agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when running a full-site SEO audit via /seo audit — orchestrates all SEO sub-agents in parallel for one unified Health Score.
$ npx -y skills add fusengine/agents --skill seo-audit --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/seo-auditContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when running a full-site SEO audit via /seo audit — orchestrates all SEO sub-agents in parallel for one unified Health Score.
name: seo-audit description: Use when running a full-site SEO audit via /seo audit — orchestrates all SEO sub-agents in parallel for one unified Health Score. user-invocable: false related-skills: seo, seo-technical, seo-schema, seo-content, seo-geo, seo-images, seo-sitemap
<objective> Orchestrates a full-site SEO audit: detects business type from homepage signals (SaaS/local/ecommerce/publisher/agency), spawns SEO sub-agents in parallel (seo-technical, seo-schema, seo-content, seo-geo, seo-entity, seo-images, seo-sitemap, plus seo-local and/or seo-cluster conditionally), aggregates results into a weighted SEO Health Score (0-100: technical 25, schema 15, content 20, GEO 20, images 10, local 10), and generates a prioritized action plan (Critical → High → Medium → Low) at `.fuse-seo/reports/<date>-audit.md`. This is the entry point for "audit the whole site" requests — for a single URL only, use seo-page instead. </objective>
1. **Detect business type** from homepage signals (SaaS, local, ecommerce, publisher, agency) 2. **Spawn sub-agents in parallel** (single message, multiple Agent calls):
3. **Conditional spawns**:
4. **Aggregate results** → SEO Health Score 0-100 5. **Generate report** in `.fuse-seo/reports/<date>-audit.md` 6. **Prioritize actions**: Critical → High → Medium → Low
Technical (25 pts): robots OK + sitemap valid + CWV green + crawlable Schema (15 pts): JSON-LD present + validated against schema.org Content (20 pts): E-E-A-T signals + no cannibalization + meta complete GEO (20 pts): quick answer first 100 words + citations + structure Images (10 pts): alt text 100% + formats (WebP/AVIF) + lazy loading Local (10 pts): NAP consistent + GBP linked (if applicable)
# SEO Audit Report — <url> — <date> ## Health Score: <score>/100 ### Critical Issues - ... ### High Priority - ... ### Medium / Low - ... ## Sub-Agent Results - Technical: <summary> - Schema: <summary> - Content: <summary> - GEO: <summary> - Images: <summary> - Sitemap: <summary>
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).