blog-post

Authoring or revising a public-facing blog post (learn/blog/*.md + portal registration). Enforces hero-piece narrative arc, sourcing every external claim, killing the three over-claim flavors, and the mandatory cross-family review bar.

Quality

77%

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 ./.agents/skills/blog-post/SKILL.md

Quality

Content

87%Weight 40%Scale 1-3

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

A token-efficient, actionable pointer skill that delegates detail to a real, one-level-deep reference with clear navigation. Its only weakness is workflow_clarity: the required gates (including cross-family review) are named but not sequenced as an explicit validation workflow in the body itself.

Suggestions

Add a short explicit checkpoint sequence in the body (e.g. draft → verify every external claim is sourced → run over-claim check → cross-family review → only then ship) so validation is sequenced, not just listed.

State the validate→fix→retry loop explicitly for the cross-family review gate to lift workflow_clarity to 3.

Consider naming the gate checklist as numbered steps so the validation order is unambiguous before delegating to the guide.

Dimension	Reasoning	Score
Conciseness	Lean and efficient — it assumes Claude's competence (no explanation of what a blog post is) and every line earns its place: a concrete redirect plus a one-sentence statement of the gates with the #13486 empirical anchor. Not a 2 because there is no unnecessary explanation or padding to tighten.	3 / 3
Actionability	Gives a concrete, executable instruction — "you MUST immediately use the `view_file` tool to read and strictly adhere to `.agents/skills/blog-post/references/blog-authoring-guide.md` before drafting or editing" — with a specific tool, path, and timing. Not a 2 because the redirect is complete and copy-paste ready rather than vague or pseudocode; the detailed authoring actions are appropriately delegated to the reference.	3 / 3
Workflow Clarity	A clear trigger→read-guide→adhere sequence is present and the gates ("every external claim sourced, zero over-claims, and cross-family review before it ships") are named, but they are not laid out as an explicit validate→fix→retry workflow with checkpoints in the body. Not a 3 because validation checkpoints are implicit rather than sequenced; not a 1 because the sequence and the gates are stated.	2 / 3
Progressive Disclosure	The body is a concise overview with a single, well-signaled one-level-deep reference to `references/blog-authoring-guide.md`, which exists in the bundle (verified). Not a 2 because navigation is explicit (named path + view_file instruction) and content is appropriately split rather than inlined.	3 / 3
	Total	11 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 specific, third-person description with a clear niche and concrete gate-listing actions, but it omits an explicit "Use when..." trigger clause and offers only narrow trigger-term coverage, which caps completeness and trigger_term_quality at 2.

Suggestions

Append an explicit trigger clause, e.g. "Use when authoring or revising a public-facing blog post, publishing a learn/blog article, or registering a post in the portal."

Broaden natural trigger terms to include variations users actually say (write/publish a blog post, blog article, portal blog registration).

Keep the gate list but ensure the when-guidance is stated as a trigger, not only implied by the gerund opening.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Authoring or revising a public-facing blog post", "Enforces hero-piece narrative arc, sourcing every external claim, killing the three over-claim flavors, and the mandatory cross-family review bar" — matching the anchor for listing several specific concrete actions. Not a 2 because the actions are comprehensive of the skill's gates rather than a partial naming of the domain.	3 / 3
Completeness	Clearly answers "what" (authoring/revising a post plus the enforced gates) but provides no explicit "Use when..." trigger clause — the "when" is only implied by "Authoring or revising". Per the rubric guideline, a missing Use-when clause caps completeness at 2; not a 1 because the what is strong, not a 3 because the when is not explicit.	2 / 3
Trigger Term Quality	"blog post" and "public-facing blog post" are natural terms a user would say, but coverage is thin — no common variations like write/publish a blog, blog article, or post. Not a 3 because it lacks the breadth of natural trigger variations; not a 1 because the core term is genuinely user-natural rather than jargon.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — public-facing blog post authoring with specific gates (narrative arc, sourced claims, over-claim killing, cross-family review) — unlikely to trigger for the wrong skill. Not a 2 because the gate set and the learn/blog/*.md + portal-registration scope make it clearly distinct from sibling skills like release-notes.	3 / 3
	Total	10 / 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: neomjs/neo
Path: .agents/skills/blog-post/SKILL.md
Commit: c1ce853

Reviewed: 8 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.