blog-writer

Plan, write, and review VS Code blog posts. ALWAYS use this skill when the user asks to "write a blog post", "draft a blog", "add a blog post for", "review this blog post", or provides a feature/issue/PR to announce on the VS Code blog. For new posts, it proposes an outline and asks clarifying questions first, and does not edit any files until you approve the plan.

Quality

90%

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

88%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-crafted skill body: concrete formats, paths, and limits make the guidance fully executable, and the two-phase workflow with an explicit approval gate and verification steps is exemplary. The only improvements are trimming cross-section repetition and slightly tightening the organization.

Suggestions

State the blog-writing style guide link once in a single Style section and reference it elsewhere as "the style guide" to remove the four repeated full links.

Define the public-availability rule once in Guardrails and have Phase 1 step 4 and Review mode step 3 reference it rather than restating it.

Mention "Happy coding! 💙" once (in the style-guide summary of required elements) instead of repeating it in Guardrails, Phase 2, and Review mode.

Dimension	Reasoning	Score
Conciseness	The body is dense and purely instructional with no padding of concepts Claude already knows, but there is minor repetition that could be trimmed: the blog-writing style guide link appears four times, the public-availability rule is stated in Guardrails, Phase 1 step 4, and Review mode, and "Happy coding! 💙" is spelled out three times. Fits "efficient; minor instances of over-explanation that could be trimmed" rather than level 5.	4 / 5
Actionability	Fully concrete, executable guidance: exact path template blogs/<year>/<month>/<day>/<slug>.md, the named frontmatter fields, byline format "<Month> <day>, <year> by [<author>](<social link>)", character limits (MetaDescription under 160, TOCTitle under 30), a repo-mapping table for source checks, the gh CLI, and a TODO-placeholder protocol for images. As an instruction-only skill, the absence of code is not penalized.	5 / 5
Workflow Clarity	Two clearly sequenced phases with explicit checkpoints and feedback loops: ask clarifying questions when ambiguous, "Stop and wait for approval. Do not proceed to Phase 2 until the user explicitly approves", verify public availability and Order uniqueness before drafting, and a post-draft verification step. Review mode has its own checklist plus a do-not-edit guard, matching the level-5 anchor.	5 / 5
Progressive Disclosure	Well-organized sections (When to Use, Guardrails, Phase 1, Phase 2, Review Mode) with style-guide detail correctly delegated to a clearly signaled one-level-deep external file, and no bundle references/scripts/assets exist to navigate. It falls short of level 5 because the ~83-line body carries all operational content inline and restates guardrail rules across sections — "good structure; minor organization gaps".	4 / 5
	Total	18 / 20 Passed

Description

91%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 clearly states what the skill does, when to use it via quoted literal trigger phrases, and its plan-first behavior in third person. The only refinements are slightly generic action verbs and niche scoping that leans on the "VS Code" qualifier alone.

Dimension	Reasoning	Score
Specificity	"Plan, write, and review VS Code blog posts" names the domain and multiple actions, and the description adds concrete behaviors ("proposes an outline", "asks clarifying questions first", "does not edit any files until you approve the plan"). The core verbs are slightly generic compared to the level-5 anchor's fully enumerated concrete operations, so it sits above the midpoint but below comprehensive.	4 / 5
Completeness	It explicitly answers both questions: "what" (plan, write, and review VS Code blog posts, with the plan-first behavior spelled out) and "when" ("ALWAYS use this skill when the user asks to…" followed by concrete trigger phrases), matching the level-5 anchor exactly.	5 / 5
Trigger Term Quality	It quotes literal natural phrases users would say — "write a blog post", "draft a blog", "add a blog post for", "review this blog post", and announcing a feature/issue/PR on the VS Code blog — covering synonyms (write/draft/add/review/announce) comprehensively with no common variation missing.	5 / 5
Distinctiveness Conflict Risk	"VS Code blog posts" is a clear niche with distinct triggers and is distinguishable from doc/release-note/API-doc skills, but generic "blog post" writing requests carry minor overlap risk since the scoping depends on the single "VS Code" qualifier — fits "mostly distinct; minor overlap risk" better than the minimal-conflict level-5 anchor.	4 / 5
	Total	18 / 20 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
relative_links	Relative link issues: 1 missing, 5 suspicious	Warning

	Total	14 / 16 Passed

Repository: microsoft/vscode-docs
Path: .github/skills/blog-writer/SKILL.md
Commit: 279a4a7

Reviewed: 9 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.