Build-Assistant
Build Claude Code framework components (agents, slash commands, skills, plugins) following standardized templates. Use when creating new agents, commands, skills, or plugins for the multiagent framework.
What this skill does
# Build-Assistant This skill provides templates, validation scripts, and documentation for building Claude Code framework components following the multiagent framework standards. ## Instructions ### When Creating a New Agent 1. Read the agent template: `templates/agents/agent.md.template` 2. Read the agent example: `templates/agents/agent-example.md` 3. Read documentation: `docs/claude-code-agents.md` (if available) 4. Create agent file with: - Proper frontmatter (name, description, tools, model, color) - Clear process steps - Key rules and output format 5. Validate using: `scripts/validate-agent.sh <agent-file>` ### When Creating a Slash Command 1. Read the command template: `templates/commands/command.md.template` 2. Read the command example: `templates/commands/command-example.md` 3. Read documentation: `docs/01-claude-code-slash-commands.md` 4. Create command file with: - Frontmatter (description, argument-hint, allowed-tools) - Task invocation with proper subagent_type - Success criteria and notes 5. Validate using: `scripts/validate-command.sh <command-file>` ### When Creating a Skill 1. Read the skill template: `templates/skills/SKILL.md.template` 2. Read the skill example: `templates/skills/skill-example/SKILL.md` 3. Read documentation: `docs/02-claude-code-skills.md` 4. Read decision guide: `docs/04-skills-vs-commands.md` 5. Create SKILL.md with: - Frontmatter with "Use when" trigger context - Step-by-step instructions - Concrete examples - Requirements 6. Validate using: `scripts/validate-skill.sh <skill-directory>` ### When Creating a Plugin 1. Read the plugin template: `templates/plugins/plugin.json.template` 2. Read the plugin example: `templates/plugins/example-plugin/` 3. Read documentation: `docs/03-claude-code-plugins.md` 4. Create plugin structure with: - `.claude-plugin/plugin.json` manifest - README.md with components list - commands/, skills/, agents/ as needed 5. Validate using: `scripts/validate-plugin.sh <plugin-directory>` ### Choosing Between Skills and Commands Consult `docs/04-skills-vs-commands.md` to decide: - **Use Skill** when: Claude should discover it automatically, complex capability, multiple supporting files - **Use Command** when: User explicitly triggers it, simple orchestration, workflow shortcut ## Available Resources ### Templates **Agents:** - `templates/agents/agent.md.template` - Standard agent template with frontmatter - `templates/agents/agent-example.md` - Complete working example **Commands:** - `templates/commands/command.md.template` - Standard slash command template - `templates/commands/command-example.md` - Complete working example **Skills:** - `templates/skills/SKILL.md.template` - Standard skill template - `templates/skills/skill-example/SKILL.md` - Git commit helper example - `templates/skills/README.md` - Skills template documentation **Plugins:** - `templates/plugins/plugin.json.template` - Plugin manifest template - `templates/plugins/example-plugin/` - Complete plugin example with commands and skills ### Validation Scripts - `scripts/validate-agent.sh` - Validates agent frontmatter and structure - `scripts/validate-command.sh` - Validates command frontmatter and structure - `scripts/validate-skill.sh` - Validates SKILL.md frontmatter and "Use when" context - `scripts/validate-plugin.sh` - Validates plugin manifest and structure - `scripts/test-build-system.sh` - Comprehensive build system test suite ### Documentation - `docs/01-claude-code-slash-commands.md` - Slash command reference - `docs/02-claude-code-skills.md` - Skills reference with frontmatter fields - `docs/03-claude-code-plugins.md` - Plugin architecture and structure - `docs/04-skills-vs-commands.md` - Decision guide for choosing component type ## Requirements - Templates must exist in `templates/` directory - Validation scripts must be executable - Documentation files should be available in `docs/` - Follow Claude Code standards for frontmatter - Include "Use when" context in skill descriptions ## Best Practices 1. **Always validate** - Run validation scripts after creation 2. **Follow templates** - Use provided templates as starting point 3. **Read examples** - Study working examples before creating new components 4. **Check documentation** - Consult docs for standards and patterns 5. **Test thoroughly** - Use test-build-system.sh for comprehensive testing --- **Generated from**: multiagent-build plugin build-assistant skill **Purpose**: Standardize framework component creation across multiagent ecosystem **Load when**: Creating agents, commands, skills, or plugins
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.