programmatic-seo-spy

Reverse-engineer how competitors do programmatic SEO. Detects URL pattern clusters (vs/, integrations/, for-{industry}/), estimates page count per pattern, analyzes template quality, infers which patterns actually drive traffic, and identifies gaps you can exploit. Outputs a competitive pSEO landscape report.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/seo/composites/programmatic-seo-spy/SKILL.md

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-sequenced, largely actionable workflow with concrete commands and a thorough output template, undermined by duplicated trigger lists, a placeholder fetch step, and the absence of validation checkpoints in a batch operation.

Suggestions

Remove the duplicate 'Trigger Phrases' section (or merge it into 'When to Use') to cut redundancy.

Replace the Phase 4 placeholder comment with an actual fetch_webpage command and add explicit validation checkpoints (e.g., verify the sitemap crawl returned URLs before pattern detection).

Move the full output template into a referenced file (e.g. references/report-template.md) so SKILL.md stays a lean overview, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Most content earns its place (regex pattern table, classification scheme, quality dimensions, output template), but there is redundancy — the 'Trigger Phrases' section near-duplicates 'When to Use' — and verbose blocks like the full 'Agent Prompt to User' quote that could be tightened; not a 3.	2 / 3
Actionability	It gives concrete, runnable commands (catalog_content.py invocation, a DataForSEO POST example) and a copy-paste output template, but Phase 4's fetch step is only a comment placeholder ('# Pick pages from the pattern') and several phases describe rather than instruct, leaving it incomplete.	2 / 3
Workflow Clarity	The phase sequence (Phase 0 Intake through Phase 6 Output) is clearly laid out, but this batch operation across multiple competitors has no explicit validation or verification checkpoints, which the rubric caps at 2.	2 / 3
Progressive Disclosure	No bundle files exist and all content is inline in a ~280-line monolithic SKILL.md; it is well organized into phases, but large blocks like the 50-line output template could be split into a referenced file, so it is not a fully split, one-level-deep structure.	2 / 3
	Total	8 / 12 Passed

Description

72%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, well-targeted description that clearly names the capability and its niche, but it lacks an explicit 'Use when...' trigger clause and slips into second person ('you can exploit'), which costs it specificity points.

Suggestions

Add an explicit trigger clause, e.g. 'Use when analyzing competitor programmatic SEO, reverse-engineering their URL patterns, or finding pSEO gaps to exploit.'

Rephrase 'identifies gaps you can exploit' in third person (e.g. 'identifies exploitable gaps') to avoid the second-person specificity penalty.

Expand trigger terms with common variants like 'comparison pages', 'integration pages', or 'competitor URL structure'.

Dimension	Reasoning	Score
Specificity	It lists multiple concrete actions ('Detects URL pattern clusters (vs/, integrations/, for-{industry}/)', 'estimates page count per pattern', 'analyzes template quality'), which would rate a 3, but the phrase 'identifies gaps you can exploit' uses second person ('you'), triggering the rubric's one-point specificity penalty.	2 / 3
Completeness	It thoroughly answers 'what' (reverse-engineer, detect, estimate, analyze, identify, output) but contains no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 2.	2 / 3
Trigger Term Quality	Natural terms users would say are well covered — 'programmatic SEO', 'competitors', 'pSEO', 'URL pattern', 'competitor SEO' — giving good coverage of the phrasings a user would naturally invoke.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply defined — programmatic SEO competitor reverse-engineering with specific URL-pattern clusters — making it unlikely to trigger for unrelated SEO or general analysis skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/seo/composites/programmatic-seo-spy/SKILL.md
Commit: 8866b2a

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.