Search Results for "phrazzld" | AgentCC

brand

Full brand-as-code pipeline: discovery, identity, tokens, assets, logo, video. Creates brand.yaml, compiles to CSS/Tailwind/TypeScript tokens, generates OG cards, social images, logos, and branded video. One command from zero to full brand system. Use when establishing or updating brand identity.

GitHub App Scaffold

Scaffold and implement GitHub Apps from existing automation ideas using Probot + @octokit/app. Use when turning scripts, bots, or manual GitHub workflows into a proper GitHub App.

Agentic UI Contract

Design and implement agentic product flows using the contract: model decides what to do, tools decide how it is done, UI schema decides how it is rendered. Use for chat-first apps, tool-calling agents, generative UI systems, and planner/tool architecture decisions. Keywords: agentic UX, tool calling, planner, generative UI, function tools.

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

visual-qa

Browser-based visual QA for frontend changes. Opens the running app, takes screenshots, identifies layout/styling/UX issues. Use when: frontend changes are code-complete, before commit or PR. Composes: agent-browser for automation, taste-skill for anti-slop analysis.

observability

Complete observability infrastructure. Error tracking, alerting, logging, health checks. Optimized for indie dev: minimal services, CLI-manageable, AI agent integration.

pencil-renderer

Render DNA codes to Pencil .pen frames. Does ONE thing well. Input: DNA code + component type (hero, card, form, etc.) Output: .pen frame ID + screenshot Use when: design-exploration or other orchestrators need to render visual proposals using Pencil MCP backend.

Bitcoin

Complete Bitcoin payment lifecycle. Audits current state, fixes all issues, and verifies payment flows work end-to-end. Every run does all of this. Auto-invoke when: files contain bitcoin/btc/utxo/satoshi, imports bitcoin packages, references BITCOIN_* or BTC_* env vars, wallet handlers modified.

external-integration-patterns

Patterns for reliable external service integration: env validation, health checks, error handling, observability. Invoke when integrating Stripe, Clerk, SendGrid, or any external API.

mobile-migrate

Add an Expo + EAS React Native mobile app to an existing web project, sharing logic, design tokens, auth, and backend integrations. Use when migrating a web codebase into a web+mobile monorepo.

moneta-ingest

Parse new financial documents into Moneta. Detect type, run parser, validate output, summarize reconciliation.

audit

Audit any domain: stripe, bitcoin, lightning, btcpay, payments, docs, landing, observability, onboarding, posthog, production, product-standards, virality, bun. Run /audit <domain> for structured P0-P3 findings report. /audit --all for everything. Invoke for: domain audit, compliance check, launch readiness, gap analysis.

naming-conventions

Apply universal naming principles: avoid Manager/Helper/Util, use intention-revealing names, domain language, verb+noun functions. Use when naming variables, functions, classes, reviewing names, or refactoring for clarity. Language-agnostic principles.

shape

Full interactive planning for a single idea. Product spec, technical design, breadboarding, and implementation planning in one conversational session. Use when: planning a feature, shaping an idea, writing specs, designing architecture. Trigger: /shape, /spec, /architect, /brainstorm, /breadboard, /shaping, /critique.

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Produces a structured report with full reproduction evidence -- screenshots, repro videos, and detailed repro steps for every finding.

tax-check

Validate tax calculations: bracket math, deduction eligibility, Form 8949 format, audit-risk flags.

posthog

Complete PostHog lifecycle management. Audits current state, fixes all issues, and verifies event tracking works end-to-end. Every run does all of this. Auto-invoke when: files contain posthog/analytics/tracking, imports posthog-js package, references POSTHOG_* env vars, event tracking code modified, user mentions "analytics not working" or "events not sending".

Guardrail

Generate custom lint rules from architectural patterns. ESLint local plugins (JS/TS) or ast-grep YAML rules (Python/Go/Rust/any). Invoke when: codifying an import boundary, enforcing API conventions, blocking deprecated patterns, or any "always/never" constraint.

finances-snapshot

Capture current financial state into the append-only ledger at ~/Documents/finances/. Updates prices (BTC, gold, silver), reads current balance sheet CSVs, and appends a timestamped snapshot to data/snapshots.jsonl and data/liabilities.jsonl. Use when: updating financial records, after exporting new balance sheets, weekly or monthly financial check-ins, tracking net worth. Keywords: net worth, balance sheet, snapshot, financial update, update finances, capture finances, record net worth.

done

Session retrospective, codification, and implementation feedback capture. Extracts learnings, updates docs, captures retro signals for future grooming. Invoke for: "done", "wrap up", "what did we learn", "retro", "session end", finishing multi-step work, after debugging hard problems.

issue

Issue quality primitives: lint, enrich, decompose. `/issue lint [#N|--all]` — Score issues against org-standards. `/issue enrich [#N]` — Fill gaps with sub-agent research. `/issue decompose [#N]` — Split oversized issues into atomic sub-issues.

pr-polish

Elevate a working PR: hindsight review, code refinement, test audit, docs, quality gates. Use when: PR works but could be better, pre-merge quality pass, retrospective review. Trigger: /pr-polish, 'polish this PR', 'elevate quality', 'hindsight review'.

autopilot

Full autonomous delivery from issue to PR. Finds highest-priority issue, specs it, designs it, builds it, ships it. Use when: shipping an issue end-to-end, autonomous delivery, sprint execution. Trigger: /autopilot, "ship this issue", "build and ship", "sprint execute".

bun

Complete Bun lifecycle management. Audits current state, plans migration, executes changes, verifies success. Full orchestrator for Bun adoption. Invoke for: migrate to bun, adopt bun, bun migration, switch to bun.

delegate

Multi-AI orchestration primitive. Delegate to specialized AI tools, collect outputs, synthesize. Use when: analysis, review, audit, investigation tasks need multiple expert perspectives. Keywords: orchestrate, delegate, multi-ai, parallel, synthesis, consensus, dag, swarm

debug

Systematic debugging and investigation for local and production issues. Four-phase protocol: root cause, pattern analysis, hypothesis test, fix. Use for: any bug, test failure, production incident, unexpected behavior, "investigate", "why is this broken", "debug this", "what went wrong".

next-patterns

Next.js patterns, best practices, cache components, and upgrade guides. Auto-invoke when: writing Next.js code, configuring next.config, using App Router, implementing caching, upgrading Next.js versions. Keywords: Next.js, App Router, RSC, use cache, PPR, cacheLife, cacheTag, metadata, route handlers, middleware, Suspense, hydration

visual-explainer

Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled HTML page instead.

Pencil to Code

Export .pen design to React/Tailwind code. Does ONE thing well. Input: .pen frame ID or file path Output: React component code + Tailwind config Use when: design-exploration or user needs implementation code from a finalized Pencil design.

flywheel-qa

Agentic QA for flywheel PRs. Navigate preview deploys with an Agent Browser, verify UI rendering, check for error boundaries, and test interactive flows. Use when: PR passes CI but needs runtime verification before merge.

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

changelog

Complete changelog and release notes infrastructure. Audits current state, implements missing components, verifies pipeline end-to-end. Covers semantic-release, commitlint, GitHub Actions, LLM synthesis, public changelog page, and RSS.

crypto-gains（crypto-gains）

Calculate capital gains with FIFO, wash sale detection, term classification, and Form 8949 outputs.

og-hero-image

Generate premium open-graph hero images for brands using AI. Use when: creating social sharing images, website headers, marketing collateral. Keywords: og image, open graph, hero image, social header, brand image

content

Content creation and optimization: copywriting, copy editing, social media, launch announcements, email sequences, and AI-writing cleanup. Covers the full content lifecycle from first draft to polished, on-brand output. Use when writing, editing, or publishing any marketing or product content.

pr-fix

Unblock a PR: resolve conflicts, fix CI, self-review, address feedback, refactor. One command takes a blocked PR to green and mergeable. Use when: PR blocked, CI red, unaddressed reviews, code review needed, refactoring. Trigger: /pr-fix, /fix-ci, /review-branch, /review-and-fix, /respond, /address-review, /refactor.

log-issues

Audit a domain then create GitHub issues for all findings. Handles: stripe, bitcoin, lightning, btcpay, docs, landing, observability, onboarding, posthog, production, product-standards, bun, virality. Deduplicates against open issues. Invoke for: backlog creation from audit, issue triage, gap tracking.

test-coverage

Test audit, TDD enforcement, and coverage analysis. Prefer Vitest. Runs coverage, identifies gaps, enforces test-first workflow. Use for: "run test audit", "coverage gaps", "write tests", "TDD", "testing philosophy", "vitest setup", "test quality review".

stripe

Complete Stripe lifecycle: audit, design, scaffold, configure, verify, and maintain payment integrations. Covers webhooks, subscriptions, checkout flows, billing UX, local development, reconciliation, and security. One skill for all Stripe work.

find-skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

LLM infrastructure

Audit and maintain LLM-powered features. Model currency, prompt quality, evals, gateway routing, observability, CI/CD. Ensures all AI features follow best practices. CRITICAL: Training data lags months. ALWAYS web search before LLM decisions.

ui-skills

Opinionated constraints for building better interfaces with agents.

pr

Full PR workflow from working directory to draft PR. Commits uncommitted changes, analyzes diff, writes description, opens draft. Use when: opening a pull request, shipping to review, creating PR. Trigger: /pr, "open PR", "create pull request", "ship to review".

monorepo-scaffold

Convert single-app repos into a Turborepo monorepo using pnpm workspaces. Use when splitting apps into apps/ and shared code into packages/ with cached pipelines.

triage

Full incident lifecycle: audit, investigate, fix, verify, postmortem, prevent. Multi-source observability triage via Sentry, Vercel, health endpoints, CI/CD. Use for: production down, error spikes, CI failures, incident response, "postmortem", "verify fix", "is production ok", user reports.

distill

Distill repo knowledge into CLAUDE.md and codify session learnings into durable improvements. Invoke at end of sessions or when onboarding a repo.

webapp-testing

Toolkit for testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing screenshots, and viewing browser logs. Reference skill for browser-based testing patterns.

audit-website

Audit websites for SEO, performance, security, technical, content, and 15 other issue categories with 230+ rules using the squirrelscan CLI. Returns LLM-optimized reports with health scores, broken links, meta tag analysis, and actionable recommendations. Use to discover and assess website or webapp issues and health.