blog-brand

Establish durable brand and voice context for cross-skill consumption. Generates BRAND.md (audience, positioning, do/don't editorial rules, taboo phrases, competitor differentiation) and VOICE.md (existing persona JSON re-expressed as readable prose), both written to the project root. When present, the blog orchestrator auto-loads these files for write, rewrite, brief, outline, calendar, and strategy workflows. Pairs with blog-persona, which manages the structured persona JSON. Use when user says "blog brand", "create brand context", "brand voice doc", "BRAND.md", "VOICE.md", "establish editorial brand", "brand guidelines for blog".

Quality

91%

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

82%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, actionable skill body with concrete interview steps, full output templates, and explicit workflows. It is slightly held back by a trimmable rationale section, validation steps separated from the main flow, and no post-write verification.

Suggestions

Trim the 'Why this exists' section and de-duplicate the intro against the frontmatter description to tighten conciseness.

Fold the Error Handling checkpoints (especially the ask-before-overwrite and refuse-skeleton rules) inline into the Init/Update workflow steps so validation is visible at the point of action, and add an explicit post-write verification step (e.g. re-read the files and confirm sections are populated).

Consider extracting the full BRAND.md/VOICE.md templates into reference files linked from the body, which would let the overview stay lean and lift progressive_disclosure toward a clear one-level-deep structure.

Dimension	Reasoning	Score
Conciseness	Largely efficient actionable content (interview questions, templates, workflows), but the 'Why this exists' rationale section and intro repetition of the description are minor instances of over-explanation that could be trimmed; not below midpoint, so 4 rather than 3.	4 / 5
Actionability	Highly actionable for an instruction-only skill: a 5-step interview with specific questions, copy-paste-ready fill-in BRAND.md/VOICE.md templates, explicit show/update workflows, and concrete error-handling rules cover the common cases.	5 / 5
Workflow Clarity	The 5-step Init sequence and show/update flows are clearly sequenced with validation present (refuse minimal answers, ask before overwriting existing files), but the checkpoints live in a separate Error Handling section rather than inline and there is no post-write verification step — minor gaps keeping it at 4.	4 / 5
Progressive Disclosure	Well-organized with clear sections, tables, and inlined output templates (which are the deliverable, appropriately inline); no external reference files exist or are needed, so structure is good with only minor organization gaps rather than a clear multi-file overview.	4 / 5
	Total	17 / 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.

A strong description that explicitly states concrete deliverables, their contents, and auto-loading behavior, then provides an explicit 'Use when' clause with natural trigger phrases. It clearly distinguishes itself from the related blog-persona skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete deliverables with their contents — 'Generates BRAND.md (audience, positioning, do/don't editorial rules, taboo phrases, competitor differentiation) and VOICE.md (existing persona JSON re-expressed as readable prose)' plus the auto-load behavior across six named workflows, giving comprehensive coverage.	5 / 5
Completeness	Clearly answers both 'what' (generates and auto-loads BRAND.md/VOICE.md with detailed contents) and 'when' (concrete 'Use when user says...' trigger phrases), matching the top anchor exactly.	5 / 5
Trigger Term Quality	An explicit 'Use when user says' clause enumerates eight natural phrases including file names ('blog brand', 'BRAND.md', 'VOICE.md', 'brand voice doc', 'brand guidelines for blog'), covering synonyms and concrete file triggers.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear editorial-brand niche with distinct file triggers, and explicitly differentiates from blog-persona ('Pairs with blog-persona, which manages the structured persona JSON'), minimizing conflict risk.	5 / 5
	Total	20 / 20 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: AgriciDaniel/claude-blog
Path: brain/.raw/sources/claude-blog-skill/skills/blog-brand/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.