ForgeyClap
- 130 skills
- 0 followers
- 2 repo stars
- 3 days ago last updated
- ▌ Subagent Driven Development · forgeyclap bundleUse to run a plan's independent tasks via subagents.
- ▌ Finishing A Development Branch · forgeyclap bundleUse when work is done and tests pass: integrate it.
- ▌ Verification Before Completion · forgeyclap bundleUse before claiming done or passing: evidence first.
- ▌ Forge Token Economy · forgeyclap bundleUse for token or cost questions (hoe vol zit je, kosten) or caveman mode.
- ▌ Forge Windows Shell · forgeyclap bundleUse when running or writing commands on Windows (PowerShell, Git Bash); stop one PID by port (poort bezet).
- ▌
- ▌
- ▌ Forge Security Review · forgeyclap bundleUse for a security review of a diff, app or CI (is dit veilig, gelekte keys).
- ▌ Forge Skill Authoring · forgeyclap bundleUse when writing or slimming a skill (nieuwe skill, skill triggert niet).
- ▌ Receiving Code Review · forgeyclap bundleUse when receiving review feedback, before acting on it: verify first.
- ▌
- ▌ Forge Long Form Writing · forgeyclap bundleUse when writing an article, blog or newsletter (schrijf een artikel).
- ▌ Forge Research Evidence · forgeyclap bundleUse when a research result rests on sources (onderzoek met bronnen, citaten checken).
- ▌
- ▌ Forge Team Orchestration · forgeyclap bundleUse when splitting a job over 2+ parallel Bosses or lanes (werk verdelen).
- ▌ Resolving Merge Conflicts · forgeyclap bundleUse when resolving an in-progress git merge or rebase conflict.
- ▌
- ▌
- ▌
- ▌ Forge I18N Docs · forgeyclap bundleUse when writing or fixing project docs (README, changelog) or i18n (meertalig).
- ▌ Forge UI Polish · forgeyclap bundleUse when a built UI needs a final polish (oppoetsen, strakker maken, ziet er goedkoop/AI-achtig uit).
- ▌ Frontend Design · forgeyclap bundleDistinctive visual design for new or restyled UI. Use when building UI.
- ▌ Forge Plan Large · forgeyclap bundleUser-invoked only: /forge-plan-large. Plans work too big for one session (groot plan, meerdere sessies, roadmap, plan in kaart): local ticket map, frontier, fog, step briefs.
- ▌ Setup Pre Commit · forgeyclap bundleSet up Husky pre-commit hooks with lint-staged, Prettier, typecheck and tests. User-invoked only.
- ▌ Forge Ecc Adapter · forgeyclap bundleUse when running an ECC skill or command that hard-codes ~/.claude/skills paths (ECC skill draaien).
- ▌ Forge Web Quality · forgeyclap bundlePlaybook for web speed and SEO: Core Web Vitals (gebruik bij sneller maken).
- ▌
- ▌ Forge Autoresearch · forgeyclap bundleUser-invoked only: /forge-autoresearch. Bounded keep-or-revert experiment loop on one measured metric (speed, size, score): frozen harness, one change per round, decision log.
- ▌ Forge Prompt Coach · forgeyclap bundleUse on vague asks (maak het beter, doe iets): make them buildable.
- ▌ Forge Observability · forgeyclap bundleUse for traces, metrics, logs, Sentry or incidents (monitoring, storing).
- ▌
- ▌
- ▌ Poteto Mode · forgeyclap bundleUser-invoked only: /poteto-mode. Lauren Tan's (poteto) working style in Forge words: goal first, steer by named principles, prototype instead of asking, evidence labels, fresh agents.
- ▌ Forge Devops · forgeyclap bundleUse for Docker, CI/CD, GitHub Actions, Terraform or deploys (deployen).
- ▌ Forge Memory · forgeyclap bundleUse when recalling earlier work or a lesson (hoe deden we X eerder).
- ▌
- ▌ Brainstorming · forgeyclap bundleUse before creative work (features, behavior changes): explore intent.
- ▌ Forge Context · forgeyclap bundleUse when context degrades (context vol, vergeet instructies) or before /compact.
- ▌
- ▌
- ▌ Forge Release · forgeyclap bundleUse when cutting a release (nieuwe versie, changelog, semver bump).
- ▌ Forge Testing · forgeyclap bundleUse when writing or fixing tests: Playwright, Vitest, flaky (test faalt soms).
- ▌
- ▌ Forge Database · forgeyclap bundlePlaybook for databases: Postgres, Prisma, migrations (gebruik bij database).
- ▌
- ▌
- ▌ Grilling · forgeyclap bundleGrills the user to stress-test a plan. Use on any grill trigger phrase.
- ▌ Ponytail · forgeyclap bundleUse for the smallest complete change (ponytail, minder code, kleinste diff).
- ▌ Forge Prd 2 · forgeyclap bundleUse before a non-trivial feature (schrijf een PRD, spec this out): PRD + tickets.
- ▌
- ▌ Forge A11Y · forgeyclap bundlePlaybook for WCAG 2.2 audits: axe, keyboard (gebruik bij toegankelijkheid).
- ▌ Forge Fullstack 2 · forgeyclapForge playbook for full-stack apps with frontend + backend + database + auth. Use when building a complete application, web app, SaaS, CRUD app, or data-backed dashboard with a database and login — keywords: full-stack, app, SaaS, backend, API, database, Postgres, Supabase, auth, login, JWT, session, signup, CRUD, end-to-end. Coordinates frontend, backend, DB, and auth specialists across git worktrees.
- ▌ Forge Heartbeat 2 · forgeyclapDetect a dispatched agent that has gone silent mid-run — reads the run's events.jsonl and flags any started-but-not-finished agent that hasn't logged anything for longer than a window (default 10 minutes). Use during multi-agent runs, periodically or whenever a run feels quiet, and as a check forge-doctor can call later.
- ▌ Forge Prediction 2 · forgeyclapForge playbook for prediction, sports-data, and analysis systems (incl. Telegram tip delivery). Use when building forecasting, sports betting analysis, odds/value models, or statistical prediction with confidence labels — keywords: prediction, forecast, sports, betting, odds, value bet, model, backtest, statistics, confidence, Telegram tips, bot. Enforces uncertainty labels, backtesting, and NO automatic real-money betting.
- ▌ Forge Integration 2 · forgeyclapForge playbook for business automation and API integrations — Gmail, Calendar, CRM, webhooks, Slack, payments. Use when connecting services, automating a business process, or wiring webhooks/OAuth between apps — keywords: integration, API, Gmail, Google Calendar, CRM, HubSpot, webhook, OAuth, Slack, sync, notification, automation. Enforces secret hygiene, webhook auth, input validation, and draft-only outreach.
- ▌ Forge Agent Report 2 · forgeyclapStructured 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).
- ▌ Forge N8n 2 · forgeyclapForge playbook for building and validating n8n automation workflows. Use when creating, fixing, or validating an n8n workflow — keywords: n8n, workflow, webhook, automation, node, trigger, schedule, cron, retry, error branch, credentials, validate_workflow. Orchestrates the ECC n8n skills and n8n MCP tools and enforces the validation gate before claiming production-ready.
- ▌ Forge RAG 2 · forgeyclapForge playbook for AI chatbots and RAG systems. Use when building a chatbot, assistant, RAG, or knowledge-base Q&A over documents — keywords: chatbot, RAG, retrieval, embeddings, vector search, ingestion, system prompt, knowledge base, assistant, hallucination, source-aware, lead capture. Covers retrieval logic, grounding, fallback behavior, and safety.
- ▌ Forge Doctor 2 · forgeyclapRun Forge's self-test + secret/leak scan — node --check every source, run all test suites, verify the honesty gate still rejects unknown events, confirm the dashboard SPA is intact, and scan git-tracked files for leaked secrets. Use before shipping, after big changes, or when the owner asks "test everything / does it execute / find leaks".
- ▌ Forge Mindmap 2 · forgeyclapGenerate a mind map (nodes + edges from an indented outline) to visualize a plan, architecture, or mission decomposition (Forge Mission Control Phase 2, WP4 "Mind Map"). Use when a plan or architecture has enough branching structure that a graph reads clearer than prose. Trigger on "make a mind map", "map this out", "visualize the plan/architecture", "break this mission down visually".
- ▌ Forge Website 2 · forgeyclapForge playbook for websites, landing pages, and frontend UI. Use when building or improving a website, landing page, marketing site, dashboard UI, or frontend — keywords: website, landing page, hero, CTA, responsive, mobile layout, UI, UX, accessibility, a11y, SEO, page speed, Lighthouse, frontend, React, Vue, Tailwind. Covers UI/UX, responsiveness, accessibility, SEO, performance, forms, and screenshot-loop review.
- ▌ Forge Registry 2 · forgeyclapBuild the GLOBAL, opt-in, read-only Forge Project Registry — a cross-project index of every Forge project (status, last run, open tickets, port) plus a self-contained home-view HTML. Use when the owner wants a bird's-eye view across all their Forge projects.
- ▌ Forge Scraping 2 · forgeyclapForge playbook for SAFE, legal web scraping and data collection. Use when scraping, crawling, harvesting, or collecting data from websites or APIs — keywords: scrape, scraping, crawler, spider, data collection, harvest, extract data, API pull, lead list, contacts. Enforces public/official/permitted sources only, rate limits, and DRAFT-ONLY outreach.
- ▌ Forge Deeplearn 2 · forgeyclapOn-demand, READ-ONLY full-codebase priming scanner (Forge Mission Control Phase 2, WP2 "Deep Learn Mode"). Use before generating a PRD, before a big refactor, or whenever the Lead is dropped into a new/unfamiliar project and needs an honest project-summary + risk-list before planning. Trigger on "deep learn", "prime the codebase", "scan the project", "learn this codebase before we plan".
- ▌ Forge Report 2 · forgeyclapProduces 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 Intake 2 · forgeyclapPrompt Master intake for Forge. Use at the START of any /forge BUILD/create/automate task to capture the project's real goal before building — presents the owner ONE clarifying-question list (subagent-brainstormed, project-type-aware), then feeds the answers into the PRD and Boss dispatch prompts. Also governs that every Boss dispatch is Prompt Master-shaped and lint-checked. Keywords: intake, requirements, clarify, goal, scope, questions, kickoff, brief, PRD.
- ▌ Forge Router 2 · forgeyclap bundleForge V2 router and agent-selection brain. Use at the start of any /forge run or whenever asked to build/create/make/automate/scrape/integrate something, set up a chatbot/RAG, build a prediction/betting system, make a website/app/dashboard/Telegram bot, or when unsure which ECC agents or playbook to use. Classifies a task by DOMAIN and COMPLEXITY (L1–L4), selects the smallest fitting team of real ECC agents/skills/commands, decides parallel vs serial, sets the review gates, and loads the matching forge-* domain playbook.
- ▌ Forge Verify 2 · forgeyclapRun Forge's verify-loop — after an agent (or a work package) claims to be done, check whether that claim actually holds against events.jsonl and the ticket store, and send the task back to the agent when it doesn't. Use after every agent/work-package completion in a /forge run, and again at the end of the run before the final report.
- ▌ Ship Readiness 2 · forgeyclapADVISORY pre-deploy / pre-handoff checklist (not a blocker). Use when preparing a project for deployment, release, or client/handoff to sanity-check it's genuinely ready — covers websites/landing pages, full-stack apps, APIs, dashboards, n8n workflows, scraping, AI/RAG chatbots, prediction systems, Telegram bots, and business automations. Trigger on "deploy", "ship", "go live", "release", "hand off".
- ▌ Forge Graded Verify 2 · forgeyclapAdvisory GRADED verification for high-stakes answer-quality Forge tasks (RAG/research/scraping/prediction). Use when output quality is subjective and needs per-criterion scoring + actionable feedback — ALONGSIDE (never replacing) forge-verify (structural) and forge-evals (deterministic binary gate). Keywords: graded, rubric, quality, verify, review, answer quality, RAG quality, source grounding.
- ▌ Forge API · forgeyclapForge playbook for contract-first APIs. Use for API, REST, GraphQL, gRPC, OpenAPI, endpoint, auth, JWT, versioning, rate limit, idempotency, contract test, backend.
- ▌ Forge CLI · forgeyclapForge 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 Cms · forgeyclapForge 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 N8n · forgeyclapForge playbook for building and validating n8n automation workflows. Use for n8n, workflow, webhook, trigger, cron, retry, error branch, credentials, validate_workflow.
- ▌ Forge RAG · forgeyclapForge playbook for AI chatbots and RAG systems. Use for chatbot, RAG, retrieval, embeddings, vector search, knowledge base, hallucination, source-aware, lead capture.
- ▌ Forge Bots · forgeyclapForge playbook for chat bots — Discord, Slack, Telegram. Use for bot, slash command, webhook, signature verification, OAuth scopes, rate limit, dead-letter, interaction handler.
- ▌ Forge Data · forgeyclapForge 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 Game · forgeyclapForge 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.
- ▌ Gsap · forgeyclap bundleGSAP web-animation toolkit for Forge website/frontend work — timelines, ScrollTrigger, React integration, plugins, performance. Use when building advanced scroll, reveal, hover, or hero animations. Read the matching reference below when you need the detail (progressive disclosure).
- ▌ Forge Agent · forgeyclapForge 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 Debug · forgeyclapForge systematic-debugging playbook. Use for ANY bug, crash, stack trace, failing test, or regression — debug, root cause, bisect, flaky test — before proposing a fix.
- ▌ Forge Figma · forgeyclapForge 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 Mlops · forgeyclapForge 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 Scout · forgeyclapForge 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 Voice · forgeyclapForge 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 Doctor · forgeyclapRuns 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 Intake · forgeyclap bundlePrompt 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 Mobile · forgeyclapForge 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 Report · forgeyclapProduces 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 Router · forgeyclap bundleForge 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 Verify · forgeyclap bundleRuns 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 Mindmap · forgeyclapGenerates 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 Website · forgeyclapForge playbook for websites, landing pages, and frontend UI. Use for website, landing page, responsive, mobile layout, SEO, accessibility, Lighthouse, React, Vue, Tailwind.
- ▌ Forge Docdrift · forgeyclapDetects 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.
- ▌ Forge Electron · forgeyclapForge playbook for Electron desktop apps. Use for electron, desktop app, .exe, installer, IPC, contextBridge, contextIsolation, nodeIntegration, code signing, auto-update.
- ▌ Forge Guardian · forgeyclapScaffold design doctrine for an owner-gated production self-healing guardian (not live). Use only when designing auto-rollback, incident response, canary, circuit breaker automation.
- ▌ Forge Payments · forgeyclapForge playbook for payment/checkout/billing — Stripe, Mollie, Adyen, PayPal. Use for payment, checkout, subscription, refund, webhook signature, idempotency key, PCI, 3D Secure.
- ▌ Forge Registry · forgeyclapBuilds 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.
- ▌ Forge Scraping · forgeyclapForge 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.