analysing a project's user-facing health — discoverability, documentation, and product clarity.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md2.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

User Perspective (USR)

Evaluates how well the project communicates its purpose and value to users, contributors, and integrators. Assigns a score from 0.0 to 1.0 across three dimensions.

Dimensions

README quality — Can someone discover and use this project?

  • Missing README = 0.0
  • Score = min(readmeLength / 2000, 1.0) — 2000+ chars = full score
  • A thin README (<500 chars) generates a high-priority task

Description — Is the package self-describing?

  • If no package.json exists, marked N/A (not applicable to non-npm projects)
  • If package.json exists: non-empty description field = 1.0, missing or empty = 0.0

Changelog — Is the release history communicated?

  • CHANGELOG.md or CHANGELOG present = 1.0
  • Missing = 0.5 (partial credit — not critical)

Scoring

usr_score = (readme + description + changelog) / 3

Score interpretation:

  • 0.9–1.0 Well-documented and discoverable
  • 0.7–0.9 Good documentation with minor gaps
  • 0.5–0.7 Documentation is present but thin — a new user would struggle
  • 0.0–0.5 Project is effectively undiscoverable — documentation is a blocker

Tasks Generated

FindingPriority
No README.mdcritical
README < 500 charshigh
No package.json description (when package.json exists)medium

Agent Analysis Guide

When performing a manual USR analysis:

  1. Read the README as if you are a new user — can you answer: what is this, how do I install it, how do I use it?
  2. Check for usage examples with real commands or code snippets (not just API reference)
  3. If package.json exists: verify the description field accurately describes what the package does in one line; if no package.json, mark this dimension N/A
  4. Check if there is a CHANGELOG and whether it lists breaking changes for major versions
  5. Look for a CONTRIBUTING.md — if contributors cannot find setup instructions they cannot help
  6. Assess any public API surface: are types and parameters documented?
  7. Identify anything a user would need to know that is not in the docs

Output: gaps in user-facing documentation ranked by impact on onboarding friction, with specific sections or files that need to be written or expanded.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Universal guardrails loaded by every agent. Defines Verify Before Reporting (VBR), Write-Ahead Log (WAL), and the security baseline. Always-on, role-independent.

中文简介正在准备中。当前显示原文说明。

Agistra/agistra.dev52026年10月19日 更新

Use when: architecture mode, architect this, ADR, C4, PlantUML, system boundary, design decision, PRD gap, high ambiguity, multiple technical approaches, security architecture, data architecture, integration risk, implementability gap, story ticket, or epic ticket.

中文简介正在准备中。当前显示原文说明。

Agistra/agistra.dev52026年10月19日 更新

Use when: assumptions audit, audit assumptions, check for hidden assumptions, plan/ticket has ambiguous scope edges, pre-flight before finalizing a ticket, unstated assumptions, or 'what am I assuming'. Surfaces unstated assumptions, ambiguous scope edges, and untested preconditions in a finished plan/ticket/ADR before it is handed to Builder. Optional pass — Architect judges when to apply it; not a mandatory gate on every ticket.

中文简介正在准备中。当前显示原文说明。

Agistra/agistra.dev52026年10月19日 更新

Use when: Tester needs UI state evidence for VBR, or Builder needs to verify an integration wire is observable end-to-end. Powered by agent-browser MCP — token-efficient browser automation (200–400 tokens/page).

中文简介正在准备中。当前显示原文说明。

Agistra/agistra.dev52026年10月19日 更新

Use when drafting a bug or defect ticket, reviewing one someone else wrote, or deciding whether a reported problem is ready to file. Keeps what the reporter actually saw separate from what the agent later found out, so a reader can tell which lines are testimony and which are collected proof. Trigger phrases: 'file a bug', 'write up this defect', 'triage this report', 'is this ticket ready to file', 'what did the reporter actually see'.

中文简介正在准备中。当前显示原文说明。

Agistra/agistra.dev52026年10月19日 更新

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

中文简介正在准备中。当前显示原文说明。

Agistra/agistra.dev52026年10月19日 更新

查看 Agistra 的全部技能

报告此技能的问题