Agent Scaffolders

Trigger with "mine this skill", "analyze this skill", "run targeted skill analysis", "extract patterns from this skill", or when you want focused analysis on a single Agent Skill directory without processing an entire plugin. Use this when the user points to a specific skill folder or says "look at this skill".

Trigger with "run self-audit", "test the analyzer", "regression test the plugin analyzer", "audit the agent-scaffolders", or "verify the analyzer works correctly". Runs the analyze-plugin skill against the agent-scaffolders itself and its test fixtures as a regression smoke test. Use this after making changes to the analyzer to verify nothing broke.

Audits and aligns individual agent skills and sub-agents against ecosystem evolution standards, verifying line budgets, evals schemas, and hub-and-spoke isolation.

Scaffolds a new event-driven hook in a plugin. NOT for creating interactive slash commands (use `create-command`) and NOT for GitHub Actions agentic workflows (use `create-agentic-workflow`).

Scaffolds a lean, invariant-driven agent rule following universal best practices. Enforces hard constraints, zero incident post-mortems, zero dates, zero usernames, high information density, and strict separation between rules (constraints) and skills (procedures).

This skill should be used when the user asks to "audit a plugin", "validate my plugin", "check plugin structure", "verify plugin is correct", "validate .claude-plugin/plugin.json", "check if my plugin is compliant", "review plugin components", or mentions plugin validation or structure compliance. Also trigger proactively after the user creates or modifies any plugin component (commands, agents, skills, hooks, .claude-plugin/plugin.json). Use this skill even when the user says "check my work" or "make sure this is right" in a plugin context. Do NOT use this for auditing individual skills only (use skill-reviewer for that).

Creates a new skill in an existing plugin. Skills are the universal capability primitive across all modern AI platforms (automatically callable as slash commands, agent skills, and prompt tools). Use this as the primary default for procedural capabilities. NOT for isolated multi-turn wizards or adversarial swarm agents (use `create-sub-agent`), and NOT for stateful counters (use `create-stateful-skill`).

Trigger with "mine plugins", "analyze plugin collection", "run the full analysis pipeline", "inventory and analyze all plugins", "mine patterns from this directory", or when you want to run the complete virtuous cycle: inventory, analyze, extract patterns, synthesize recommendations, and deliver a structured report. Use this even if the user just says "analyze everything in this folder".

Scaffolds a new top-level agent plugin directory. NOT for scaffolding single skills (use `create-skill`) and NOT for adding MCP integrations to existing plugins (use `create-mcp-integration`).

Systematically analyze agent plugins and skills to extract design patterns, architectural decisions, and reusable techniques. Trigger with "analyze this plugin", "mine patterns from", "review plugin structure", "extract learnings from", "what patterns does this plugin use", "check if this plugin is well-structured", "validate plugin compliance", or when examining any plugin or skill collection to understand its design. Use this skill even when the user just says "look at this plugin" or "tell me how this is structured."

Guidance on slash commands vs. skills. Explains modern best practices where skills (skills/<name>/SKILL.md) supersede legacy commands/workflows (commands/<name>.md), and guides users to use create-skill instead for portable, evaluated, multi-agent workflows. Retains reference for creating personal flat prompt shortcuts if explicitly requested.

Triggers the L5 Red Team Sub-Agent to rigorously audit a plugin against the 39-point L4 pattern matrix.

Scaffolds a new autonomous sub-agent with its own prompt, system instructions, and tool permissions. Enforces modern architectural guidance: sub-agents are reserved for isolated execution contexts, strict tool sandboxing, or adversarial personas. NOT for simple procedural skills (use `create-skill`) and NEVER for pointer-wrapper stubs that merely delegate to a skill.

Fixes broken path references in plugin skill and agent files to ensure portability across installed environments. Use when you see "plugins/" paths in SKILL.md or agent files, need to standardize path references after installing a skill, want to audit and fix cross-plugin path dependencies, run a portability audit on a repository, neutralize hardcoded machine paths like /Users/, find Python scripts using PROJECT_ROOT or Path() to reach into plugins/<name>/ at runtime, or are preparing plugin files for distribution via uvx or bootstrap.py. Also handles evolving a skill in-session while tracking quality scores with the eval runner to continuously improve skill routing accuracy.

Activate when the user wants to create a new APM-native package from scratch for reusable agent skills, agents, commands, hooks, MCP configuration, prompts, or governance-managed agent assets. Do not use this for existing plugin migration; use convert-plugin-to-apm instead.

Deploys a skill as an Azure AI Foundry hosted agent. NOT for Docker runtime skills (use `create-docker-skill`) and NOT for MCP server integrations (use `create-mcp-integration`).

This skill should be used when the user wants to "create a marketplace", "setup a marketplace catalog", "scaffold marketplace.json", "initialize a plugin registry", or "configure a Gemini CLI extension". Use this even if they just mention "setting up a marketplace".

Activate when the user wants to compile an APM package into top-level context documents such as AGENTS.md, CLAUDE.md, or GEMINI.md, especially for Codex, Gemini, OpenCode, or agents-protocol style hosts. Do not use when the user only needs per-skill installation; use install-apm-package instead.

Scaffolds an agent skill with a Docker runtime environment. NOT for normal local skills (use `create-skill`) and NOT for Azure hosted agents (use `create-azure-agent`).

Provides active execution protocols to rigorously audit how code, directory structures, and agent actions comply with the authoritative ecosystem specs. Trigger when validating new skills, plugins, or workflows.

Activate when the user wants to install, deploy, test, or materialize an APM package into runtime directories such as .agents/, .github/, .claude/, .cursor/, .gemini/, .codex/, .opencode/, or .windsurf/. Use after creating or converting an APM package.

Performs an uncompromising L5 Enterprise Red Team Audit on a given plugin against the 39-point architectural maturity matrix. Trigger when the user requests a security audit, red team assessment, structural compliance review, or maturity gap analysis of any agent plugin or skill directory.

Scaffolds a deterministic GitHub Actions CI/CD workflow YAML. NOT for scaffolding interactive agentic workflows (use `create-agentic-workflow`) and NOT for local event-driven hooks (use `create-hook`).

Convert raw plugin analysis results into actionable improvement recommendations for agent-scaffolders and agent-scaffolders. Trigger with "synthesize learnings", "generate improvement recommendations", "what should we improve in our scaffolders", "update our meta-skills based on these findings", or after completing a plugin analysis.

Activate when the user wants to add APM governance, lockfile/audit readiness, or multi-runtime package management to an existing Claude/Copilot/agent plugin, or explicitly convert a plugin into an APM-native package.

Scaffolds an advanced stateful agent skill with filesystem-native state schemas, lifecycle state machines, and skill chaining. NOT for simple stateless skills (use `create-skill`), NOT for isolated conversational wizards / persona swarms (use `create-sub-agent`), and NOT for GitHub Actions workflows (use `create-agentic-workflow`).

Trigger with "evaluate autoresearch fit", "score this skill for karpathy loop", "is this a good autoresearch candidate", "assess autoresearch viability for", "which skills are best for autonomous loop optimization", "score skills for 3-file architecture", or when the user wants to determine if a skill is a good candidate for applying the Karpathy autoresearch autonomous optimization loop pattern.

Adds an MCP server integration configuration to an existing plugin. NOT for scaffolding a brand-new plugin (use `create-plugin`) and NOT for Azure hosted agents (use `create-azure-agent`).

Audit file path references in plugins and skills. Trigger with "audit path references", "check file references", "find broken references", "path reference audit", "verify paths", or when you need to validate that all ./references in code actually exist in the skill/plugin. Three-phase audit: (1) SCAN all files for references, (2) VERIFY each exists, (3) REPORT issues. Generates inventory.json for reuse across multiple checks.

Automatically updates the plugin/skill/agent counts in README.md based on the current plugins/ directory.

Scaffolds a Copilot GitHub agent, an agent that runs in GitHub Actions, a GitHub workflow agent, or a GitHub Agentic Workflow (gh-aw) from an existing skill. Supports three target configurations: Target A (Custom Copilot agent), Target B (GitHub Agentic Workflow), and Target C (CI/CD Smart Failure agent).

Provides information about how to create, structure, install, and audit Agent Skills, Plugins, Antigravity Workflows, and Sub-agents. Trigger this when specifications, rules, or best practices for the ecosystem are required.