blog-draft

Draft a blog post from ideas and resources. Use when users want to write a blog post, create content from research, or draft articles. Guides through research, brainstorming, outlining, and iterative drafting with version control.

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.

A thorough, well-sequenced drafting workflow with strong actionability and clear checkpoints, but it is verbose and monolithic — generic writing tips and repeated templates pad the body and nothing is offloaded to reference files.

Suggestions

Remove the "Tips for Quality" section and the redundant citation guidance in Notes; Claude already knows general writing advice, so keep only skill-specific citation rules.

Extract the resource-summary, outline, and draft markdown templates into a `references/templates.md` and link to it, reducing the inline bulk and improving progressive disclosure.

Consolidate the citation requirements (currently stated in Step 6, Tips, and Notes) into a single authoritative block to cut repetition.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete templates, but the "Tips for Quality" section pads with writing advice Claude already knows ("Each paragraph should connect to the next", "Use short paragraphs") and citation guidance is repeated across Steps 6, Tips, and Notes.	2 / 3
Actionability	Provides concrete, copy-ready scaffolding: folder slug format `YYYY-MM-DD-short-topic-name`, exact file paths, commit message templates, and citation formats with worked examples like "Studies show that 65% of developers prefer TypeScript [1]".	3 / 3
Workflow Clarity	Steps 0–9 are clearly sequenced with explicit approval checkpoints ("Wait for user responses before proceeding", "ask for approval or modifications") and a defined iteration loop in Step 9, satisfying the validation/checklist anchor.	3 / 3
Progressive Disclosure	Well-organized into clear sections, but at ~200 lines it is monolithic with no bundle references; the reusable resource/outline/draft templates that are repeated inline could be split into separate reference files.	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 concise, third-person, and explicitly states both capability and trigger conditions with natural user phrasing. It cleanly matches the top anchors across all dimensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: "Draft a blog post from ideas and resources" plus "research, brainstorming, outlining, and iterative drafting with version control", matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what ("Draft a blog post from ideas and resources") and when ("Use when users want to write a blog post..."), the clearest anchor.	3 / 3
Trigger Term Quality	Natural phrases a user would say are well covered — "write a blog post", "create content from research", "draft articles" — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (blog drafting with version control) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: luongnv89/claude-howto
Path: 03-skills/blog-draft/SKILL.md
Commit: 97fc961

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.