skills/beam-next-learning/learn-projects/SKILL.md
Learn how Beam Next builds work. Load when user mentions: learn projects, how do builds work, builds vs skills, build tutorial, what is a project, build structure, build lifecycle, understand builds, explain builds. 8-10 min.
npx skillsauth add beam-ai-team/beam-next-skills learn-projectsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This is a learning skill. With Build-First onboarding, suggest AFTER first project, not before.
# In user-config.yaml
build_first.checkpoints.first_project_created: true → learn_projects auto-completed!
When user creates their first project, learn_projects is automatically marked complete via auto_complete_map. They learned by DOING.
Check both:
learning_tracker.completed.learn_projects - explicit completionbuild_first.checkpoints.first_project_created - auto-completionPROACTIVELY SUGGEST when user:
Suggestion Pattern (Post-Experience):
💡 You've already created a project! Want to understand the system more deeply?
'learn projects' covers:
- When to use builds vs skills (avoid anti-patterns)
- Build lifecycle and best practices
- How to track progress effectively
Say 'learn projects' for the deep-dive (8 min), or continue working.
If user already created build, acknowledge it:
You've got practical experience now! This tutorial will deepen your understanding
of WHY the system works this way.
DO NOT suggest if:
Teach how Beam Next builds work through examples and decision framework.
Help user understand when to create builds vs skills, how builds are structured, and the project lifecycle. Uses concrete examples before abstract concepts.
Time Estimate: 8-10 minutes
Show what IS and ISN'T a project:
[OK] BUILDS:
- Build client proposal for Acme Corp
- Research competitors and write analysis
- Create onboarding docs for new hires
[ERROR] NOT BUILDS (these are skills):
- Generate weekly status reports (repeating)
- Qualify incoming leads (repeating)
- Format documents (repeating)
Pattern: Builds END. Skills REPEAT.
Ask: "What work are YOU planning? Let's classify it."
Question 1: Direction or Work?
• Direction = Goal (goals.md)
• Work = Build or Skill
Question 2: Does it repeat?
• NO → PROJECT (has endpoint)
• YES → SKILL (reusable)
ANTI-PATTERN:
[ERROR] "weekly-report-week-1", "weekly-report-week-2"...
[OK] ONE "weekly-report" SKILL used every week
[DIR] 03-projects/05-client-proposal/
├── 01-planning/
│ ├── overview.md # What & why
│ ├── plan.md # How
│ └── steps.md # Tasks (checkboxes)
├── 02-resources/ # Reference materials
├── 03-working/ # Work in progress
└── 04-outputs/ # Final deliverables
PLANNING → IN_PROGRESS → COMPLETE → ARCHIVED
Explain each state briefly.
Ask: "Tell me 3 things you're planning to work on."
For each: apply decision framework together, explain reasoning.
To create a project, say:
• "create build for [description]"
• "new project: [name]"
Ready? Say "create build" to start one!
Actions (MUST complete all):
Mark skill complete in user-config.yaml:
learning_tracker:
completed:
learn_projects: true # ADD THIS LINE
Display completion:
[OK] Learn Builds Complete!
You now understand:
• Builds vs Skills (builds END, skills REPEAT)
• Decision framework (Direction → Work → Repeat?)
• Project structure (planning → resources → working → outputs)
• Lifecycle states (PLANNING → IN_PROGRESS → COMPLETE)
Next steps:
• 'create build' - Start your first project
• 'learn skills' - Learn about reusable workflows
• 'learn beam next' - System mastery
Session ending tip:
💡 When you're done, open a NEW chat for your next topic.
learning_tracker.completed.learn_projects: true in user-config.yamldevelopment
--- name: taste-skill type: skill version: '1.0' author: Leonxlnx (packaged by Zhichao Li) category: general tags: - frontend - design - anti-slop - landing-page updated: '2026-06-11' visibility: public description: Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check. license: MIT.
development
Use when communicating quantitative information in any form — Slack updates, emails, reports, decks, dashboards, landing pages, product UI, public talks. Covers two integrated layers: (1) making numbers semantically meaningful (translation, anchoring, simplification, story-pairing) and (2) showing numbers cleanly (chart vs table vs prose, chart-by-message, pre-attentive emphasis, color discipline, decluttering). Distilled and integrated from *Show Me the Numbers* (Stephen Few) and *Make Numbers Count* (Chip Heath & Karla Starr). Not for raw data analysis or statistics — this is about communication of numbers, not their derivation.
development
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
tools
Stateful multi-session tutor adapted for Beam — teach a stakeholder to understand, trust, and operate a specific agent, or teach a Solution Engineer a client's business process for delivery. Grounds every lesson in Knowledge Hub sources (real agent graphs, real tasks, transcripts, Linear) before any web resource. Also works for any general topic. Trigger on "teach me", "beam teach", "教我", "onboard <person> on <agent>", "help <stakeholder> understand the agent", "learn this client's process".