opencode-knowledge-work 0.0.0-stage → 0.1.1

package/content/data/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

package/content/data/README.md

@@ -0,0 +1,121 @@
+# Data Analyst Plugin
+
+A data analyst plugin primarily designed for [Cowork](https://claude.com/product/cowork), Anthropic's agentic desktop application — though it also works in Claude Code. SQL queries, data exploration, visualization, dashboards, and insight generation. Works with any data warehouse, any SQL dialect, and any analytics stack.
+
+## Installation
+
+```
+claude plugin marketplace add anthropics/knowledge-work-plugins
+claude plugin install data@knowledge-work-plugins
+```
+
+## What It Does
+
+This plugin transforms Claude into a data analyst collaborator. It helps you explore datasets, write optimized SQL, build visualizations, create interactive dashboards, and validate analyses before sharing with stakeholders.
+
+### With a Data Warehouse Connection
+
+Connect your data warehouse MCP server (e.g., Snowflake, Databricks, BigQuery, or any SQL-compatible database) for the best experience. Claude will:
+
+- Query your data warehouse directly
+- Explore schemas and table metadata
+- Run analyses end-to-end without copy-pasting
+- Iterate on queries based on results
+
+### Without a Data Warehouse Connection
+
+Without a data warehouse connection, paste SQL results or upload CSV/Excel files for analysis and visualization. Claude can also write SQL queries for you to run manually, and then analyze the results you provide.
+
+## Commands
+
+| Command | Description |
+|---------|-------------|
+| `/analyze` | Answer data questions -- from quick lookups to full analyses |
+| `/explore-data` | Profile and explore a dataset to understand its shape, quality, and patterns |
+| `/write-query` | Write optimized SQL for your dialect with best practices |
+| `/create-viz` | Create publication-quality visualizations with Python |
+| `/build-dashboard` | Build interactive HTML dashboards with filters and charts |
+| `/validate` | QA an analysis before sharing -- methodology, accuracy, and bias checks |
+
+## Skills
+
+| Skill | Description |
+|-------|-------------|
+| `sql-queries` | SQL best practices across dialects, common patterns, and performance optimization |
+| `data-exploration` | Data profiling, quality assessment, and pattern discovery |
+| `data-visualization` | Chart selection, Python viz code patterns, and design principles |
+| `statistical-analysis` | Descriptive stats, trend analysis, outlier detection, and hypothesis testing |
+| `data-validation` | Pre-delivery QA, sanity checks, and documentation standards |
+| `interactive-dashboard-builder` | HTML/JS dashboard construction with Chart.js, filters, and styling |
+
+## Example Workflows
+
+### Ad-Hoc Analysis
+
+```
+You: /analyze What was our monthly revenue trend for the past 12 months, broken down by product line?
+
+Claude: [Writes SQL query] → [Executes against data warehouse] → [Generates trend chart]
+       → [Identifies key patterns: "Product line A grew 23% YoY while B was flat"]
+       → [Validates results with sanity checks]
+```
+
+### Data Exploration
+
+```
+You: /explore-data users table
+
+Claude: [Profiles table: 2.3M rows, 47 columns]
+       → [Reports: created_at has 0.2% nulls, email has 99.8% cardinality]
+       → [Flags: status column has unexpected value "UNKNOWN" in 340 rows]
+       → [Suggests: "High-value dimensions to explore: plan_type, signup_source, country"]
+```
+
+### Query Writing
+
+```
+You: /write-query I need a cohort retention analysis -- users grouped by signup month,
+     showing what % are still active 1, 3, 6, and 12 months later. We use Snowflake.
+
+Claude: [Writes optimized Snowflake SQL with CTEs]
+       → [Adds comments explaining each step]
+       → [Includes performance notes about partition pruning]
+```
+
+### Dashboard Building
+
+```
+You: /build-dashboard Create a sales dashboard with monthly revenue, top products,
+     and regional breakdown. Here's the data: [pastes CSV]
+
+Claude: [Generates self-contained HTML file]
+       → [Includes interactive Chart.js visualizations]
+       → [Adds dropdown filters for region and time period]
+       → [Opens in browser for review]
+```
+
+### Pre-Share Validation
+
+```
+You: /validate [shares analysis document]
+
+Claude: [Reviews methodology] → [Checks for survivorship bias in churn analysis]
+       → [Verifies aggregation logic] → [Flags: "Denominator excludes trial users
+          which could overstate conversion rate by ~5pp"]
+       → [Confidence: "Ready to share with noted caveat"]
+```
+
+## Connecting Your Data Stack
+
+> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](CONNECTORS.md).
+
+This plugin works best when connected to your data infrastructure. Add MCP servers for:
+
+- **Data Warehouse**: Snowflake, Databricks, BigQuery, Definite, or any SQL-compatible database
+- **Analytics/BI**: Amplitude, Looker, Tableau, or similar
+- **Notebooks**: Jupyter, Hex, or similar
+- **Spreadsheets**: Google Sheets, Excel
+- **Data Orchestration**: Airflow, dbt, Dagster, Prefect
+- **Data Ingestion**: Fivetran, Airbyte, Stitch
+
+Configure MCP servers in your `.mcp.json` or Claude Code settings to enable direct data access.

package/content/data/skills/data-analyze/SKILL.md

@@ -0,0 +1,119 @@
+---
+name: analyze
+description: Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.
+argument-hint: "<question>"
+---
+
+# /analyze - Answer Data Questions
+
+> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md).
+
+Answer a data question, from a quick lookup to a full analysis to a formal report.
+
+## Usage
+
+```
+/analyze <natural language question>
+```
+
+## Workflow
+
+### 1. Understand the Question
+
+Parse the user's question and determine:
+
+- **Complexity level**:
+  - **Quick answer**: Single metric, simple filter, factual lookup (e.g., "How many users signed up last week?")
+  - **Full analysis**: Multi-dimensional exploration, trend analysis, comparison (e.g., "What's driving the drop in conversion rate?")
+  - **Formal report**: Comprehensive investigation with methodology, caveats, and recommendations (e.g., "Prepare a quarterly business review of our subscription metrics")
+- **Data requirements**: Which tables, metrics, dimensions, and time ranges are needed
+- **Output format**: Number, table, chart, narrative, or combination
+
+### 2. Gather Data
+
+**If a data warehouse MCP server is connected:**
+
+1. Explore the schema to find relevant tables and columns
+2. Write SQL query(ies) to extract the needed data
+3. Execute the query and retrieve results
+4. If the query fails, debug and retry (check column names, table references, syntax for the specific dialect)
+5. If results look unexpected, run sanity checks before proceeding
+
+**If no data warehouse is connected:**
+
+1. Ask the user to provide data in one of these ways:
+   - Paste query results directly
+   - Upload a CSV or Excel file
+   - Describe the schema so you can write queries for them to run
+2. If writing queries for manual execution, use the `sql-queries` skill for dialect-specific best practices
+3. Once data is provided, proceed with analysis
+
+### 3. Analyze
+
+- Calculate relevant metrics, aggregations, and comparisons
+- Identify patterns, trends, outliers, and anomalies
+- Compare across dimensions (time periods, segments, categories)
+- For complex analyses, break the problem into sub-questions and address each
+
+### 4. Validate Before Presenting
+
+Before sharing results, run through validation checks:
+
+- **Row count sanity**: Does the number of records make sense?
+- **Null check**: Are there unexpected nulls that could skew results?
+- **Magnitude check**: Are the numbers in a reasonable range?
+- **Trend continuity**: Do time series have unexpected gaps?
+- **Aggregation logic**: Do subtotals sum to totals correctly?
+
+If any check raises concerns, investigate and note caveats.
+
+### 5. Present Findings
+
+**For quick answers:**
+- State the answer directly with relevant context
+- Include the query used (collapsed or in a code block) for reproducibility
+
+**For full analyses:**
+- Lead with the key finding or insight
+- Support with data tables and/or visualizations
+- Note methodology and any caveats
+- Suggest follow-up questions
+
+**For formal reports:**
+- Executive summary with key takeaways
+- Methodology section explaining approach and data sources
+- Detailed findings with supporting evidence
+- Caveats, limitations, and data quality notes
+- Recommendations and suggested next steps
+
+### 6. Visualize Where Helpful
+
+When a chart would communicate results more effectively than a table:
+
+- Use the `data-visualization` skill to select the right chart type
+- Generate a Python visualization or build it into an HTML dashboard
+- Follow visualization best practices for clarity and accuracy
+
+## Examples
+
+**Quick answer:**
+```
+/analyze How many new users signed up in December?
+```
+
+**Full analysis:**
+```
+/analyze What's causing the increase in support ticket volume over the past 3 months? Break down by category and priority.
+```
+
+**Formal report:**
+```
+/analyze Prepare a data quality assessment of our customer table -- completeness, consistency, and any issues we should address.
+```
+
+## Tips
+
+- Be specific about time ranges, segments, or metrics when possible
+- If you know the table names, mention them to speed up the process
+- For complex questions, Claude may break them into multiple queries
+- Results are always validated before presentation -- if something looks off, Claude will flag it