By phdata
phData Toolkit CLI foundation: verify/install the toolkit binary, configure shell PATH, initialize a toolkit project, configure JDBC connections and datasources (Snowflake, SQL Server, Oracle, Postgres, MySQL, Hive, Databricks, Athena), and optionally configure the LLM client for toolkit agent commands. Required by all phData workflow plugins.
Add or verify a JDBC connection and datasource in toolkit.conf for any supported type — Snowflake, SQL Server, Oracle, Postgres, MySQL, Hive, Databricks, Athena — including JDBC driver installation for non-bundled types and verification via a scoped ds scan. Use when configuring data sources, fixing connection errors, or when toolkit-check reports no datasource.
Configure the optional llmClient block in toolkit.conf so toolkit agent commands (discovery, pipeline-build, fix-sql, codegen ask) can call an LLM — Amazon Bedrock, OpenAI, or Anthropic. Use when agent commands fail for lack of an LLM, when switching providers or models, or when onboarding to the toolkit agent workflows.
Install and configure the phData Toolkit CLI end to end — verify Java, get the toolkit binary on PATH, authenticate, initialize a toolkit project, and extract Data Source tool defaults. Use when the toolkit is missing, toolkit-check fails, or a user is onboarding to phData Toolkit workflows.
Show a doctor-style report of the phData Toolkit CLI installation — binary, Java, project, datasources, and optional connectivity. Use when the user asks whether the toolkit is set up, why a toolkit command might be failing, or wants a health check before starting toolkit work.
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.
Claude Code plugin marketplace for phData's coding-agent extensions — plugins that package
phData Toolkit CLI workflows (skills, preflight scripts, hooks)
so engineering repos don't each carry their own .claude/skills/.
| Plugin | Description |
|---|---|
| toolkit-core | Toolkit CLI foundation: install, PATH setup, project init, JDBC connection/datasource configuration. Required by all other toolkit plugins. |
| toolkit-pipeline | Dataspec-driven pipeline generation via toolkit agent discovery and toolkit agent pipeline-build: SQL, dbt, or PySpark transforms plus data-quality tests and a synthetic-data spec. |
Inside Claude Code:
/plugin marketplace add phdata/agent-marketplace
/plugin install toolkit-core@phdata
/plugin install toolkit-pipeline@phdata
Installing toolkit-pipeline automatically installs its toolkit-core dependency from this
marketplace.
For team/repo-wide auto-install, check a .claude/settings.json into the consuming repo —
see docs/team-setup.md.
Cortex Code consumes the same plugin format but not the marketplace catalog, so install each plugin by its subdirectory:
cortex plugin install github:phdata/agent-marketplace/toolkit-core
cortex plugin install github:phdata/agent-marketplace/toolkit-pipeline
Notes:
@<branch> to pin a branch (e.g. github:phdata/agent-marketplace/toolkit-core@feature/initial_plugin
while testing pre-release changes); the subdirectory path goes before the @.toolkit-core explicitly alongside
toolkit-pipeline.cortex plugin update re-fetches from the pinned source; cortex plugin list shows what's
installed and enabled.The plugins detect a missing or misconfigured Toolkit CLI and fix it with you
(/toolkit-core:setup), delegating installation to the official phData install scripts for
macOS, Linux, and Windows — see the
install docs. Most toolkit commands
also need an auth token (toolkit auth); some features are license-tiered (free vs pro).
<plugin>/.claude-plugin/plugin.json.claude plugin validate <plugin-dir> before opening a PR.claude --plugin-dir ./<plugin-dir>, then /reload-plugins to pick up edits.<plugin-name>--v<version>, pushed with claude plugin tag --push.npx claudepluginhub phdata/agent-marketplace --plugin toolkit-coreGenerate data pipelines with the phData Toolkit agent stack: author or supply a DiscoveryConfig dataspec, run toolkit agent discovery to produce a reviewable data contract, resolve human-review items, then pipeline-build SQL, dbt, or PySpark transforms with data-quality tests and a synthetic-data spec.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows