newmindsgroup
- 1.5k skills
- 0 followers
- 2 repo stars
- 3 days ago last updated
- ▌ Calendar Scheduler · newmindsgroupFinds available time, proposes slots, and books meetings on the user's behalf. Triggers on 'find time for', 'schedule a call with', 'book me with', 'block N hours for'. Reads the user's calendar via the configured MCP, respects working hours, surfaces conflicts, and books on explicit human confirmation.
- ▌ Design Methodology · newmindsgroup bundleApplies a structured design process to logo design, brand identity, web design, and app design. Enforces the loop Discovery → Diagnosis → Principles → Exploration → Critique → Lock → Propagate. Use when the user asks to create, redesign, iterate on, or critique a logo, wordmark, monogram, favicon, brand identity, visual identity, color system, typography system, design tokens, website, landing page, or app UI. Also triggers on 'apply golden ratio', 'make this award-winning', 'is this the best option', 'brutally honest critique', 'lock and propagate', or when a user uploads a mockup, wordmark, or design file for analysis. Encodes the correct scope of golden ratio (enclosed proportions, not letter-spacing), a seven-stage iteration playbook, an eight-criterion award test, and a self-critique honesty protocol — all distilled from a real brand-system build.
- ▌ Newsletter Drafter · newmindsgroupDrafts a newsletter issue from RSS sources, the brand voice playbook, and a master HTML template. Stages the draft in the user's email platform AND saves a copy to the repo for review. Pings the review channel for human approval. Never auto-sends. Triggers on 'draft this week's newsletter', 'write the newsletter', 'pull RSS items into a newsletter', or as a scheduled weekly run.
- ▌ Context7 CLI · newmindsgroup bundleUse the ctx7 CLI to fetch library documentation, manage AI coding skills, and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7", needs current docs for any library, wants to install/search/generate skills, or needs to set up Context7 for their AI coding agent.
- ▌ Get API Docs · newmindsgroupUse this skill when you need documentation for a third-party library, SDK, or API before writing code that uses it — for example, "use the OpenAI API", "call the Stripe API", "use the Anthropic SDK", "query Pinecone", or any time the user asks you to write code against an external service and you need current API reference. Fetch the docs with chub before answering, rather than relying on training knowledge.
- ▌ Competitive Monitor · newmindsgroupDaily scan of curated competitor / peer / inspiration sites for new posts, pricing changes, positioning shifts, and hiring signals. Diffs each fetch against the previous snapshot and surfaces material changes via the review channel. Compounds intel without manual checking. Triggers on 'competitive scan', 'check competitor changes', 'monitor [domain]', or as a scheduled daily run.
- ▌ Voice Drift Scanner · newmindsgroupScans recently published or scheduled content (social posts, marketing emails, blog posts, scheduled drafts) against a brand's voice playbook, banned-phrase list, and entity-separation rules. Surfaces deviations before they compound. Triggers on 'audit my recent posts', 'check brand voice on my content', 'scan for banned phrases', 'voice drift check', 'is anything off-brand', or as a scheduled daily/weekly run. Read-only — flags drift, does not edit live content.
- ▌ Agent Browser · newmindsgroup bundleBrowser 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. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
- ▌ Brand Ssot Precedence · newmindsgroupApply this skill on every session in any project that has brand context. Defines the precedence chain for brand single sources of truth (SSOT) — AGENTS.md, DESIGN.md, voice playbook, design tokens, brand-config.yml — so the agent reads brand canon BEFORE producing any human-facing copy or visual artifact. The chain is: AGENTS.md (project rules) → DESIGN.md (visual SSOT) → voice playbook (voice DNA) → tokens.json (machine-canonical token values, wins on conflicts with DESIGN.md). Triggers proactively before any drafting, designing, or imagery-generation work — even when the user doesn't explicitly mention brand canon. Project-agnostic — works for any company with documented brand standards.
- ▌ Social Content Drafter · newmindsgroupDrafts day-themed social content for the user's brand — typically one LinkedIn post + one X thread + one IG caption per day. Stages each as a scheduled draft via the configured social MCP. Pings the review channel with previews and per-platform approval. Never publishes. Triggers on 'draft today's social posts', 'write me a LinkedIn post about X', 'social drafts for the week', or as a daily scheduled run.
- ▌ Brand Blueprint Builder · newmindsgroup bundleBuilds a comprehensive brand blueprint for any business — personal brand, founder brand, agency, product company, or service business. Produces a multi-document brand system covering identity, narrative, visual identity, messaging, services & revenue, content engine, and AI operating manual. Use when the user asks to 'build a brand blueprint', 'create a brand book', 'document our brand', 'set up brand foundation', 'do a brand audit and lock decisions', 'write our positioning', 'create brand guidelines', 'redo our brand strategy', or starts a new venture and needs a complete brand foundation. Walks through the work in eight ordered sections with explicit prompts; outputs both supporting documents AND a master blueprint that synthesizes them. Generic across personal vs. commercial brands.
- ▌ Self Improvement Review · newmindsgroupWeekly meta-review of the agent's own performance. Reads pattern memories from the past 7 days plus the owner's revisions/critiques on agent-generated drafts, then drafts proposed updates to CLAUDE.md / system prompt voice rules. Pings review channel for owner's approve/skip decision. Compounds the agent's voice fidelity over time. Triggers on 'review your performance', 'propose improvements to your prompt', 'self-improvement check', or as a scheduled Sunday-evening run.
- ▌ Tool Leverage Heuristics · newmindsgroupApply this skill on every session to make the agent strategic about which tools and sub-agents it reaches for. Maps natural-language triggers ("AI-search visibility", "production is down", "map this codebase", "ready to ship?") to specific tool/agent combos that should fire together. Loads as a system-prompt directive — the agent reads the trigger table before deciding how to handle each user message and proactively reaches for the right tools without being asked. Companion to runbooks/tool-leverage-heuristics.md (the human-readable version of the same patterns).
- ▌ Prompt Engineering Expert · newmindsgroup bundleDesigns, improves, converts, debugs, and operationalizes prompts, system instructions, agent definitions, and reusable AI-agent behavior. Works autonomously by default: reads the project, infers intent, and produces a finished prompt with stated assumptions in one pass; runs a guided one-question-at-a-time interactive mode on request. Use when the user is writing or refining a prompt, a system prompt, GPT/agent instructions, an AGENTS.md or CLAUDE.md, a Cursor rule, or asks to make a prompt better, convert a prompt between platforms, debug poor prompt output, or cut a prompt's token usage. Triggers on: 'write a prompt', 'improve this prompt', 'prompt for', 'system prompt', 'agent instructions', 'convert this prompt', 'why is this prompt failing', 'reduce tokens', 'prompt engineering'.