blog-writing-guide

This skill enforces Sentry's blog writing standards across every post — whether you're helping an engineer write their first blog post or a marketer draft a product announcement.

Quality

49%

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 ./skills/blog-writing-guide/SKILL.md

Quality

Content

63%Scale 1-5

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

This is a well-crafted editorial style guide with strong examples and clear standards, but it's moderately verbose for a skill file — repeating key points across sections and including some explanatory framing that Claude doesn't need. The actionability is strong with concrete good/bad examples and usable checklists, though the single-file structure could benefit from splitting reference material (banned words, checklists) into supporting files for better token efficiency.

Suggestions

Eliminate redundancy: 'never say excited to announce' appears in Banned Language, The Opening example, and Non-Negotiables — consolidate to one authoritative location.

Remove the meta-description opening paragraph ('This skill enforces...') since it duplicates the frontmatter description and tells Claude what the skill is rather than how to use it.

Consider extracting the Banned Language list and Review Checklists into separate bundle files (e.g., BANNED_LANGUAGE.md, REVIEW_CHECKLIST.md) to reduce the main file's token footprint while keeping reference material accessible.

Dimension	Reasoning	Score
Conciseness	The skill contains genuinely useful, non-obvious guidance (banned language list, title examples, post type table), but there's notable verbosity: the opening meta-description repeats the frontmatter, the voice section over-explains with metaphors Claude doesn't need, and several points are restated across sections (e.g., 'never say excited to announce' appears three times). The content could be tightened by ~30% without losing information.	3 / 5
Actionability	The skill provides concrete, actionable guidance with good/bad examples for openings, titles, closings, and banned language. The checklists and post-type table are directly usable. However, it's an instruction-only skill (no code), and some guidance remains slightly abstract — e.g., 'include a diagram' without specifying format or tooling, and 'code must work' without specifying how Claude should verify code in a blog draft context.	4 / 5
Workflow Clarity	The review/editing section provides a clear three-part checklist (Technical Review, Editorial Review, Final Check) that serves as a solid workflow for reviewing drafts. The post structure (problem → how it works → trade-offs → next steps) is a clear sequence for writing. Minor gap: there's no explicit workflow for the writing process itself (e.g., outline → draft → review cycle), and no feedback loop for iterating on drafts that fail the checklists.	4 / 5
Progressive Disclosure	The content is a single monolithic file at ~200 lines with no references to supporting files. While the sections are well-organized with clear headings, some content (like the full banned language list, the post types table, or the detailed checklists) could benefit from being split into referenced files. For a skill of this length, the lack of any bundle structure is a missed opportunity, though the internal organization with headers is reasonable.	3 / 5
	Total	14 / 20 Passed

Description

36%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.

The description identifies the domain (Sentry blog writing standards) but is too vague about what concrete actions the skill performs. It lacks an explicit 'Use when...' clause and reads in second person ('you're helping'), which reduces clarity. The description would benefit significantly from listing specific capabilities and adding explicit trigger guidance.

Suggestions

Add specific actions the skill performs, e.g., 'Reviews tone, enforces heading structure, checks for jargon, validates formatting against Sentry's style guide'.

Add an explicit 'Use when...' clause with trigger terms like 'Use when writing or reviewing Sentry blog posts, drafting product announcements, or when the user asks about Sentry's blog style guide or content standards'.

Rewrite in third person voice — replace 'whether you're helping an engineer' with something like 'Applies to posts by engineers, marketers, or other contributors'.

Dimension	Reasoning	Score
Specificity	Names the domain (blog writing standards for Sentry) but provides no concrete actions. 'Enforces standards' is vague — it doesn't specify what actions are taken (e.g., checking tone, formatting headers, validating structure, suggesting edits).	2 / 5
Completeness	The 'what' is vaguely stated as 'enforces blog writing standards' without specifics. There is no explicit 'when' clause — no 'Use when...' guidance. The examples of use cases (engineer's first post, marketer's announcement) weakly imply when, but don't constitute explicit trigger guidance. Per rubric, missing 'Use when...' caps this at 3, and the vague 'what' brings it to 2.	2 / 5
Trigger Term Quality	Includes some relevant keywords like 'blog', 'writing standards', 'blog post', 'product announcement', and 'Sentry', but misses natural user phrases like 'write a post', 'draft', 'content review', 'style guide', or 'editorial guidelines'.	3 / 5
Distinctiveness Conflict Risk	Mentioning 'Sentry's blog writing standards' adds some specificity, but 'enforces writing standards' could overlap with general writing/editing skills, style guide skills, or content review skills. The Sentry-specific qualifier helps but the lack of concrete actions makes boundaries unclear.	3 / 5
	Total	10 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/blog-writing-guide/SKILL.md
Commit: 57c135b

Reviewed: 1 day 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.