Agent skill · Audited from source
seo-audit-full
skill · jeffli1993/seo-audit-skillMIT licenceAudited 21 Oct 2026 · source beca7a5818b6
Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit beca7a5818b6 and observed network access and no hard-coded secrets. The audit raised 1 finding, 1 critical or high. What it does: Advanced full SEO audit skill. Runs its own full workflow from local scripts, including the basic SEO checks plus PageSpeed, social metadata, and advanced review modules when available.
Cite
Cite this page
ModelsAtlas. “seo-audit-full (jeffli1993/seo-audit-skill)”. Retrieved 21 Oct 2026. https://modelsatlas.com/skills/jeffli1993/seo-audit-full
Trust audit
Audit 0.4.1 · source read 21 Oct 2026
CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 13,985 of 14,816 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkDeclared5 observations
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | PASS | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | FAIL | 1 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (1)
HIGHPrompt injectionprompt.credential_read · SKILL.md:52
Open "Acquiring and using an API key" → "Get a Key".
- Why
- asks the agent to read credentials
- Fix
- —
Audit 0.4.1 · source sha beca7a5818b6 · 21 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisherjeffli1993 GitHub userOwner of the repository this skill is read from
- Source folderjeffli1993/seo-audit-skill/seo-audit-fullThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdictbeca7a5818b6A new audit runs when the source changes
- Repository statusNot archivedLast push 125 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Advanced full SEO audit skill. Runs its own full workflow from local scripts, including the basic SEO checks plus PageSpeed, social metadata, and advanced review modules when available.
---
name: seo-audit-full
description: >-
Advanced full SEO audit skill. Runs its own full workflow from local scripts,
including the basic SEO checks plus PageSpeed, social metadata, and advanced
review modules when available.
metadata:
author: Jeff
version: "2.1"
---
# seo-audit-full — Advanced Full SEO Audit
This skill runs a full single-page SEO audit from the `seo-audit-full` directory.
It does not route to `seo-audit` when only a URL is provided.
---
## When to Use This Skill
Use `seo-audit-full` when the user asks for:
- "seo-audit-full"
- "full SEO audit"
- "advanced SEO audit"
- "technical SEO audit"
- "deep audit"
- "comprehensive SEO review"
- "audit everything"
URL-only requests are valid. When external datasets are not supplied, run the
full public-signal workflow and clearly note missing data sources in the report.
---
## Input Expected
| Input | Required | Notes |
|-------|----------|-------|
| Page URL | Yes | The primary page to audit |
| Primary keyword | Recommended | Improves content relevance scoring |
| PageSpeed API key | Yes | Required for full audit PageSpeed checks. Ask at the start and do not run PageSpeed without it. |
| Raw HTML or page content | Optional | Enables more accurate content checks when supplied |
| GSC / crawl / analytics data | Optional | Include when supplied, otherwise mark unavailable |
| Competitor benchmark data | Optional | Include when supplied |
At the start of a full audit, ask the user for a PageSpeed Insights API key:
```
For PageSpeed checks, please provide a Google PageSpeed Insights API key.
Get one here: https://developers.google.com/speed/docs/insights/v5/get-started
Open "Acquiring and using an API key" → "Get a Key".
If you do not provide one, I will stop before running the full audit because
PageSpeed is a required full-audit module.
```
Do not run `seo-audit-full` PageSpeed checks without a PageSpeed API key supplied
by `--api-key`, `PAGESPEED_API_KEY`, or `GOOGLE_PAGESPEED_API_KEY`. If the key is
missing, stop and ask the user to configure it instead of rendering a full report
with missing PageSpeed data.
---
## Architecture: Full = Core + Performance + Advanced
```
┌─────────────────────────────────────────────────────────────┐
│ seo-audit-full Workflow │
│ │
│ Phase 1: Run core scripts (./scripts/) │
│ ┌──────────────────────────────────────────────────────┐ │
│ │ check-site.py → robots.txt, sitemap, 404, URL │ │
│ │ check-page.py → title, H1, meta desc, slug │ │
│ │ check-schema.py → JSON-LD validation │ │
│ │ fetch-page.py → raw HTML for analysis │ │
│ └──────────────────────────────────────────────────────┘ │
│ ↓ │
│ Phase 2: Run performance + full-only scripts (./scripts/) │
│ ┌──────────────────────────────────────────────────────┐ │
│ │ check-pagespeed.py → Lighthouse scores + metrics │ │
│ │ check-social.py → OG Tags + Twitter Card │ │
│ │ (more scripts added here as modules grow) │ │
│ └──────────────────────────────────────────────────────┘ │
│ ↓ │
│ Phase 3: LLM-only advanced checks │
│ ┌──────────────────────────────────────────────────────┐ │
│ │ E-E-A-T content quality scoring │ │
│ │ Duplicate content signals │ │
│ │ Anchor text quality assessment │ │
│ └──────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────────┘
```
---
## Output
Produce an **Advanced Full SEO Audit Report** by filling the template at
[assets/report-template.html](assets/report-template.html),
then **save it to a file — never print raw HTML to the terminal**.
**File naming:** `reports/<hostname>-<slug>-full-audit.html`
```
https://example.com/blog/best-tools → reports/example-com-blog-best-tools-full-audit.html
https://example.com/ → reports/example-com-full-audit.html
```
**After saving, tell the user:**
```
✅ Full Report saved → reports/example-com-full-audit.html
Open it now? (yes / no)
```
If yes → run: `open reports/example-com-full-audit.html`
**Template placeholders** — fill each independently:
| Placeholder | Content |
|---|---|
| `{{summary_verdict}}` | One sentence: total checks run, how many failed/warned/passed |
| `{{summary_critical_html}}` | `<li>` per critical item, or `<li class="summary-empty">None</li>` |
| `{{summary_warnings_html}}` | `<li>` per warning item, or `<li class="summary-empty">None</li>` |
| `{{summary_passing_html}}` | `<li>` per passing check, or `<li class="summary-empty">None</li>` |
| `{{pagespeed_checks_html}}` | Full PageSpeed module using `check-pagespeed.py` output |
| `{{site_checks_html}}` | Site-level check tables |
| `{{eeat_checks_html}}` | E-E-A-T trust page table |
| `{{page_checks_html}}` | Page-level check tables, including full-only additions |
| `{{priority_actions_html}}` | Ordered priority action list |
| `{{insights_html}}` | Optional finding walkthrough cards |
---
## Scripts
Run full scripts from this directory. All output is structured JSON — use it
directly as evidence.
**Dependencies:** `pip install requests`
### Phase 1: Core scripts
```bash
# 1. site-level checks (robots.txt + sitemap.xml + 404 + URL canonicalization)
python scripts/check-site.py https://example.com
# 2. page-level checks (H1, title, meta description, canonical, URL slug)
python scripts/check-page.py https://example.com --keyword "primary keyword"
# 3. fetch raw HTML for downstream scripts
python scripts/fetch-page.py https://example.com --output /tmp/page.html
# 4. JSON-LD schema validation
python scripts/check-schema.py --file /tmp/page.htmExcerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit beca7a5
git clone https://github.com/jeffli1993/seo-audit-skill git -C seo-audit-skill checkout beca7a5818b6
The author documents no install command, so this uses the repository directly. Our verdict covers commit beca7a5818b6 only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- !CAUTION B 89 / 100
first audit · source
beca7a5818b6
Similar skills
obra/superpowers
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions…
obra/superpowers
Use when you have a spec or requirements for a multi-step task, before touching code
obra/superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
Questions about seo-audit-full
What does the seo-audit-full skill do?
Is seo-audit-full safe to install?
What can seo-audit-full access on my machine?
How current is this page?
Sources
- github.com/jeffli1993/seo-audit-skill/tree/main/seo-audit-full — the audited source at commit beca7a5818b6 and every finding aboveObserved · 21 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the seo-audit-full skill do?
- Is seo-audit-full safe to install?
- What can seo-audit-full access on my machine?