blog-writer

Blog post writing skill with structure templates and style guidelines. Guides the agent through writing well-structured, engaging technical blog posts with proper formatting, section flow, and reader engagement techniques.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./python/agents/agent-skills-tutorial/app/skills/blog-writer/SKILL.md

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 concise, well-sequenced, and uses progressive disclosure effectively by offloading detailed style rules to a real reference file. Its main weakness is actionability: concrete directives are present but no worked examples or templates demonstrate the expected output.

Suggestions

Add a short worked example (e.g., a sample outline and one finished H2 section) so the directives are copy-paste-ready rather than abstract.

Show one concrete 'Hook' example alongside the bullet definition to anchor the outline guidance.

Optionally surface 1-2 of the style-guide's anti-patterns inline so the agent applies them without an extra file load for common cases.

Dimension	Reasoning	Score
Conciseness	The body is lean and step-structured with no padding or explanation of concepts Claude already knows; every line gives a concrete directive ('Keep paragraphs to 2-3 sentences', 'Use `load_skill_resource` to read references/style-guide.md'), so every token earns its place.	3 / 3
Actionability	Guidance is concrete and specific (H2 subheadings, fenced code blocks with language tags, 2-3 sentence paragraphs, bullet vs numbered lists), but there are no worked examples or a template showing a sample hook/section, so it stops short of copy-paste-ready specificity.	2 / 3
Workflow Clarity	The four steps (Structure, Outline First, Write Each Section, Polish) are clearly sequenced, and Step 4 includes an explicit verification checklist ('Verify all code examples are complete and runnable', 'Ensure consistent tone'); for a simple non-destructive writing skill this meets the clear-sequence-with-checkpoints bar.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview that signals a single one-level-deep reference ('references/style-guide.md' via load_skill_resource), and that file exists and holds the detailed style rules, giving clear navigation with appropriately split content.	3 / 3
	Total	11 / 12 Passed

Description

50%

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 clearly conveys what the skill does in third-person voice and avoids fluff, but it omits any explicit 'Use when...' trigger guidance and offers only modestly specific actions. Adding concrete trigger phrases would lift completeness, trigger quality, and distinctiveness together.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrases (e.g., 'Use when writing blog posts, articles, or technical posts, or when the user asks for help structuring or polishing a blog post').

Replace generic aspect words ('reader engagement techniques') with concrete actions ('drafts outlines, writes H2-led sections, formats code blocks, adds transitions and calls-to-action').

Include common keyword variations like 'article' and 'post' to broaden trigger coverage and reduce overlap with general writing skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('blog post writing') and several aspects ('formatting, section flow, and reader engagement techniques'), but these are attributes rather than a comprehensive list of concrete actions, so it sits at the 'names domain and some actions' level rather than listing multiple specific actions.	2 / 3
Completeness	It clearly states what the skill does ('Guides the agent through writing well-structured, engaging technical blog posts...') but provides no 'Use when...' clause or equivalent explicit trigger guidance, so 'when' is only implied and completeness is capped at 2 per the guidelines.	2 / 3
Trigger Term Quality	It includes relevant natural terms like 'blog post writing' and 'technical blog posts' that a user might say, but coverage is narrow and missing common variations ('write a blog', 'article', 'post'), placing it at 'some relevant keywords but missing common variations.'	2 / 3
Distinctiveness Conflict Risk	'Blog post writing' is a recognizable niche, but the lack of explicit triggers and the generic 'writing' framing means it could overlap with broader writing or documentation skills, fitting 'somewhat specific but could still overlap.'	2 / 3
	Total	8 / 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: google/adk-samples
Path: python/agents/agent-skills-tutorial/app/skills/blog-writer/SKILL.md
Commit: a862ebc

Reviewed: about 11 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.