blog

Full-lifecycle blog engine with 31 sub-skills, 12 content templates, 5-category 100-point scoring, and 5 specialized agents. Routes user requests to the right sub-skill: writing, rewriting, analysis, outlines, audits, schema, charts, images, repurposing, AI citation SEO, FLOW framework prompts, topic-cluster execution, and multilingual publishing. Optimized for Google rankings around the May 2026 Core Update, E-E-A-T, and AI citations as one SEO discipline. Supports any platform (WordPress, Next.js MDX, Hugo, Ghost, Astro, Jekyll, 11ty, Gatsby, HTML). Use when user says "blog", "write a blog", "blog post", "blog strategy", "content brief", "editorial calendar", "blog audit", "blog optimization", "topic cluster", "multilingual blog", "FLOW framework", or any /blog subcommand. Sub-skill descriptions cover narrower triggers.

Quality

88%

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

77%

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 well-structured orchestrator with strong actionability and an explicit gated workflow, but it is held back by inline-heavy security rationale and pervasive version/date noise that hurt conciseness and progressive disclosure.

Suggestions

Move the detailed Untrusted-Data Contract, nonce/CSPRNG mechanics, and Defense-class summary into a dedicated reference file (e.g. references/untrusted-context-contract.md) and keep only the trusted-helper invocation rule inline.

Strip per-feature version tags (v1.8.0, v1.9.0, v1.8.3, etc.) from inline prose, or consolidate them into a single changelog/deprecated section; they add time-sensitive noise that penalizes conciseness.

The orchestration-details.md pointer is repeated three times (Sub-Skills, Execution Flow, and Auto-loaded Project-Root Context); reference it once to remove redundancy.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with dense tables and copy-paste bash, but it carries repeated version tags (v1.8.0, v1.9.0, v1.8.3, v1.8.6, v1.7.0) and dated update names (May/March 2026) outside any deprecated section, plus an over-explained nonce/CSPRNG rationale; not a 3 because these tokens do not each earn their place, and not a 1 because the bulk is tight and assumes competence.	2 / 3
Actionability	Execution Flow provides fully executable bash with env-var fallbacks and absolute-path validation, the routing table maps every command to a concrete sub-skill, and Quality Gates give explicit thresholds — copy-paste ready and specific, matching the highest anchor.	3 / 3
Workflow Clarity	The 7-step Execution Flow includes an explicit validation checkpoint (5-gate preflight, check the BLOCKING line, loop back to Step 4, max 3 iterations, STOP on 3rd failure) — a clear feedback loop for a batch operation, matching the anchor for sequenced steps with validation and error recovery.	3 / 3
Progressive Disclosure	The 22 reference files are real, one-level-deep, and well-signaled with a descriptive listing, but the large inline Untrusted-Data Contract / nonce mechanics and Defense-class summary read like reference material that should be split out; not a 3 because content that belongs in a separate file is inlined, and not a 1 because navigation to the bundle is clear and shallow.	2 / 3
	Total	10 / 12 Passed

Description

100%

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

The description is specific, third-person, and pairs a strong what-clause with an explicit when-clause of natural trigger terms. It is distinguishable and unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — "writing, rewriting, analysis, outlines, audits, schema, charts, images, repurposing, AI citation SEO, FLOW prompts, topic clusters, and multilingual publishing" — matching the anchor for multiple specific concrete actions; third-person voice ("Routes requests", "Optimized for") is correct.	3 / 3
Completeness	Clearly answers both what ("Full-lifecycle blog engine with 31 sub-skills..." plus the action list) and when (an explicit "Use when..." clause), matching the anchor that requires both with explicit triggers.	3 / 3
Trigger Term Quality	Explicit "Use when user says 'blog', 'blog post', 'blog audit', 'topic cluster', 'multilingual blog', or any /blog subcommand" gives good coverage of natural terms a user would actually say, matching the highest anchor.	3 / 3
Distinctiveness Conflict Risk	A clear blog/content niche with distinct triggers ("blog", "blog post", "blog audit", "/blog subcommand") that are unlikely to fire for unrelated skills; not a 2 because the scope is narrowly bounded rather than overlapping.	3 / 3
	Total	12 / 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: 2 missing	Warning

	Total	14 / 16 Passed

Repository: AgriciDaniel/claude-blog
Path: brain/.raw/sources/claude-blog-skill/skills/blog/SKILL.md
Commit: aec971a

Reviewed: about 13 hours 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.