036bc6a52e
Group G — markdown tech-debt cleanup (post-audit 2026-05-02).
- 36 SKILL.md files: added "## When to use" section. Was missing across the
catalog; orchestrator routing by keyword could not auto-dispatch.
- 20 code-implementer agent .md files: added Output Footer block prescribing
RULE 0.16 STATUS-TRUTH MARKER schema in agent's final report. Previously only
code-implementer-rust.md had it; other 27 language/role variants were silent
about the marker, breaking RULE 0.16 §3 status-truth aggregation for non-Rust
batches.
- skills/site-create/: added phase-5-preview.md and phase-6-deploy.md skeleton
files. SKILL.md table-of-contents referenced 7 phases; only 5 existed on disk.
- skills/{ai-animation,rag-pipeline}/skill.md: added migration banner comment
noting they should be SKILL.md (canonical filename). Case-rename via git is a
separate orchestrator task (macOS APFS is case-insensitive; Linux deploy needs
explicit rename).
- 3 deprecated skills (site-builder, competitor-analysis, design-inspiration):
added concrete removed-after dates (was vague "before v2").
- docs/CONVERGENCE-PLAN.md:129: TBD on _blocks/evidence-grading.md duplicate
resolved (file exists, not duplicated).
- docs/DNA-INDEX.md: count edits made then overwritten by auto-encyclopedia-refresh
hook during agent run. The .kei-registry-ignore files in test fixtures (Group F)
are the structural fix; kei-registry walker implementation is the follow-up.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
55 lines
2.1 KiB
Markdown
55 lines
2.1 KiB
Markdown
---
|
|
name: seo-audit
|
|
description: Use when auditing SEO — technical + content analysis via WebFetch and code inspection
|
|
arguments:
|
|
- name: url
|
|
description: URL or project path to audit
|
|
required: true
|
|
---
|
|
|
|
# SEO Audit Workflow
|
|
|
|
## When to use
|
|
|
|
- Auditing a live URL or project codebase for technical SEO issues (meta tags, canonical, sitemap, Core Web Vitals).
|
|
- Before launching a site or page to ensure discoverability and ranking fundamentals are in place.
|
|
- Generating a prioritised fix list covering both technical and content SEO signals.
|
|
|
|
## Step 1: Technical SEO
|
|
Fetch and analyze the page:
|
|
- **Meta tags:** title (<60 chars), description (<155 chars), viewport, robots
|
|
- **Headings:** proper H1-H6 hierarchy, single H1
|
|
- **URLs:** clean, descriptive, no query params for content pages
|
|
- **Canonical:** present and correct
|
|
- **Sitemap:** exists at /sitemap.xml
|
|
- **Robots.txt:** exists, not blocking important pages
|
|
- **HTTPS:** enforced, no mixed content
|
|
- **Mobile:** responsive meta tag, no horizontal scroll
|
|
|
|
## Step 2: Performance Impact
|
|
- Image optimization: format (WebP/AVIF), size, lazy loading, alt text
|
|
- Core Web Vitals indicators:
|
|
- LCP: largest element load time
|
|
- CLS: layout shift from images/fonts without dimensions
|
|
- FID/INP: heavy JS blocking interaction
|
|
- Bundle size check if applicable
|
|
|
|
## Step 3: Content SEO
|
|
- Keyword presence in: title, H1, first paragraph, URL
|
|
- Content length (>300 words for ranking)
|
|
- Internal links (to other pages on same domain)
|
|
- External links (to authoritative sources)
|
|
- Structured data (JSON-LD): Article, Product, FAQ, etc.
|
|
- Open Graph + Twitter Card meta tags
|
|
|
|
## Step 4: Issues Report
|
|
Format as prioritized list:
|
|
- **Critical:** blocks indexing or ranking (missing title, noindex, broken canonical)
|
|
- **Important:** significant ranking impact (no meta description, missing alt text, slow LCP)
|
|
- **Nice-to-have:** minor improvements (schema markup, additional links)
|
|
|
|
Each issue: what's wrong, where, how to fix, impact level.
|
|
|
|
## Step 5: Action Items
|
|
- Generate fix list ordered by impact
|
|
- For code changes: specific file + line + suggested edit
|