seo-programmatic
An agent skill by AgriciDaniel, from AgriciDaniel/claude-seo. Tags: architecture, automation, development, seo, validation.
What it does
Programmatic SEO planning and analysis for pages generated at scale from data sources. Covers template engines, URL patterns, internal linking automation, thin content safeguards, and index bloat prevention. Use when user says "programmatic SEO", "pages at scale", "dynamic pages", "template pages", "generated pages", or "data-driven SEO".
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add AgriciDaniel/claude-seo --skill seo-programmaticOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/AgriciDaniel/claude-seo
cp -r claude-seo/skills/seo-programmatic ~/.claude/skills/seo-programmaticSafety box score
Grade B, low risk: 14 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This is a documentation-only SEO analysis/planning skill; it ships no executable code in the reviewed files. The main exposure is that it may inspect user-provided URLs, CSV/JSON, or database data, and it references an external plugin command that is not included here.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 1 (low) | The skill documents a command to run an external executable: `"${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo" run metadata_template.py --pairs-file <file> --json`, so using it may execute out-of-repo code. |
| Network access | 1 (low) | It is built to evaluate `API endpoints` and handle `URL unreachable` cases, so it can send requests to user-supplied remote hosts during analysis. |
| Filesystem reach | 1 (low) | It explicitly covers local `CSV/JSON files` and `Database queries`, so it may read structured data from files or data sources the user points it at. |
| Secrets & credentials | 0 (none) | There is no instruction to access tokens, passwords, keychains, `.env` files, or browser sessions. |
| Privilege & persistence | 0 (none) | No sudo, service registration, global installs, or shell/OS configuration changes are described. |
| Instruction hijack surface | 0 (none) | The file contains guardrails like `require explicit user approval` and `Halt analysis`, but no prompt-injection or hidden instructions to ignore higher-priority rules. |
| Irreversible actions | 0 (none) | It is an analysis/planning skill and does not itself post, deploy, pay, book, delete, or otherwise act externally. |
| Transparency | 1 (low) | It delegates to an external tool path (`${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo`) whose implementation is not included in the reviewed files. |
Before installing
- Inspect the installed `${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo` executable or source before letting the agent run the documented command.
- Try the skill first on a scratch URL or tiny sample CSV/JSON to confirm what outbound requests and file reads it performs.
- Treat the Google policy/date claims as time-sensitive and verify them against current official documentation if you rely on them.
Rated 2026-10-16 by an automated review of 2 files from the skill's repository.
Source
- Repository
- AgriciDaniel/claude-seo (all skills from this repository)
- Path
- skills/seo-programmatic/SKILL.md
- Branch
- main
- Collection
- claude-seo
- Updated
- 2026-09-21
Related skills
- principle-separate-before-serializing-shared-state — Apply when concurrent actors might write to the same file, branch, key, or state object.
- principle-type-system-discipline — Apply when designing types, reviewing a function signature, or writing code in any statically-typed language.
- seo — Comprehensive SEO analysis for any website or business type.
- seo-audit — Full website SEO audit with parallel subagent delegation.
- seo-content — Content quality and E-E-A-T analysis with AI citation readiness assessment.
- seo-drift — SEO drift monitoring: capture baselines of SEO-critical elements, detect changes, and track regressions over time.