blog-publisher

Skill compositora que pega texto/assunto e gera post de blog HTML completo no repo configurado em ~/.dev-team-kit/blog-config.json, com imagens (via skill 17 fal.ai ou skill 42 Playwright screenshot), commit+push automático, retorna URL pública via GitHub Pages. Trigger em: "post no blog", "publicar post", "escrever post", "blog post", "publish blog", "gera post", "criar post", "novo post no meu blog".

Quality

91%

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

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-structured, executable workflow with strong sequencing, explicit validation gates, and a feedback loop. Conciseness is good but slightly padded in the founding-principle section, and progressive-disclosure references are signposted inline rather than gathered into one navigable index.

Suggestions

Tighten the 'Princípio fundador' section: keep the one-line rule and the anti-padrão callout, drop the narrative restatement of the 5-step flow that already appears in the Protocolo.

Consolidate the repeated pointers to docs/skill-guides/blog-publisher.md, policies/*.md, and scripts/*.mjs into a single 'Referências' section so navigation lives in one place instead of being scattered across steps.

Note that no bundle directories (references/, scripts/, assets/) ship with the skill — if the referenced docs/policies/scripts are part of the kit, confirm they resolve at runtime or inline the few critical snippets directly.

Dimension	Reasoning	Score
Conciseness	Mostly lean and action-oriented with no explaining of concepts Claude already knows, but the 'Princípio fundador — AUTORAL' section and repeated anti-padrão prose add some padding that could be trimmed.	4 / 5
Actionability	Fully executable guidance: a copy-paste scaffold command with every flag, concrete git/grep commands, exact image dimensions (1500×750), and a named model (gpt-image-1-mini) covering the common cases.	5 / 5
Workflow Clarity	A fixed-order Protocolo (steps 1–6) with an explicit mandatory gate, a grep-until-zero feedback loop for the anti-AI checklist, and a completion checklist including an HTTP 200 verification — validation is present, so the destructive/batch cap does not apply.	5 / 5
Progressive Disclosure	Good structure with well-signaled one-level-deep references ('ver detalhes em docs/skill-guides/blog-publisher.md', policies, scripts), but the navigation is scattered inline rather than consolidated into a single reference section, leaving minor organization gaps.	4 / 5
	Total	18 / 20 Passed

Description

95%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, third-person description that concisely states concrete pipeline actions and pairs them with an explicit, bilingual trigger clause. The only gap is that it omits the LinkedIn-distribution block and index update that the body marks as obligatory.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'gera post de blog HTML completo', 'com imagens (via skill 17 fal.ai ou skill 42 Playwright screenshot)', 'commit+push automático', 'retorna URL pública via GitHub Pages' — with minor coverage gaps (omits the mandatory LinkedIn block and index/README update that the body treats as required).	4 / 5
Completeness	Explicitly answers both what (generate HTML post with images, auto commit+push, return public URL) and when (a dedicated 'Trigger em:' clause with concrete trigger phrases), so it does not hit the missing-trigger cap of 3.	5 / 5
Trigger Term Quality	Eight natural trigger phrases spanning PT-BR and EN synonyms and the exact phrasing a user would say ('publicar post', 'escrever post', 'blog post', 'publish blog', 'novo post no meu blog'), giving comprehensive coverage including synonyms.	5 / 5
Distinctiveness Conflict Risk	Clear niche — publishing to the user's own GitHub Pages blog repo — with distinct, blog-specific triggers, minimizing overlap with general writing or doc skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_field	'metadata' should map string keys to string values	Warning
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	13 / 16 Passed

Repository: felvieira/claude-skills-fv
Path: skills/41-blog-publisher/SKILL.md
Commit: 74aa7c1

Reviewed: 3 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.