What does this skill do, and when should you use it?
seo-programmatic focuses specifically on programmatic SEO, not the full capability set of the Claude SEO repository. It assesses CSV, JSON, API, and database inputs, designs templates for genuinely distinct pages, and reviews URLs, internal links, canonicals, sitemaps, and index controls. Its quality gates cover uniqueness, word count, human review, rollout size, and page justification. It fits teams that need to publish many structured-data pages without treating scale alone as evidence of search value.
Evaluates CSV or JSON files, API responses, and database records for row counts, field uniqueness, missing values, freshness, and duplicate or near-duplicate records. Plans template variables for titles, H1s, body sections, meta descriptions, and schema, along with conditional sections and supplementary content. Designs URL patterns, hub-and-spoke linking, related-page links, breadcrumbs, and varied anchor text. Applies quality gates for unique-content percentage, page word count, review coverage, and publishing volume. Reviews self-referencing canonicals, parameter handling, pagination, faceted navigation, noindex decisions, XML sitemaps, and index-bloat controls. Produces a scored assessment with prioritized issues and recommendations.
- An SEO team is turning a product catalog into landing pages and needs to verify that each record contains enough unique information.
- A local-services site plans city-and-service pages and wants to detect templates that merely swap location names.
- A SaaS company is building integration pages and needs a structure for setup instructions, API details, and related links.
- A content operation is preparing hundreds of data-driven pages and needs review, batching, and indexing safeguards before launch.
- A technical SEO specialist is auditing an existing page set for canonicals, sitemap coverage, faceted URLs, and low-value records.
How do you install this skill?
- The 2025–2026 enforcement, policy, and 45% reduction claims are uncited in the skill file and should be verified individually before use.
- Hard-stop conditions, uniqueness-measurement scope, and rollout rules leave threshold interpretation open; they should not be treated as universal Google policy or guarantees.
- Before using APIs, databases, credentials, or bulk publishing, confirm permissions, data flows, privacy boundaries, human review, and recovery procedures separately.
- Chinese output and mainland-China network reachability are undocumented; validate availability when external SEO, Google, or crawling services are required.
- Network access
- Local filesystem
This skill is part of the 33-skill AgriciDaniel/claude-seo collection, and the source does not document a separate installation process. Install the collection with git clone --depth 1 https://github.com/AgriciDaniel/claude-seo.git, then run bash claude-seo/install.sh. The skill file is located at skills/seo-programmatic/SKILL.md. The repository is MIT-licensed.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/AgriciDaniel/claude-seo.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/seo-programmatic" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- pages at scale,
In a Claude Code environment with the collection installed, run /seo programmatic <url> for a programmatic SEO analysis. You can also ask for an audit or plan using phrases such as “programmatic SEO,” “pages at scale,” “dynamic pages,” or “data-driven SEO.” The documented argument is a URL or plan; the skill file does not specify a separate input protocol for supplying files or database credentials.
What are this skill's strengths and limitations?
- Covers the full planning chain from data quality and template design to indexing controls.
- Provides concrete thresholds for uniqueness, word count, review coverage, and publishing volume.
- Includes a hard-stop process for insufficient justification or very low content uniqueness.
- Works for both new programmatic SEO plans and audits of existing page sets.
- The skill file does not document a dedicated test suite, standalone scripts, or automatic execution commands.
- Results depend on accessible, sufficiently complete source data and pages; authentication details for APIs and databases are not specified.
- It does not provide its own crawler, keyword database, or external SEO-data integration.
- Some enforcement dates and policy context are presented as reference material and should be rechecked against current search-engine guidance.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Programmatic SEO Planner this page | 47 · Use with care | ★ 19k | 23d ago | MIT |
| Full-Site SEO Audit | 53 · Use with care | ★ 19k | 23d ago | MIT |
| Single-Page SEO Inspector | 51 · Use with care | ★ 19k | 23d ago | MIT |
| Site Structure Optimizer | 59 · Recommended | ★ 3k | 13d ago | Apache-2.0 |
| On-Page SEO Checker | 54 · Use with care | ★ 3k | 13d ago | Apache-2.0 |
How did FollowSkills review this skill?
The skill is primarily for SEO analysis and planning, and it includes unreachable-URL handling, quality gates, and user confirmation before hard stops. No malware, credential theft, or destructive default is shown; however, data flows, API/database permissions, sensitive-data handling, external publishing effects, and rollback are not specified, so points are deducted.
Data assessment, templates, URLs, linking, index management, and error handling are structured and conceptually actionable. However, there is no execution evidence for this skill path, the relationship among the 40%/30% uniqueness thresholds and other gates is not fully clear, and failure feedback for real inputs and dependency failures is limited; the score is also constrained by static calibration.
Trigger phrases, input forms (URL or plan), and primary scenarios are reasonably clear. Non-fit boundaries, output contracts, false-trigger boundaries, and Chinese-language support are not defined. Core use does not entirely depend on overseas services, but assumptions around APIs, databases, and URL access are insufficiently documented, so points are deducted.
The SKILL.md provides metadata, version 2.2.0, MIT licensing, layered sections, quality gates, an output structure, and error handling. It lacks skill-specific installation/dependency notes, examples, FAQs, changelog, maintenance ownership, and update path; publisher identity is also unverified by the stated registry, so points are deducted.
The skill covers data quality, template value, URLs, internal links, canonicals, sitemaps, and index-bloat controls, providing a useful audit checklist. It lacks a verifiable skill-specific output sample or actual artifact, and its thresholds and SEO-risk conclusions require human review. Static calibration therefore limits the score to 7 or below, with further deduction for incomplete proof of direct usability.
The skill makes several 2025–2026 policy and enforcement claims without citations, source references, or a reproducible calculation tool in the selected file. The repository supplies general CI and tests, but the provided tests do not cover this skill's key paths, so only limited auditability is credited.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →