Software Development Skills

Rebuild the L1-L4 tree-sitter AST index for fast semantic search. L1=files, L2=symbols, L3=signatures, L4=dependencies. Respects .gitignore.

Patterns for finding bugs — anti-patterns from the playbook, edge cases, regression triggers, and common failure modes in agentic systems.

CI quality gates — what blocks merge, what warns. GitHub Actions workflow checks and their pass/fail criteria.

Set up Claude Code GitHub Actions for automated PR creation, code review, issue triage, and CI/CD automation. @claude mentions in PRs and issues.

Create, install, distribute, and manage Claude Code plugins. Marketplace setup, plugin structure, skills, agents, hooks, MCP servers, and community distribution.

Build custom agents with the Claude Agent SDK. Programmatic Claude Code via CLI (-p flag), Python, and TypeScript. Structured output, streaming, tool approval, and CI/CD scripting.

Automated multi-agent PR security review. Fleet of specialized agents examine code for logic errors, security vulnerabilities, broken edge cases, and regressions.

Cert Domain 1 (27%): Agentic loops, multi-agent coordination, subagent spawning, handoff patterns, hook enforcement, task decomposition, session state.

Cert Domain 2 (18%): Tool descriptions, MCP structured errors, tool distribution, MCP server integration, built-in tool selection.

Cert Domain 3 (20%): CLAUDE.md hierarchy, commands/skills config, path-scoped rules, plan mode vs direct execution, iterative refinement, CI/CD integration.

Cert Domain 4 (20%): Explicit criteria prompts, few-shot examples, JSON schema enforcement via tooluse, validation/retry loops, batch processing, multi-pass review.

Cert Domain 5 (15%): Context window management, long-session strategies, session resumption, error escalation, human-in-the-loop calibration.

Non-negotiable architectural rules governing the jadecli ecosystem. Violations fail the build. Derived from cert exam + playbook.

End-to-end validation flows across plugins, integrations, and mobile. Proves the full jadecli ecosystem works with real data.

Kimball dimensional modeling methodology with semantic layer declarations, 1-table-per-file DDL, load types, pipeline metadata, and version-controlled business logic. Based on The Data Warehouse Toolkit.

Per-role analytics for jadecli knowledge worker plugins — measure ROI across data-engineering, frontend-engineering, integration-engineering, and analytics-engineering roles.

Concrete test implementations for each of the 10 architect milestones. Run these to validate the entire jadecli ecosystem end-to-end.

Guide for using Netlify Blobs object storage. Use when storing files, images, documents, or simple key-value data without a full database.

Guide for controlling caching on Netlify's CDN.

Guide for using the Netlify CLI and deploying sites.

Reference for netlify.toml configuration.

Guide for using Netlify DB (managed Neon Postgres). Use when the project needs a relational database, structured data storage, SQL queries, or data that will grow over time. Covers provisioning, raw SQL via @netlify/neon, Drizzle ORM integration, migrations, and deploy preview branching. Also covers when to use Netlify Blobs instead.

Guide for writing Netlify Edge Functions.

Guide for using Netlify Forms for HTML form handling. Use when adding contact forms, feedback forms, file upload forms, or any form that should be collected by Netlify.