seo-flow

FLOW framework integration: evidence-led SEO using the Find → Leverage → Optimize → Win loop. Surfaces stage-specific AI prompts from the FLOW knowledge base (41 prompts, CC BY 4.0). Use when user says "FLOW", "FLOW framework", "seo flow", "evidence-led SEO", "find leverage optimize win", or wants stage-specific SEO prompts.

Quality

87%

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

Quality

Content

85%

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

The body is a tightly organized orchestration hub: actionable file paths and commands, clear per-command workflows with error-recovery feedback loops, and exemplary progressive disclosure pointing to a verified 41-prompt bundle. Its only weakness is mild redundancy between the orchestration sections and the standalone Reference Files block.

Suggestions

Fold the standalone "Reference Files" section into the orchestration blocks or trim it to just the on-demand rule, since each path and load condition is already stated per sub-command.

State the CC BY 4.0 attribution once (in the Attribution section) rather than also previewing it in the runtime-context note.

Add an inline validation checkpoint in the `/seo flow sync` workflow (e.g., verify the JSON summary shows no errors before showing the attribution) to match the batch-operation feedback-loop pattern used elsewhere.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with no concept padding, but the standalone "Reference Files" section restates paths and load conditions already embedded in each orchestration block, and the attribution is stated twice (runtime note and dedicated block), so it could be tightened.	2 / 3
Actionability	Gives concrete, executable guidance: exact reference paths to read, the literal command `claude-seo run sync_flow.py`, specific cross-reference command strings (`/seo cluster <seed-keyword>`), and concrete selection rules for the optimize stage.	3 / 3
Workflow Clarity	Each sub-command has a clear numbered sequence, the Error Handling table supplies explicit feedback loops for recovery (network/auth failures, missing files), and the optimize stage requires a justification checkpoint ("State which prompts you chose and why").	3 / 3
Progressive Disclosure	SKILL.md is a concise overview pointing to one-level-deep real references (flow-framework.md, bibliography.md, prompts/README.md, and verified per-stage prompt directories totaling 41), with an explicit on-demand loading discipline ("Load on-demand, do NOT load all at startup").	3 / 3
	Total	11 / 12 Passed

Description

90%

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 well-constructed description that clearly states the skill's purpose and gives explicit, natural trigger guidance. It is only slightly limited on specificity, relying on one umbrella action rather than enumerating multiple concrete operations.

Dimension	Reasoning	Score
Specificity	Names the domain (evidence-led SEO) and a core action ("Surfaces stage-specific AI prompts from the FLOW knowledge base") with the Find→Leverage→Optimize→Win loop elaborated, but it rests on a single umbrella action rather than listing multiple distinct concrete operations, so it does not reach the multi-action anchor.	2 / 3
Completeness	Explicitly answers both what (FLOW integration surfacing stage-specific prompts) and when via a dedicated "Use when user says..." clause, hitting the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Provides good coverage of natural terms a user would actually say ("FLOW", "FLOW framework", "seo flow", "evidence-led SEO", "find leverage optimize win"), matching the strong-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	The branded FLOW/"seo flow" triggers carve a clear niche unlikely to fire for the wrong skill; the broad phrase "stage-specific SEO prompts" is a minor overlap risk but the primary triggers are distinctive.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 12 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: AgriciDaniel/claude-seo
Path: skills/seo-flow/SKILL.md
Commit: 09d37c7

Reviewed: 4 days 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.