blog-cluster

Semantic topic cluster planning and automated execution engine for claude-blog. Performs SERP-based keyword research, groups keywords by search intent and SERP overlap, builds a hub-and-spoke cluster architecture, generates an interactive SVG cluster map, and executes the full cluster by orchestrating blog-write calls with shared cluster context and automatic internal-link injection. Fills the strategy-to-execution gap: blog-strategy plans the blueprint, blog-cluster builds the house. Use when user says "blog cluster", "topic cluster", "content cluster", "cluster plan", "cluster execute", "pillar content", "hub and spoke", "content ecosystem", "cluster map".

Quality

92%

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%Weight 40%Scale 1-5

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

A well-structured, highly actionable orchestration skill with clear multi-phase workflows, validation checkpoints for a batch operation, and proper progressive disclosure into three real reference files. The main weakness is redundancy — several tables restate material already covered inline.

Suggestions

Remove the 'Output Artifacts (summary)' table; it restates the file/phase/format information already given in Plan Step 5 and the Execute Phase steps.

Consolidate the Quality Gates and Error Handling tables with their corresponding inline steps so failure behavior is stated once rather than in three places.

Move the provenance block ('Adapted from the semantic-cluster-engine submission...') to the repo README or a comment; it documents origin rather than guiding execution and adds context-window cost.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient task-specific guidance, but it restates the same information in several places — the 'Output Artifacts (summary)' table duplicates Plan Step 5, and Quality Gates / Error Handling overlap with the inline Execute steps — so it could be tightened.	3 / 5
Actionability	Concrete, executable guidance throughout: real commands (`/blog cluster plan <seed-keyword>`), a complete `cluster-plan.json` schema, an XSS-safe HTML/SVG rule set, a deterministic execution-order formula, and explicit file-path and slug constraints.	5 / 5
Workflow Clarity	Plan (6 steps) and Execute (8 steps) phases are clearly numbered with explicit validation checkpoints — JSON validation on plan load, user confirmation before execution, stop-on-quality-failure, and resume logic — plus checklist-style Quality Gates and Error Handling tables for a batch operation.	5 / 5
Progressive Disclosure	A 'Key references (load on demand)' section points to three real one-level-deep bundle files (semantic-clustering.md, cluster-architecture.md, execution-workflow.md, all present in ./references/), keeping the SKILL.md an overview while detailed methodology lives in the references.	5 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

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

An exemplar description: third-person voice, concrete multi-action capability list, comprehensive natural trigger phrases, and an explicit differentiation from the upstream blog-strategy skill. No vague fluff or over-claims; every clause earns its place.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Performs SERP-based keyword research', 'groups keywords by search intent and SERP overlap', 'builds a hub-and-spoke cluster architecture', 'generates an interactive SVG cluster map', 'orchestrating blog-write calls with shared cluster context and automatic internal-link injection' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (semantic cluster planning + automated execution engine with the listed actions) and 'when' (the 'Use when user says...' trigger clause), so neither half is missing or only implied.	5 / 5
Trigger Term Quality	The 'Use when user says' clause supplies nine natural trigger phrases including synonyms and variants ('blog cluster', 'topic cluster', 'content cluster', 'pillar content', 'hub and spoke', 'content ecosystem', 'cluster map'), covering what a user would actually say.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche — 'Fills the strategy-to-execution gap: blog-strategy plans the blueprint, blog-cluster builds the house' — with cluster-specific triggers that minimize overlap with sibling claude-blog skills.	5 / 5
	Total	20 / 20 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
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: AgriciDaniel/claude-blog
Path: skills/blog-cluster/SKILL.md
Commit: 84f7abf

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.