apex-methodology
Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix, add feature, refactor, develop).
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
$ npx -y skills add fusengine/agents --skill agent-creator --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/agent-creatorContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
name: agent-creator description: Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references. versions: claude-plugins: "1.35" user-invocable: true references: references/architecture.md, references/frontmatter.md, references/required-sections.md, references/hooks.md, references/registration.md, references/templates/agent-template.md, references/templates/hook-scripts.md related-skills: skill-creator, exploration
<objective> Agent Creator scaffolds a complete Claude Code expert agent: frontmatter (name, description, model, tools, skills, hooks), the mandatory Agent Workflow section, hook scripts, and marketplace registration. It covers three flows -- creating a brand-new domain/framework expert, adapting an existing agent to a new stack, and updating an agent's skills or hooks -- each ending with a `fuse-ai-pilot:sniper` validation pass.
It does not create the skills an agent references -- for that, use `skill-creator`; agent-creator only wires the agent frontmatter and workflow around skills that already exist or are created alongside it. </objective>
Before ANY agent creation, delegate via `Agent` — spawn 2 agents in parallel (single message, 2 `Agent` calls). Generated agents carry `Agent` and `SendMessage` in their tools, so this same pattern is what they must use internally too:
1. **fuse-ai-pilot:explore-codebase** - Check existing agents, analyze patterns 2. **fuse-ai-pilot:research-expert** - Fetch latest agent conventions
`mcp__context7__query-docs` is a direct MCP call, not a spawned agent — invoke it directly (alongside the 2 Task calls) to get examples from existing agents.
After creation, run **fuse-ai-pilot:sniper** for validation.
---
| Action | When to Use | |--------|-------------| | **New Agent** | New domain/framework expert needed | | **Adapt** | Copy from similar agent (Next.js → React) | | **Update** | Add skills, modify hooks |
---
1. **ALL content in English** - Never French or other languages 2. **Frontmatter complete** - name, description, model, tools, skills, hooks 3. **Agent Workflow section** - Always first content section 4. **SOLID rules reference** - Link to solid-[stack] skill 5. **Register in marketplace.json** - Or agent won't load 6. **Hook scripts executable** - `chmod +x` 7. **Output Format section mandatory** - Every generated agent must define a standard `## Output Format` section (status, files_changed, errors, sources) — an agent invoked by a lead must return structured data, not prose
---
plugins/<plugin-name>/
├── agents/
│ └── <agent-name>.md # Agent definition
├── skills/
│ ├── skill-a/
│ └── solid-[stack]/
├── scripts/
│ └── validate-*.sh # Hook scripts
└── .claude-plugin/
└── plugin.json→ See [architecture.md](references/architecture.md) for details
---
| Topic | Reference | When to Consult | |-------|-----------|-----------------| | **Architecture** | [architecture.md](references/architecture.md) | Understanding agent structure | | **Frontmatter** | [frontmatter.md](references/frontmatter.md) | YAML configuration | | **Required Sections** | [required-sections.md](references/required-sections.md) | Mandatory content | | **Hooks** | [hooks.md](references/hooks.md) | Pre/Post tool validation | | **Registration** | [registration.md](references/registration.md) | marketplace.json |
| Template | When to Use | |----------|-------------| | [agent-template.md](references/templates/agent-template.md) | Creating new agent | | [hook-scripts.md](references/templates/hook-scripts.md) | Validation scripts |
---
# 1. Research existing agents → explore-codebase + research-expert # 2. Create files touch plugins/<plugin>/agents/<agent-name>.md touch plugins/<plugin>/scripts/validate-<stack>-solid.sh chmod +x plugins/<plugin>/scripts/*.sh # 3. Register in marketplace.json # 4. Validate → sniper
# 1. Copy similar agent cp plugins/nextjs-expert/agents/nextjs-expert.md plugins/new-plugin/agents/new-expert.md # 2. Adapt with sed sed -i '' "s/nextjs/newstack/g; s/Next\.js/NewStack/g" agents/new-expert.md # 3. Update skills, tools, register
---
---
**When creating an agent, you often need to create skills too.**
Use **`/fuse-ai-pilot:skill-creator`** to create skills for the agent:
| Scenario | Action | |----------|--------| | New agent needs skills | Create skills with skill-creator first | | Agent references skills | Ensure skills exist in skills/ | | Adapting agent | Adapt related skills too |
---
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Repo: fusengine/agents
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).
Use when exploring an unfamiliar codebase -- architecture analysis, pattern detection, dependency mapping, rapid discovery.