Claude Skills by ForgeyClap

Structured completion-report contract for every dispatched Boss, validated by forge-report.cjs. Use when dispatching a subagent or ingesting its final report — completion contract, validation.

Forge playbook for AI agents, LLM apps, and eval harnesses. Use for agent, LLM app, tool-calling, function calling, MCP tool, prompt injection, eval, benchmark, guardrail, fallback.

Forge playbook for contract-first APIs. Use for API, REST, GraphQL, gRPC, OpenAPI, endpoint, auth, JWT, versioning, rate limit, idempotency, contract test, backend.

Forge playbook for chat bots — Discord, Slack, Telegram. Use for bot, slash command, webhook, signature verification, OAuth scopes, rate limit, dead-letter, interaction handler.

Forge structured-ideation playbook. Use BEFORE building when the approach isn't obvious — brainstorm, options, trade-offs, alternatives, design direction, which way to build.

Forge playbook for CLIs and dev tools. Use for CLI, command line, argparse, flag, --help, exit code, stdin, stdout, pipe, dry-run, cross-platform, terminal, subcommand.

Forge playbook for CMS work — WordPress and headless CMS. Use for CMS, WordPress, theme, plugin, custom post type, WP-CLI, Contentful, Sanity, Strapi, Payload, content model.

Forge code-review method — order, severity levels, Codex handoff. Use before any commit or when asked to review code — code review, check my code, PR review, before I commit.

Forge playbook for data engineering — ETL/ELT, dbt/SQL pipelines. Use for data pipeline, warehouse, Snowflake, BigQuery, dbt, incremental load, schema contract, data quality, PII.

Forge systematic-debugging playbook. Use for ANY bug, crash, stack trace, failing test, or regression — debug, root cause, bisect, flaky test — before proposing a fix.

Read-only full-codebase priming scanner. Use before a PRD or big refactor, or onboarding into an unfamiliar project — deep learn, prime the codebase, scan the project, risk list.

Detects drift between cited external docs (Claude Code, n8n nodes) and what our skills claim. Use before major n8n work or on /forge docs-check — doc drift, source verification, staleness.

Runs Forge's self-test + secret-leak scan across source, tests, and dashboard. Use before shipping or when asked to test everything, check it executes, or find leaks.

Forge playbook for e-commerce and cashflow shops. Use for shop, store, cart, checkout, product, inventory, Shopify, WooCommerce, Etsy, Stripe, order fulfillment, oversell.

Forge playbook for Electron desktop apps. Use for electron, desktop app, .exe, installer, IPC, contextBridge, contextIsolation, nodeIntegration, code signing, auto-update.

Forge playbook for browser extensions (Chrome/Edge MV3). Use for chrome extension, manifest v3, service worker, content script, permissions, CSP, Web Store, store policy.

Forge playbook for design-to-code. Use for figma, design to code, mockup, design tokens, pixel-perfect, responsive, breakpoints, style guide, dev mode, handoff, accessibility.

Forge playbook for full-stack apps — frontend + backend + database + auth. Use for full-stack, SaaS, CRUD app, Postgres, Supabase, JWT, session, signup, dashboard.

Forge playbook for games — Canvas/WebGL/Phaser/Godot. Use for game, browser game, gameplay, game loop, win/lose state, soft-lock, frame rate, collision, save load, playtest.

Advisory graded quality scoring for RAG/research/scraping/prediction output. Use alongside forge-verify for subjective answer quality — rubric, per-criterion score, source grounding.

Scaffold design doctrine for an owner-gated production self-healing guardian (not live). Use only when designing auto-rollback, incident response, canary, circuit breaker automation.

Detects a dispatched agent gone silent mid-run from events.jsonl. Use during multi-agent runs or when a run feels quiet — silent agent, stalled run, heartbeat check, timeout.

Prompt Master intake — captures the real goal via one clarifying-question list before building. Use at the START of any /forge build/create/automate task — intake, requirements, scope, PRD.

Forge playbook for business automation and API integrations — Gmail, Calendar, CRM, webhooks, Slack, payments. Use for integration, OAuth, sync, notification, automation.

Forge doctrine for using MCP servers as a client — opt-in, tiered, least-privilege. Use when a Boss needs an external tool grant or when installing/discussing an MCP server.

Forge playbook for legacy modernization without a big-bang rewrite. Use for migration, legacy, port, upgrade, strangler fig, characterization test, parity, feature flag, cutover.

Generates a mind map (nodes+edges) to visualize a plan or architecture. Use when a plan has enough branching that a graph reads clearer than prose — mind map, visualize the plan.

Forge playbook for production ML systems (opt-in Python) — training-to-serving lifecycle. Use for MLOps, model registry, MLflow, drift monitoring, A/B test, canary, rollback.

Forge playbook for mobile apps — React Native/Expo/Flutter. Use for mobile app, iOS, Android, Expo, EAS, Flutter, apk, ipa, secure storage, deep link, App Store, Play Store.

Forge playbook for building and validating n8n automation workflows. Use for n8n, workflow, webhook, trigger, cron, retry, error branch, credentials, validate_workflow.

Overnight session-limit-resilient builder — work-package queue, auto-resume, morning briefing. Use for run this overnight, keep going while I'm away, resume tomorrow, opt-in only.

Forge playbook for payment/checkout/billing — Stripe, Mollie, Adyen, PayPal. Use for payment, checkout, subscription, refund, webhook signature, idempotency key, PCI, 3D Secure.

Forge playbook for prediction, sports-data, and betting analysis (incl. Telegram tips). Use for forecast, odds, value bet, backtest, confidence label — NO real-money betting.

Generates a top-tier project-specific CLAUDE.md. Use when a project has no CLAUDE.md or a thin/generic one — project brain, onboarding, project identity, hard rules, governance.

Forge playbook for AI chatbots and RAG systems. Use for chatbot, RAG, retrieval, embeddings, vector search, knowledge base, hallucination, source-aware, lead capture.

Builds the global, opt-in, read-only Forge Project Registry across all projects. Use when the owner wants a bird's-eye view of status, last run, tickets, and ports.

Produces the standard end-of-task Forge report — project adaptation, agent ledger, memory update. Use when delivering the result of any non-trivial /forge build, fix, or review.

Forge V2 router — classifies a task by domain/complexity and selects the smallest fitting agent team. Use at the START of any /forge run or build/create/automate request.

Forge doctrine for researching and vetting external skills, plugins, MCP servers, and CLIs. Use for find a skill for X, check if there's a plugin/MCP for Y — approve/hard-pass gate.

Forge playbook for SAFE, legal web scraping and data collection. Use for scrape, crawler, spider, harvest, extract data, API pull, lead list — public/permitted sources only.

Standard test protocol for a new/changed Forge skill: activation-test (trigger vs near-miss phrases, target >=95%) + opt-in fresh-session A/B benchmark. Use when creating or editing any skill.

Regenerates FORGE_SNAPSHOT.md from real project sources so no session loses the mission across compaction. Use on /forge snapshot or let PreCompact/SessionStart hooks trigger it.

Runs Forge's verify-loop — checks a completion claim against events.jsonl and the ticket store, sends it back if false. Use after every agent/work-package completion in a run.

Forge playbook for AI voice/phone agents — Dutch-first calls, turn-taking, safe handling. Use for voice agent, voicebot, phone, IVR, Twilio, Vapi, ElevenLabs, TTS, STT, barge-in.

Forge playbook for websites, landing pages, and frontend UI. Use for website, landing page, responsive, mobile layout, SEO, accessibility, Lighthouse, React, Vue, Tailwind.

Forge safe-parallel-work playbook using git worktrees. Use when more than one Boss writes code in the same repo at once — parallel agents, worktree, isolate, avoid conflicts.

Advisory pre-deploy/pre-handoff checklist (not a blocker). Use when preparing a project for deployment, release, or client handoff — deploy, ship, go live, release, hand off.

Global lightweight Forge Core. Use for any goal-shaped build/create/automate/fix/research request, or triggers: install Forge V2 into this project, use Forge system, gebruik Forge systeem, start Forge dashboard. Runs the Forge Command Center at 127.0.0.1:4100.

Structured completion-report contract every dispatched Boss ends its final message with, plus the forge-bin/forge-report.cjs tool that parses, validates, and ingests it. Use when dispatching any subagent (include the contract requirement in the prompt) and when a dispatched agent's final message comes back (validate/ingest it before treating the work as done).

Global lightweight Forge Core. Use for any goal-shaped build/create/automate/fix/research request, or triggers: install Forge V2 into this project, use Forge system, gebruik Forge systeem, start Forge dashboard. Runs the Forge Command Center at 127.0.0.1:4100.