跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
营销与销售

audit

Use when the user wants a complete, whole-site audit that combines search visibility, front-end defects, and design quality in one pass, the deterministic scan alone, or a design engineering review of code they paste. Runs all 15 specialist sub-agents across SEO, accessibility/interaction/layout/code defects, and UX/visual/motion/content design, then merges them into one scored report with a prioritized action plan. Its pre-pass computes the objective checks and runs the 48 rules of the rules engine, with no sub-agent and no model: missing focus rings, clipped dropdowns, bad z-index, placeholder-as-label, missing reduced-motion. Use for: 'audit my whole site', 'complete site audit', 'full website review', 'audit everything', 'is my site good', 'review my site end to end', 'check for anti-patterns', 'scan my code', 'review before I ship', 'critique my code'. For a search-only audit use /seo audit; to see the page in a browser use /siteasy preview; for design-only use /siteasy audit.

MariusYvard · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add MariusYvard/NullToHero --skill audit

技能说明


name: audit description: "Use when the user wants a complete, whole-site audit that combines search visibility, front-end defects, and design quality in one pass, the deterministic scan alone, or a design engineering review of code they paste. Runs all 15 specialist sub-agents across SEO, accessibility/interaction/layout/code defects, and UX/visual/motion/content design, then merges them into one scored report with a prioritized action plan. Its pre-pass computes the objective checks and runs the 48 rules of the rules engine, with no sub-agent and no model: missing focus rings, clipped dropdowns, bad z-index, placeholder-as-label, missing reduced-motion. Use for: 'audit my whole site', 'complete site audit', 'full website review', 'audit everything', 'is my site good', 'review my site end to end', 'check for anti-patterns', 'scan my code', 'review before I ship', 'critique my code'. For a search-only audit use /seo audit; to see the page in a browser use /siteasy preview; for design-only use /siteasy audit." version: 4.0.0 user-invocable: true argument-hint: "[url] | full [url] [seo|defects|design|quick] | [verify|checks] [url] | review [target] | [report|learnings] [file] | compare [A] [B]" allowed-tools:

  • Read
  • Write
  • WebFetch
  • Glob
  • Grep
  • Task
  • Bash(node *)
  • Bash(python3 *)

Complete-audit toolkit for websites. One pass that orchestrates the plugin's three other skills (/seo, /inspect, /siteasy), dispatches all 15 specialist sub-agents across search visibility, front-end defects, and design quality, then merges their scored sections into a single Site Health Score with a prioritized action plan. The audit skill owns no detection logic of its own. It schedules the existing sub-agents, shares one fetch across them, and consolidates the results.

Commands

CommandWhat it doesReference
full [url] [scope]All 15 sub-agents across SEO, defects, and design; unified report + action plan. Optional scope runs one group: seo (5 SEO sub-agents), defects (4 inspect), design (6 siteasy), quick (one per group for a fast triage)references/full.md + references/refine.md
checks [url]Deterministic pre-pass only: the computed checks and the 48 rules of the rules engine, plus SITE-AUDIT.json, no sub-agentsreferences/checks.md + references/rules-engine.md
review [target]Design engineering code review of a file or a paste: motion crimes, accessibility violations, forbidden patterns, a Before/After table with a score, plus code robustness across security, performance and correctnessreferences/review.md + references/code-quality.md
verify [url]Consensus re-check: re-runs the gating dimensions (a11y, interaction, technical) K times and reconciles them by majority votereferences/full.md
compare [A] [B]Diff two targets (before/after a site, or A vs B): per-check verdict changes and score deltasreferences/compare.md
learnings [file]Review LEARNINGS.md candidates accumulated by real audits and turn accepted ones into rules, gates, laws or fixturesreferences/learnings.md
report [file]Format an existing audit into a client-ready report, a self-contained HTML page, or PDFreferences/report.md + references/html-report.md

Six commands, six references. The agent run scopes (full and its group scopes seo, defects, design, quick) share the orchestration playbook in references/full.md and differ only in which agent group is dispatched; the legacy first-token form (/audit seo [url]) remains accepted and routes to full with that scope. verify additionally re-runs the gating dimensions and reconciles them by majority vote. checks runs the deterministic pre-pass with no sub-agents and is documented in references/checks.md; it is also the ground-truth layer the agent modes consume in their fetch phase. compare diffs two targets (references/compare.md) and report formats an already-produced audit (references/report.md).

How to run a command

When the user invokes a command:

  1. Read the matching reference file with the Read tool (full.md for the agent run modes, checks.md for the deterministic pre-pass, compare.md for compare, report.md for formatting).
  2. Follow the instructions in that reference exactly. Do not improvise scoring weights or skip a dimension.
  3. If no command is specified:
    • With a URL, the bare invocation runs full against that URL.
    • A bare scope token (seo, defects, design, quick) as the first argument runs full with that scope; legacy names in tools/data/intents.csv route to their canonical command.
    • With no URL, ask the user for the site URL before dispatching any agent.

Relationship to the other skills

The three audit groups map one-to-one onto the plugin's three other skills and reuse their sub-agents directly. There is a single source of truth per dimension and no duplicated detection logic. The audit skill changes only the scheduling (parallel, shared fetch) and the consolidation (one merged report).

GroupBacking skillSub-agents reused
Search visibility/seo (see /seo audit)seo-agent-technical, seo-agent-content, seo-agent-schema, seo-agent-performance, seo-agent-geo
Front-end defects/inspect (detect, review)inspect-agent-a11y, inspect-agent-interaction, inspect-agent-layout, inspect-agent-code
Design quality/siteasy (see /siteasy audit)siteasy-agent-ux, siteasy-agent-visual, siteasy-agent-motion, siteasy-agent-content
阅读完整来源 ↗