What does this skill do, and when should you use it?
Blog Outline is an invokable skill in the claude-blog suite for planning blog structure from SERP evidence. It produces H2/H3 hierarchy, section word-count targets, content-gap notes, FAQ slots, chart and image markers, and internal-linking zones. It is intentionally a skeleton generator, not a full competitive brief, statistics-research workflow, or complete image-recommendation tool.
Accepts a topic or target keyword and infers the keyword and search intent when context allows; uses WebSearch to inspect the top five results for the keyword, recording heading structures, approximate length, visual elements, FAQs, distinctive angles, and gaps; optionally uses WebFetch on the top two to three results when snippets are insufficient; generates title suggestions, target parameters, six to eight H2 sections, optional H3 subsections, section word counts, statistic prompts, chart and image markers, three to five FAQ items, a conclusion, internal-linking zones, and a dedicated content-gap analysis; saves the result to outlines/[slug]-outline.md or a user-specified path.
- A solo blogger has a topic and wants an SEO-aware article skeleton before drafting.
- A marketing team needs consistent H2/H3 structure, word-count allocation, FAQs, and internal-linking zones for a target keyword.
- An editor wants to review the outline before handing it to /blog write for full drafting.
- A content strategist wants to compare what top-ranking pages cover and plan angles they appear to miss.
How do you install this skill?
- WebSearch/WebFetch responses may contain indirect prompt injection, but the skill does not require treating fetched content as strictly untrusted data.
- The generated outline has no explicit source, URL, or per-claim evidence record, making SERP conclusions difficult to audit.
- The core workflow depends on external search and fetch services, with no stated fallback for mainland-China reachability, localization, or service failure.
- Network access
- Local filesystem
Install the public claude-blog collection rather than this skill as a standalone package:
- In Claude Code, run: /plugin marketplace add AgriciDaniel/claude-blog
- Run: /plugin install claude-blog@agricidaniel-claude-blog
- Restart Claude Code to activate it.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/AgriciDaniel/claude-blog.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/blog-outline" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
In Claude Code, run /blog outline <topic>, for example /blog outline email marketing for nonprofits. You can also make a request containing intents such as “outline,” “blog outline,” “content outline,” or “article skeleton.” Supply a topic; if the target keyword or search intent differs, state those explicitly. The workflow performs SERP analysis and saves the outline to outlines/[slug]-outline.md; the source does not define the slug-generation details.
What are this skill's strengths and limitations?
- Covers the planning path from keyword and intent through a usable article skeleton.
- Includes heading hierarchy, section word counts, FAQs, visual markers, and internal-linking zones.
- Clearly positions itself as a lighter structure-planning tool for approval before drafting.
- Adds a dedicated content-gap section for differentiating the planned article.
- Does not produce a full competitive analysis, deep statistics research, or complete image suggestions.
- Requires WebSearch, and sometimes WebFetch, so network access is part of the workflow.
- The source documents installation for the broader claude-blog collection, not a standalone installation path for this skill.
- No independent test results or cross-platform validation are documented for this individual skill.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Blog Outline Planner this page | 39 · Not recommended | ★ 2.4k | 14d ago | MIT |
| Blog Cluster Engine | 53 · Use with care | ★ 2.4k | 14d ago | MIT |
| SEO Content Brief Generator | 52 · Use with care | ★ 19k | 23d ago | MIT |
| SERP Semantic Topic Clustering | 49 · Use with care | ★ 19k | 23d ago | MIT |
| SEOBuild Onpage (SEO-AGI) | 50 · Use with care | ★ 257 | 12d ago | — |
Compared with blog-brief in the same collection, Blog Outline is lighter and focuses on article skeletons, heading hierarchy, word-count targets, and content gaps; blog-brief is intended for full competitive analysis, statistics research, and image suggestions. Compared with prompting Claude or ChatGPT directly, the README describes direct prompting as one-shot while claude-blog uses a structured pipeline; that comparison applies to the collection and should not be read as assigning sibling skills' capabilities to Blog Outline.
How did FollowSkills review this skill?
The skill explicitly requires WebSearch/WebFetch and makes the external SERP data flow visible; however, it lacks prompt-injection defenses, sensitive-data guidance, user confirmation, source-citation requirements, and rollback handling. File creation and saving also occur without a confirmation step, so points are deducted.
The workflow, required inputs, output template, and save path are reasonably consistent, and missing keyword or intent may be inferred from context. However, WebSearch/WebFetch availability is not specified, and failures such as empty results, blocked pages, non-English SERPs, or write errors lack diagnostic handling. The static ceiling keeps this below 10.
The frontmatter lists concrete trigger phrases and distinguishes this skill from blog-brief, giving it a clear primary scenario. Non-fit boundaries, language support, localized SERP behavior, and mainland-China network reachability are not defined, and semantic overlap with research or full-brief tasks remains possible, so points are deducted.
The skill has valid frontmatter, an MIT license, staged workflow, cross-references, a stable output structure, and an explicit skeleton-only limitation. It lacks its own versioning, changelog, maintenance owner, installation and dependency notes, troubleshooting, examples, and FAQ; some governance evidence is available only from shared repository context, so points are deducted.
The template covers titles, hierarchy, word-count targets, FAQs, visual markers, internal links, and content gaps, and is theoretically usable by blog-write. However, the result depends on external SERP analysis, no representative generated artifact is verified, and statistics and facts still require later research. Static evidence supports only limited core-task credit.
The workflow and required output fields are somewhat auditable, and shared repository materials provide CI and testing signals. However, the supplied tests do not cover blog-outline key paths, and there is no generated-output sample, third-party execution evidence, or source-attribution example for this skill, so evidence remains thin.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →