agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when optimizing search experience (SXO) — intent matching, personas, dwell time, pogo-sticking.
$ npx -y skills add fusengine/agents --skill seo-sxo --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/seo-sxoContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when optimizing search experience (SXO) — intent matching, personas, dwell time, pogo-sticking.
name: seo-sxo description: Use when optimizing search experience (SXO) — intent matching, personas, dwell time, pogo-sticking. user-invocable: false related-skills: seo, seo-content, seo-featured-snippets
<objective> Covers Search Experience Optimization: the 5-layer intent-matching table (informational through post-conversion) with expected page type, key signals, and CTA per layer, the local-vs-global intent behavioral-signal comparison, the user-persona and user-story method, and SXO metrics (dwell time, scroll depth, pogo-sticking rate, CTA click-through, the CWV-to-conversion link). Includes conversion-lever tactics for local transactional pages (above-fold CTA, click-to-call, urgency, trust proof) and SXO anti-patterns (pop-ups, walls of text, buried answers, intent-mismatched selling). </objective>
| Layer | Intent | Expected Page | Key Signals | CTA | |-------|--------|---------------|-------------|-----| | L1 | Informational | Guide, tutorial | Quick answer, TOC, depth | Newsletter / next article | | L2 | Navigational | Homepage, brand page | Logo, navigation, search | Direct link to feature | | L3 | Commercial | Comparison, reviews | Tables, pros/cons, ratings | Trial / demo / comparator | | L4 | Transactional | Product, pricing | CTA, price, trust signals | Low-friction purchase | | L5 | Post-conversion | Docs, FAQ, troubleshoot | Steps, search, error fixes | Support / upsell / community |
| Dimension | Local | Global / National | |-----------|-------|-------------------| | Dominant intent | Immediate transactional + proximity navigational | Informational + commercial → deferred transactional | | SERP trigger | Map Pack (3-Pack) + local AI Overviews | Organic results + AI Overviews | | Behavioural signal | "[service] near me", "[service] [city]", direct call/tap | "[service] reviews", "best [service]", "how to choose [service]" | | Conversion speed | Fast (ready to act now) | Slow (nurture across buyer journey) | | AI Overview CTR erosion | Low — Map Pack resists (physical intent can't be answered by AI) | High — informational keywords absorbed (-40% to -58% in 2026) |
1. Define 2-3 personas (role, goals, pain points) 2. Map each persona to query types they search 3. Build pages addressing their specific intent 4. Validate with user testing (heatmaps, session recordings)
As a <persona>, I search "<query>" because I need <goal>. I expect to find <expected content> within <time>. I'll engage by <action: scroll, click, share, convert>.
Transactional intent = a **minimum-friction action CTA above the fold**. Answer-first text serves the AI Overview *and* the click; the CTA + proof serve the conversion.
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).