Claude Code plugin for the Imagine Learning Courseware team (synced from upstream)
Evaluate a PR to the il-claude-plugin repo (cw plugin) for Courseware/EdgeEX specificity, overlap with the il plugin, agentskills.io spec compliance, and overlap with open-source Claude Code skill collections
Greet the user and introduce Courseware team plugin capabilities
Use when the user needs to start the edgeex-mcp server locally, set up credentials, or troubleshoot why edgeex MCP tools are unavailable. Covers first-time setup (cloning, installing, configuring) and day-to-day token refresh.
Use when fetching articles from help.imagineedgenuity.com (EdgeEX or heritage Edgenuity) to cite product-side terminology, behavior, or permissions. The site is Cloudflare-protected — WebFetch and curl get 403; this skill documents the Playwright MCP workflow that works.
Use when investigating an enrollment in any EdgeEx environment — fetches enrollment, section, customization, supplemental, and gradebook data to produce a complete picture of how a student's course is configured and how they are progressing
Use when investigating Heritage ↔ EdgeEx section drift (Heritage references sections EdgeEx has never seen) — provides schema reference, drift-detection SQL, and investigation playbook. SQL-only; user runs queries.
No model invocation
Executes directly as bash, bypassing the AI model
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.

A Data Platform-owned fork of the Imagine Learning Claude Code plugin marketplace. It carries the upstream IL plugins (synced from ImagineLearning/il-claude-plugin on a cadence) plus the DP-owned dp plugin, which ships here ahead of upstream review so the Data Platform team can review, merge, and iterate at the speed it needs.
This marketplace contains:
dp — Data Platform team plugin: pipeline incident triage, dbt compile/run, Snowflake role-grant PRs, Snowflake Bazooka data investigation, dbt model exploration, quick recipes, and Confluence ticket publishing. Depends on il.il — org-wide IL development workflows, best practices, architecture generation, code review, OTK v2 deployments, Pact contract testing, and repository documentation. (synced from upstream)cw — Courseware and EdgeEX team-specific skills, agents, and commands. (synced from upstream)twig — Twig team-specific skills, agents, and commands. (synced from upstream)DP's plugin delivery was gated by another team's review/merge cadence on the upstream repo. Owning the fork lets the Data Platform team review, merge, iterate, and experiment at the speed it requires. The intent is not to diverge unnecessarily — we sync upstream main on a cadence and contribute DP improvements back upstream when appropriate.
Add the DP marketplace, then install the plugin you need. dp depends on il, so install both:
/plugin marketplace add https://github.com/ImagineLearning/dp-claude-plugin.git
/plugin install il # required dependency of dp
/plugin install dp # Data Platform plugin (/dp: namespace)
Use the full HTTPS
.gitURL, not theowner/reposhorthand. This repo is private, and the shorthand makes Claude Code clone over SSH ([email protected]:…), which fails withPermission denied (publickey)on machines without GitHub SSH keys. If the HTTPS add fails withcould not read Username … terminal prompts disabled, git has no cached credential for this private repo — run a manualgit clone https://github.com/ImagineLearning/dp-claude-plugin.gitonce so Git Credential Manager stores your token, then re-run the marketplace add.
To test the plugin locally, run Claude Code with the --plugin-dir flag:
claude --plugin-dir /path/to/dp-claude-plugin
Data Platform support under the /dp: namespace — 7 commands and 8 skills:
/dp:hello — Introduction and capabilities overview, with a worked example use case for each command./dp:doctor [--verbose] — Health check: Python deps, env vars, AWS SSO config, MCP availability, profiles.yml, and the bundled Snowflake modules./dp:incident <dag-name-or-task-arn> [flags] — Pipeline incident co-pilot: DAG → ECS task → CloudWatch logs, classify failure, draft Slack message + postmortem. Default account edg-dp-dev (388892568521)./dp:dbt-compile <model> — Compile a DataPlatformSnowflake dbt model against WELD_NORTH_PROD (read-only), resolving by bare name./dp:dbt-run <model> — Run a dbt model in your personal WELD_NORTH_TEST.<your_schema> sandbox. Never writes to prod./dp:assign-role <role> <email> <DP-TICKET> — Grant a Snowflake role in DataPlatformSnowflakeTerraform: pull, branch, edit user.tf + role_grants.tf, plan, confirm, open PR. Never merges./dp:investigate-data <TICKET> — Snowflake Bazooka-style autonomous investigation. Reads Jira, discovers schema via INFORMATION_SCHEMA, runs the right quick recipe, logs findings. Enforces PII protection (aggregates only).incident — Incident co-pilot catalog (failure patterns, Slack/postmortem format).dbt — dbt compile/run conventions (IL env vars, profiles.yml, never-commit policy).assign-role — Role-grant conventions (valid role list, user.tf/role_grants.tf formats, branch/PR format).publish-ticket-confluence — DP ticket-folder Confluence convention + idempotent publish via il atlassian MCP.query-snowflake — SSO-only Snowflake querying with mandatory PII protection.snowflake-quick-recipes — 7 pre-built recipes (missing records, duplicates, nulls, freshness, prod-vs-sandbox, orphans, distribution shift).explore-dbt-models — Read-only DataPlatformSnowflake lineage exploration.dbt-fix-conventions — DataPlatformSnowflake dbt conventions; auto-loaded by /il:generate-code for dw_dbt/ paths.The dp plugin can query Snowflake and read pipeline logs that may contain student data. All DP skills enforce PII protection (FERPA/COPPA): aggregates only, never write row-level PII to reports, Jira, Confluence, or CSV. /dp:assign-role is grant-only and never auto-merges (CODEOWNERS review required).
npx claudepluginhub imaginelearning/dp-claude-plugin --plugin cwClaude Code plugin for the Imagine Learning Data Platform team — pipeline incident triage, dbt compile/run, Snowflake role-grant PRs, Snowflake Bazooka data investigation, dbt model exploration, quick recipes, and Confluence ticket publishing.
Claude Code plugin for Imagine Learning development workflows, architecture, code generation, OTK deployments, Pact testing, and repository documentation (synced from upstream)
Claude Code plugin for the Imagine Learning Twig team (synced from upstream)
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Streamline people operations — recruiting, onboarding, performance reviews, compensation analysis, and policy guidance. Maintain compliance and keep your team running smoothly.