agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when generating a detailed SEO content brief for a single page or topic before writing.
$ npx -y skills add fusengine/agents --skill seo-content-brief --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/seo-content-briefContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when generating a detailed SEO content brief for a single page or topic before writing.
name: seo-content-brief description: Use when generating a detailed SEO content brief for a single page or topic before writing. user-invocable: false related-skills: seo, seo-content, seo-cluster, seo-geo, seo-entity
<objective> Generates a full content brief for one target page: runs local keyword-density analysis first (`scripts/analyze-keywords.ts`, no API key), then produces target keywords (primary/secondary/long-tail layered by buyer state L1-L4), search intent classification, meta title/description constraints, a full H2/H3 outline with a self-contained answer capsule (40-60 words, citation-eligible) opening every H2, a word-count target, 5-10 internal link suggestions, required schema types, and a GEO readiness checklist. One brief targets one buyer state per URL. Does not build the keyword cluster itself (seo-cluster) or score already-published content quality (seo-content). </objective>
Before generating a brief, run `scripts/analyze-keywords.ts` (local-first, no API key) on the target or a top competitor URL. Use the result to shape target keywords, semantic variants, heading coverage, local modifiers, and stuffing warnings.
bun run scripts/analyze-keywords.ts <url-or-path> --keyword "<primary keyword>" --synonyms "<syn1,syn2>" --locations "<city1,city2>" --format markdown
Layer keywords by buyer state, not by surface similarity:
| Layer | State | Intent signal | Example phrasing | |-------|-------|---------------|------------------| | **L1** | Awareness | "what is", "why", symptoms, problems | broad informational, conversational | | **L2** | Comparison | "vs", "alternatives", "best for" | options weighing | | **L3** | Evaluation | "pricing", "reviews", "is X worth it" | scrutiny, objections | | **L4** | Decision | "buy", "near me", "demo", "signup" | transactional/local |
One brief targets one buyer state per URL. Cluster by buyer state + intent, never by lexical surface similarity.
AI Overviews capture ~30-60% of the informational CTR. Optimize for **verbatim LLM extraction**, not raw traffic alone: every section must yield a self-contained, quotable answer. A brief that ranks but is not extractable loses the AI Overview slot.
# Content Brief: <topic> ## Target Keywords - Primary: <kw> (vol, KD, intent) - Secondary: <kw1>, <kw2>, <kw3> - Long-tail: <lt1>, <lt2>, <lt3> ## Search Intent - Type: informational | navigational | commercial | transactional - User question: "<exact question>" - Expected format: guide | listicle | comparison | tutorial ## Outline - Meta title: <primary keyword or strong variant, <=60 chars, no brand unless requested> - Meta description: <benefit + intent match, <=150 chars> - H1: <semantic match to title, primary keyword or strong variant> - H2: <synonym, long-tail phrase, question, or sub-intent> - H3: <supporting sub-intent> - H2: <section 2> - H2: FAQ - H2: Conclusion ## Answer Capsules (per H2) <40-60 word self-contained answer opening EACH H2, not only the first 100 words — citation-eligible for AI Overviews> ## Word Count Target <based on top 10 SERP average> ## Internal Links (5-10) - → <pillar page> - → <related cluster pages> ## Schema - Article + BreadcrumbList (always) - FAQPage (if FAQ section) - VideoObject (if video embed) ## GEO Requirements - Answer capsule (40-60 words) opening every H2 - One hyperlinked statistic to its primary source every 150-200 words - Name key entities explicitly (no pronouns for the primary entity) - Cite 3-5 authoritative sources - Use tables/lists for comparison data
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Repo: fusengine/agents
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix, add feature, refactor, develop).
Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to refine requirements via structured questioning.
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every…
Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional…
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD elicitation techniques).