m2ai-build-tooling

Plugin m2ai-build-tooling from marketplace m2ai-skills-pack in m2ai-portfolio/m2ai-skills-pack. Commands read from the repo's manifest — 2 days ago.

Skills (38)

• agent-commerce-mcp-spec

  Take a business's existing storefront, catalog, or checkout flow and emit a complete MCP server spec that makes it agent-callable end-to-end — tool list, JSON schemas, auth model, payment rails, and idempotency guarantees. Optionally scaffolds a Python mcp-sdk server skeleton. Use when asked "make t

• agent-commerce-scaffold

  Scaffold a new agentic-commerce product with all 8 commercial-responsibility domains pre-stubbed -- Identity, Authorization, Fraud, Payment credentials, Settlement, Refunds, Liability, CRM. Each domain gets a README, an interface contract, and a TODO:assign-owner marker so no layer silently goes un-

• agent-infra-scorer

  Score any enterprise tool (Jira, Salesforce, Workday, Google Calendar, etc.) against a 5-test structural diagnostic to determine whether it qualifies as agent infrastructure (keep), wrappable (replace with MCP), or legacy (replace). Produces a per-tool verdict and a ranked stack table. Use when the

• agent-readiness-audit

  Audit a codebase for agent-readiness across 8 pillars (style/validation, build systems, testing, docs, dev environment, code quality, observability, security governance). Generates a scored report with a prioritized fix list measured in estimated days. Use when the user says "audit readiness", "agen

• agentify-docs

  Converts existing human-oriented documentation (READMEs, runbooks, architecture docs, onboarding guides) into agent-readable equivalents with explicit boundaries, permission declarations, and "what to do when stuck" instructions. Use when asked to "write AGENTS.md", "make this doc agent-readable", "

• automation-platform-decision-guide

  Decision-support skill for choosing between agent automation platforms. Given a use case and org context, recommends between scheduling platforms (n8n, Make, Workspace Agents), custom agent frameworks (Claude Code, SDK), and personal AI assistants — and explains the governance, cost, and lock-in tra

• book-to-skill

  Create Claude Code skills from book/long-form prose. Reads a how-to chapter or draft, extracts the teachable procedure (SOP) from the writing, then converts that SOP into a production skill via skill-creator. The prose sibling of video-to-skill (same pipeline, text input instead of a screen recordin

• callable-audit

  Audit whether a business is callable by an AI agent end-to-end. Takes a business name, URL, or description and walks a structured rubric — discoverable surface, full economic task completion (discover → compare → decide → pay → confirm), auth model — producing a verdict of agent-callable, wrappable,

• claude-architect-audit

  Audit your Claude Code setup against Anthropic's 5 Certified Architect domains. Checks CLAUDE.md layering, enforcement strategy (prompts vs hooks), tool descriptions, context management, and agent architecture. Use when you want to level up your Claude Code configuration, prepare for the architect c

• claude-design-to-code

  Rapidly prototype UI wireframes and high-fidelity designs with Claude Design, then export to Claude Code with a single terminal command that preserves full design fidelity. Covers self-verification loops, mode switching (cinematic/editorial/responsive), Figma import, and bias-breaking prompting patt

• code-review-memory

  Accumulates repo-specific code review lessons and surfaces them before the next review of the same file or module. Learns from recurring issues -- migration bugs, error-handling patterns, fixture quirks, security gaps -- so the same mistake isn't flagged for the first time twice. Trigger phrases: \"

• comprehension-gate

  Pre-merge review that checks a PR diff not for syntax or test coverage, but for human understanding of implications -- plain-text credentials, cross-service data leaks, tokens without TTL, blast radius of failures, caching in shared locations. Outputs a comprehension artifact (not pass/fail) that en

• comprehension-interview-loop

  Conduct a Socratic pushback interview about something the user has built. Detects hand-waving, vague claims, and gaps in understanding, then assembles the result into a clean explanation artifact. Use when the user says "interview me", "comprehension interview", "Socratic review", "pushback intervie

• context-layer-generator

  Generate three structured context artifacts for any module or service -- a structural manifest (what it does, dependencies, dependents), behavioral contracts (idempotency, retry semantics, failure modes, performance expectations), and a decision log pre-filled from git history explaining why archite

• dark-code-audit

  Scan a codebase to map where human comprehension has gone missing -- identifying modules with no decision logs, no behavioral contracts, no authorship trail, and high AI-generation signals. Produces a tiered darkness report (summary heat map + ranked TODO list) scoring each module 0-100. Use when on

• demotion-audit

  Three-phase audit to determine whether a software tool or artifact should be demoted down the production-class ladder (Customer-Facing → Supported Internal → Team Beta → Personal Tool → retired). Returns a Demote/Hold verdict with explicit trigger evidence, transition requirements, and a "maintenanc

• eval-agent

  Score any agent tool or platform against 3 structural questions (persistent memory, inspectable artifacts, compounding context) for a given use case, then generate a delegation spec that patches the weaknesses found. Use when evaluating agent tools, comparing platforms, or deciding whether to trust

• explanation-artifact-generator

  Walk through a 4-question comprehension template for any project artifact (repo, feature, tool) and produce a structured explanation artifact that lives alongside the code. Questions cover what it is, why this approach, what would break, and what you learned. Use when the user says "explanation arti

• failure-mode-tool-router

  Given any task description, classify it into the right AI tool category and explain why common alternatives are wrong for it. Prevents wasting time building agents for tasks that should use a different tool entirely.

• get-api-docs

  Fetch curated, versioned API documentation via the `chub` CLI (Context Hub) before writing code against an external API or SDK, so calls are checked against real docs instead of recalled from training data. Use before implementing anything that calls an external API, when unsure of the correct param

• image-to-implementation

  Generate a visual reference image for a UI or design concept, then produce a structured implementation prompt that hands the image to a code-capable model. Closes the "AI invents bad taste" failure mode by anchoring implementation to a concrete visual rather than a text description alone.

• inbox-load-audit

  Scans installed skills, plugins, MCP servers, hooks, and scheduled tasks to produce an inbox load score — how many independently-managed AI surfaces the user is maintaining. Outputs a score, breakdown, and top recommendations to reduce load.

• mcp-spec-generator

  Takes any SaaS product or internal system and outputs a complete MCP server specification — tool list, input/output schemas, auth model, state-machine endpoints, audit/event endpoints, and dependency-graph queries — structured so an AI agent can use the tool as control-plane infrastructure rather th

• mismatch-check

  Diagnose whether your current agent tooling matches your actual problem. Detects expensive architecture mismatches where you've built a solution to the wrong question. Use when evaluating an existing agent setup, troubleshooting why an agent isn't delivering, or when someone says "why isn't this wor

• optimize-description

  Rewrite a skill's description field for maximum agent discoverability -- clear trigger conditions, explicit input/output contracts, and disambiguation from similar skills.

• prototype-classifier

  Classify any software tool, script, or AI artifact onto a 4-rung production-class ladder (Personal Tool → Team Beta → Supported Internal → Customer-Facing) using evidence-based thresholds. Never rounds up on aspiration — only classifies at the highest rung the artifact fully qualifies for. Trigger p

• self-healing-claudex

  Self-healing build pipeline with Planner/Builder + Codex adversarial review. Planner writes a test contract, Builder implements until tests pass, Codex pressure-tests the implementation with a different reviewer persona each round (engineer / security / ops), Builder revises, repeat until Codex agre

• self-healing-pipeline

  Self-healing build pipeline with Planner/Builder/Judge loop. Planner writes test contracts, Builder implements and runs tests, Judge evaluates and auto-retries up to 3 times before escalating to the user. File-based state tracking survives session interrupts. Use when the user says "self-healing pip

• skill-audit

  Audit your Claude Code skills directory, CLAUDE.md, and recent session patterns to surface candidates for new skills -- gaps, redundancies, and formalization opportunities -- and to catch skill hygiene failures: runtime artifacts (venv, __pycache__, node_modules) living inside a skill directory, and

• skill-maintenance

  Audit Claude Code skills for content quality against Anthropic best practices. Use when a scheduled maintenance cycle runs, when the user asks to check skill quality, or when reviewing skills before publishing.

• spec-gap-detector

  Stress-test any agent prompt or specification for ambiguity, missing constraints, and edge cases that would cause random behavior at scale.

• swarm-discovery

  Map an unfamiliar repository with a cheap, verified agent swarm before any planning work: one read-only Haiku worker per module fills a fixed card, Sonnet skeptics vote on every claim of a flagged card, Haiku hunters look for missed IO and risks until two quiet rounds, and one Opus agent writes the

• tool-audit

  Audit a tool already in your stack against a semantic-depth rubric and emit a clear decision — Extend, Wrap, Replace, or Wait — with a one-page memo. Use when evaluating whether a current tool is worth keeping, improving, or replacing; when a tool is causing agent failures; or the user says "/tool-a

• tool-build-guide-generator

  Generate a hands-on, machine-ready build guide for any tool or library — takes a tool name and produces a runnable, annotated project that closes the gap between \"I've heard of it\" and \"I can build with it\". Not a hello-world demo; a real build that develops genuine fluency. Trigger: \"build gui

• tool-fluency-builder

  Turn any AI tool or framework from "heard of it" to "can build with it" by generating a machine-ready, hands-on build guide. Goes beyond hello-world to produce a real, runnable project with annotated steps, pitfalls, and judgment calls. Closes the gap between familiarity and practical fluency.

• tool-migration-brief

  Converts enterprise tool audit results (which tools fail agent-infrastructure tests) into a leadership-ready migration brief — covering what to replace, build, or wrap, with risk, sequencing, and budget framing. Output is a 1–2 page executive document suitable for a CTO, VP Engineering, or departmen

• validated-data-migration

  Migrate a shoebox of inconsistent files (CSV, Excel, JSON, PDFs, VCF) into a clean SQLite database with rejection logic, enum normalization, duplicate merges, source provenance, row-count checks, conflict tables, and a human review queue. Use when onboarding a client with legacy data or cleaning up

• video-to-skill

  Create Claude Code skills from screen recordings of manual processes. Records tacit knowledge by sending screen capture video to Gemini video understanding API, extracting a comprehensive SOP, then converting that SOP into a production skill via skill-creator. Use when the user says "record to skill

Similar plugins