lucidlabs-hq
40 verified skills40 total stars
deploy
Deploy invoice-accounting-assistant to HQ server. Runs tests first (TDD), then builds and deploys. Use when ready to push changes to staging/production.
development1
n8n-workflow
Generate and manage n8n workflows for AI agents. Creates automation workflows that complement Mastra agents.
tools1
mastra-mcp
Configure Mastra as MCP Server to expose agents and tools via Model Context Protocol. Enables Claude Desktop and other MCP clients to use Mastra tools.
tools1
linear
Linear project management integration. Use for creating issues, updating status, and syncing work with Linear board.
testing1
create-prd
Create a Product Requirements Document from conversation. Use when starting a new project or defining product requirements.
documentation1
brainstorm
Structured pre-planning research. Explores codebase, asks clarifying questions, and produces a brainstorm output file for /plan-feature input.
development1
checkout-project
Clone an existing project from GitHub into the projects folder. Use when starting work on an existing downstream project.
testing1
budget
Track and report customer kontingent usage from Productive.io. Monitor budget consumption and warn on low kontingent.
business1
commit
Create a well-formatted git commit with PROJECT-STATUS.md updates. Use after completing implementation.
development1
.claude/skills/clone-skill
--- name: clone-skill description: Clone skills from central repository or import from clipboard. Use to add proven patterns to your project. disable-model-invocation: true allowed-tools: Read, Write, Bash, AskUserQuestion argument-hint: [skill-name] or --list or --import --- # Clone Skill Clone skills from the central Lucid Labs skills repository or import from clipboard. --- ## Usage ```bash /clone-skill [skill-name] # Clone specific skill from central repo /clone-skill --list
tools1
execute
Execute an implementation plan step by step. Use after planning is complete.
tools1
design-system-guard
Validate UI screens against Lucid Labs design system rules. Use after implementing UI components to verify adherence to brand colors, typography, layout patterns, and service board logic.
testing1
llm-evaluate
Evaluate LLM models for cost/performance ratio. Fetches current pricing and recommends optimal model for your use case. Use during project init or when optimizing costs.
testing1
mistral
Setup Mistral AI integration for a project. Use for EU-friendly, fast, cost-effective LLM access with PDF/document analysis.
documentation1
meeting-decisions
Extract AIDD decisions from tldv.io meeting transcripts and notes. Analyzes transcripts to propose proceed/pivot/drop/iterate decisions.
testing1
plan-feature
Create comprehensive feature implementation plan with deep codebase analysis. Use before implementing any feature.
development1
productizer
Bridge between Linear (execution) and Productive.io (customer value). Translates internal work into customer-facing service reports.
testing1
prime
Load project context and show current status. Use at the start of a session or when context is needed.
tools1
pre-production
Pre-Production Security & Quality Check with Strix AI. Use BEFORE deploying to production to catch vulnerabilities and issues.
testing1
publish-skill
Publish local skills to central repository for team sharing. Use when you've developed a useful pattern others should have.
development1
promptfoo
LLM evaluation and self-learning prompts. Test, compare, and improve prompts systematically. Red-teaming and vulnerability scanning.
testing1
sync
Sync updates from upstream agent-kit to this downstream project. Use when the template has new skills or patterns.
data-ai1
.claude/skills/time-report
--- name: time-report description: Cross-project time report. Aggregates all session data from ~/.claude-time/sessions/. Use to see how much time was spent across all projects. disable-model-invocation: true allowed-tools: Bash, Read argument-hint: [all | this-week | this-month | last-month | {project-name}] --- # Time Report: Cross-Project Session Overview ## Objective Read ALL session files from `~/.claude-time/sessions/*.json` and produce an aggregated time report. Supports filtering by pe
tools1
test
Run tests with coverage report and gap analysis. MANDATORY before /commit and PR creation. Use after implementation or during validation.
testing1
visual-verify
Visual UI verification with agent-browser. Use after implementing UI components to take screenshots, verify interactions, and self-check your work. FASTER than E2E tests.
testing1
init-project
Initialize a new project from Agent Kit boilerplate. Use when creating a new downstream project.
data-ai1
deploy
Deploy project to LUCIDLABS-HQ. Use /deploy for full deployment, /deploy setup for file generation, /deploy status for health checks, /deploy logs for container logs.
testing1
agentdocs
Browse Agent Kit documentation directly in terminal. Use for quick access to architecture, skills, workflows, and reference docs.
documentation1
.claude/skills/audit-sync
--- name: audit-sync description: Cross-project audit and sync. Backs up, bootstraps, promotes, syncs, and verifies all downstream projects. disable-model-invocation: true allowed-tools: Bash, Read argument-hint: [--dry-run] [--project <name>] --- # Audit Sync ## Objective Bring all downstream projects up to date with the upstream agent-kit. Runs a 5-phase workflow: Backup, Bootstrap, Promote, Sync, Verify. ## Usage ```bash # From upstream agent-kit directory ./scripts/audit-sync.sh --dry-r
tools1
browser
Interactive browser automation with agent-browser. Open pages, click elements, fill forms, take screenshots. Use for testing UI, automating tasks, or debugging visual issues.
tools1
.claude/skills/compound
--- name: compound description: Capture knowledge from development sessions. Debug patterns, architecture decisions, framework gotchas, and integration learnings compound over time. allowed-tools: Read, Write, Edit, Glob, Grep, AskUserQuestion argument-hint: <type> <title> — types: debug|decision|gotcha|pattern|integration --- # Compound: Knowledge Capture ## Objective Capture knowledge during development so it compounds over time. Every debug session, architecture decision, and framework got
tools1
review
Run parallel code reviews using specialized agents (security, performance, simplicity, nextjs-react). Produces a structured report.
development1
notion-publish
Publish markdown documents to Notion as private pages. Use for sharing specs, docs, or session outputs.
documentation1
pr
Create a feature branch, commit changes, push, and open a Pull Request. The standard way to ship changes. Use after implementation is complete.
tools1
promote
Promote generic patterns from this project back to the upstream agent-kit. Use when you have reusable patterns to share.
data-ai1
screenshot
Take visual verification screenshots using agent-browser. Use for UI verification.
data-ai1
session-end
End development session cleanly. Updates Linear tickets, checks Git compliance, ensures clean state for next session.
development1
start
Entry point for Agent Kit. Use this when starting a session in the template repository to create or open a project.
data-ai1
test-setup
Initialize testing infrastructure for a project. Syncs Vitest + Playwright configs from upstream.
testing1
update-readme
Update README with current project status and features. Use after completing features.
documentation1