opencode-skills-collection 4.1.15 → 4.1.17

package/bundled-skills/monte-carlo-performance-diagnosis/references/query-analysis.md

@@ -0,0 +1,50 @@
+# Query Analysis Patterns
+
+## Reading performance data
+
+### Runtime metrics
+
+When presenting runtime data to the user, always cite the exact numbers from the tool:
+
+- **Average runtime**: The typical execution time for a query group
+- **Total runtime**: Average x run count -- represents total compute consumption
+- **Runtime share**: Percentage of total warehouse compute this query consumes
+- **p50 / p95**: Median and 95th percentile latency -- if p95 >> p50 (>5x), outlier executions are the problem
+
+### Trend analysis
+
+- **7-day trend** (`runDurationTrend7d`): Positive = getting faster, negative = getting slower
+- Values near 0 may indicate insufficient data -- flag if trend confidence is low (<0.1)
+- Always compare current metrics to the 7-day baseline before making claims about regressions
+
+### Common performance patterns
+
+**Sudden spike**: Query changed (new JOIN, removed filter, different plan). Use `get_change_timeline` to find the change. When using `get_query_latency_distribution` to confirm timing, pass `bucket="1h"` to localize the step to a specific hour.
+
+**Gradual degradation**: Data volume growing or query becoming less efficient over time. Use `get_query_latency_distribution` to confirm the trend.
+
+**Intermittent slowness**: Outlier executions (p95 >> p50). Often caused by: resource contention, cold warehouse startup, large partition scans on specific date ranges. Pass `bucket="1h"` to `get_query_latency_distribution` to identify which hours are outlier-heavy.
+
+**Failed/futile patterns**: Use `get_query_rca` to group failures by cause. Common causes:
+- **Timeout**: Query takes too long -- needs optimization or larger warehouse
+- **Permission**: Credentials or roles changed
+- **Futile**: Query runs but returns zero rows or produces no downstream effect
+
+## Read vs write queries
+
+- When the user asks about "expensive" or "costly" queries, investigate using runtime data
+- When the user asks about "reads" or "read queries", filter with `query_type="read"` (SELECT queries)
+- When the user asks about "writes", filter with `query_type="write"` (INSERT, CREATE, MERGE)
+- **Never mix reads and writes** in the same result unless the user explicitly asks for both
+
+## Cross-platform considerations
+
+Performance data comes from multiple platforms. Note which platform each finding is from:
+
+| Platform | Job type | Task granularity |
+|----------|----------|------------------|
+| Airflow | DAG runs | Task instances within DAGs |
+| dbt | Model runs | Individual model executions |
+| Databricks | Job runs | Notebook/task runs within jobs |
+
+Each platform has different performance characteristics. An Airflow task taking 5 minutes might be normal; a dbt model taking 5 minutes might indicate a problem.

package/bundled-skills/monte-carlo-remediation/SKILL.md

@@ -9,6 +9,9 @@ date_added: 2026-07-01
 license: Apache-2.0
 license_source: https://github.com/monte-carlo-data/mc-agent-toolkit/blob/main/LICENSE
 ---
+## Bundled upstream support
+
+Supporting files are included at skill-relative paths. See [UPSTREAM-NOTICE.md](UPSTREAM-NOTICE.md) for their pinned sources, licenses, hashes, and import changes.
 
 # Monte Carlo Remediation Skill
 

package/bundled-skills/monte-carlo-remediation/UPSTREAM-LICENSE.txt

@@ -0,0 +1,201 @@
+                                 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/bundled-skills/monte-carlo-remediation/UPSTREAM-NOTICE.md

@@ -0,0 +1,13 @@
+# Upstream helpers for monte-carlo-remediation
+
+The files listed below were recovered from [monte-carlo-data/mc-agent-toolkit](https://github.com/monte-carlo-data/mc-agent-toolkit) at commit `f1ea90fa2b7fa1ece98e52a45d887c609f2a8de6`. The repository ID is `1166903665`.
+
+They retain the upstream **Apache-2.0** license reproduced in [UPSTREAM-LICENSE.txt](UPSTREAM-LICENSE.txt). This notice applies to the listed support files; it does not replace the license metadata of other catalog files. Preserve the upstream license and this attribution when redistributing them.
+
+License wording is unchanged; text-only trailing whitespace and EOF blank lines are normalized. Original license: https://github.com/monte-carlo-data/mc-agent-toolkit/blob/f1ea90fa2b7fa1ece98e52a45d887c609f2a8de6/LICENSE
+
+| Local file | Original upstream path | Original Git blob SHA | Import changes |
+| --- | --- | --- | --- |
+| `references/patterns.md` | `skills/remediation/references/patterns.md` | `657a0222c0abe6216e759e97d8a75b3aa1119d82` | text-only trailing whitespace and EOF blank lines normalized |
+| `references/tool-discovery.md` | `skills/remediation/references/tool-discovery.md` | `1f5622a575e4056210ed53e87e769ff65e27e3d4` | text-only trailing whitespace and EOF blank lines normalized |
+| `references/safety.md` | `skills/remediation/references/safety.md` | `12733982eb9e2e4c3d467ccc59aa74e82bd7123e` | text-only trailing whitespace and EOF blank lines normalized |

package/bundled-skills/monte-carlo-remediation/references/patterns.md

@@ -0,0 +1,295 @@
+# Remediation Patterns
+
+Common data quality issue patterns with example remediation workflows. These are illustrative examples for reasoning — not rigid step-by-step procedures. Real incidents often combine multiple patterns or present unique variations. Use these as a starting point, then adapt based on the specific TSA findings and available tools.
+
+---
+
+## Pattern 1: Stale data (freshness alert)
+
+### Root cause signals (from TSA)
+
+- "Pipeline has not run since..."
+- "DAG/job failed at [timestamp]"
+- "No new rows since [timestamp]"
+- "Upstream table also stale" (cascading staleness)
+
+### Reasoning
+
+Stale data usually means the pipeline that feeds this table has either failed or not run. The first step is identifying which pipeline is responsible, then determining why it stopped.
+
+### Investigation steps
+
+1. Check upstream lineage — is the source table also stale?
+   ```
+   getAssetLineage(mcons=["<table_mcon>"], direction="UPSTREAM")
+   getTable(mcon="<upstream_mcon>")  # check freshness
+   ```
+
+2. Check recent write queries — what pipeline usually updates this table?
+   ```
+   getQueriesForTable(mcon="<table_mcon>", query_type="destination", limit=5)
+   ```
+
+3. If upstream is also stale, trace further upstream to find the true root cause.
+
+### Remediation by available tools
+
+**If pipeline orchestrator is available (Airflow, Dagster, Prefect):**
+- Identify the DAG/pipeline responsible for updating the table
+- Check if the last run failed or was delayed
+- Trigger a new run or retry the failed task
+- Example: "The DAG `etl_orders_daily` last ran 26 hours ago and failed on task `load_orders`. I'll retry that specific task."
+
+**If dbt Cloud is available:**
+- Identify the dbt job that builds this model
+- Check the last run status
+- Trigger a new run
+- Example: "The dbt job 'Daily Transform' failed 18 hours ago with a compilation error. After reviewing the error, I'll trigger a rerun."
+
+**If no execution tool is available:**
+- Document which pipeline is responsible (from query analysis)
+- Provide the manual commands: `airflow dags trigger <dag_id>` or `dbt run --select <model>`
+- Present the diagnosis and recommended fix to the user and ask for next steps
+- Comment on the alert with the diagnosis and recommended fix
+
+### Verification
+
+After triggering the pipeline:
+- Wait for the job to complete (check status via the orchestrator MCP)
+- Re-check table freshness: `getTable(mcon="<table_mcon>")` — has `last_updated_on` moved forward?
+- Re-check the alert: `getAlerts(alert_ids=["<alert_id>"])` — has it resolved?
+
+---
+
+## Pattern 2: dbt model failure
+
+### Root cause signals (from TSA)
+
+- "dbt run failed with error..."
+- "Compilation error in model..."
+- "Database error during model execution"
+- "Dependency failed — upstream model did not complete"
+
+### Reasoning
+
+dbt failures can be compilation errors (code issues), database errors (permissions, resource limits), or dependency failures (upstream model failed first). The fix depends on the error type.
+
+### Investigation steps
+
+1. Read the TSA `full_response` carefully — it often contains the actual dbt error message.
+
+2. Check if the issue is the table itself or an upstream dependency:
+   ```
+   getAssetLineage(mcons=["<table_mcon>"], direction="UPSTREAM")
+   ```
+
+3. If upstream models also have alerts, the root cause is likely further upstream — remediate that first.
+
+### Remediation by available tools
+
+**If dbt Cloud is available:**
+- For compilation errors: the error likely needs a code fix → create a GitHub PR if GitHub MCP is available, otherwise describe the fix for the user
+- For transient database errors: rerun the job
+- For dependency failures: find and fix the upstream failure first, then rerun
+
+**If GitHub is available (for code fixes):**
+- Create a branch with the fix
+- Open a PR with clear description of what failed and why
+- Example: "The model `stg_orders` fails because column `order_status` was renamed to `status` upstream. Creating a PR to update the column reference."
+
+**If no execution tool is available:**
+- Describe the error and the fix needed
+- Provide the `dbt run --select <model>` command for manual execution
+- If it's a code issue, describe exactly what file and line needs changing
+
+### Verification
+
+- Check dbt job status via dbt Cloud MCP (if available)
+- Re-check table: `getTable(mcon="<table_mcon>")` — has the model been rebuilt?
+- Verify downstream tables are also refreshing
+
+---
+
+## Pattern 3: Schema change
+
+### Root cause signals (from TSA)
+
+- "Column added/removed/renamed"
+- "Column type changed"
+- "Schema differs from expected"
+
+### Reasoning
+
+Schema changes can be intentional (upstream team made a planned change) or accidental (a deployment error). The remediation depends on whether the change is expected and whether downstream consumers can handle it.
+
+### Investigation steps
+
+1. Identify what changed:
+   ```
+   getTable(mcon="<table_mcon>", include_fields=true)
+   ```
+
+2. Check blast radius — who consumes this table?
+   ```
+   getAssetLineage(mcons=["<table_mcon>"], direction="DOWNSTREAM")
+   ```
+
+3. Check if downstream tables are also alerting:
+   ```
+   getAlerts(
+     table_mcons=["<downstream_mcon_1>", "<downstream_mcon_2>"],
+     created_after="<24 hours ago>"
+   )
+   ```
+
+4. Check recent queries to identify who/what made the schema change:
+   ```
+   getQueriesForTable(mcon="<table_mcon>", query_type="destination", limit=10)
+   ```
+
+### Remediation by available tools
+
+**If the change is intentional and downstream needs updating:**
+- If GitHub is available: create a PR that updates downstream models to handle the new schema
+- If dbt Cloud is available: after fixing the code, trigger a full rebuild of affected models
+- Example: "Column `user_id` was renamed to `customer_id` in `raw_orders`. 4 downstream models reference this column. Creating a PR to update all references."
+
+**If the change is accidental and should be reverted:**
+- If GitHub is available: create a PR reverting the upstream change
+- If the change was a direct DDL (not code-managed): provide the ALTER statement to revert
+- Present findings to the user and recommend they contact the upstream table owner
+
+**If no execution tool is available:**
+- Document all affected downstream tables and the specific column changes
+- List the files/models that need updating
+- Escalate with a complete impact report
+
+### Verification
+
+- Re-check table schema: `getTable(mcon="<table_mcon>", include_fields=true)`
+- Verify downstream models are rebuilding successfully
+- Check that schema change alerts resolve
+
+---
+
+## Pattern 4: Volume anomaly
+
+### Root cause signals (from TSA)
+
+- "Row count dropped by X%"
+- "Row count significantly higher than expected"
+- "No new rows in expected time window"
+- "Duplicate rows detected"
+
+### Reasoning
+
+Volume anomalies can indicate: data loss (rows missing), data duplication (rows doubled), source system issues (upstream stopped sending data), or filter/logic changes (a WHERE clause changed). The investigation must determine which case applies.
+
+### Investigation steps
+
+1. Quantify the anomaly:
+   ```
+   getTable(mcon="<table_mcon>")  # current row count
+   ```
+
+2. Check if the issue is in this table or upstream:
+   ```
+   getAssetLineage(mcons=["<table_mcon>"], direction="UPSTREAM")
+   getTable(mcon="<upstream_mcon>")  # check upstream row counts
+   ```
+
+3. Analyze recent write queries for clues:
+   ```
+   getQueriesForTable(mcon="<table_mcon>", query_type="destination", limit=10)
+   ```
+   Look for: unusual DELETE statements, changed WHERE clauses, failed INSERT operations.
+
+4. Check monitoring for more context:
+   ```
+   getMonitors(mcons=["<table_mcon>"])
+   ```
+
+### Remediation by available tools
+
+**For missing data (row count drop):**
+- If pipeline orchestrator is available: trigger a backfill for the affected time range
+- If the drop is from a bad deployment: revert via GitHub, then rerun the pipeline
+- If upstream source stopped: present findings to the user and recommend they contact the source system owner
+
+**For duplicate data:**
+- If warehouse access is available: run a deduplication query (with user confirmation!)
+- Create a PR to fix the pipeline logic that caused duplication
+- Trigger a rebuild after the fix
+
+**For unexpected volume increase:**
+- Investigate whether this is a genuine increase or a data quality issue
+- Check if upstream sources are sending more data than expected
+- If it's a filter/logic change: review recent code changes
+
+**If no execution tool is available:**
+- Quantify the anomaly (expected vs actual row counts, affected time range)
+- Identify the likely cause from query analysis
+- Provide specific remediation steps for the user to execute manually
+
+### Verification
+
+- Re-check row counts: `getTable(mcon="<table_mcon>")`
+- Compare against expected values
+- Monitor over the next few pipeline runs to confirm stability
+
+---
+
+## Pattern 5: Unknown or complex root cause
+
+### Root cause signals (from TSA)
+
+- TSA returned `failed` status
+- TSA `tldr` is unclear or generic ("multiple issues detected")
+- Root cause spans multiple systems or teams
+- The issue is intermittent and hard to reproduce
+
+### Reasoning
+
+Not every issue has a clear, automatable fix. When the root cause is unclear or complex, the best approach is to present full context to the user and ask for direction — not guess at a fix.
+
+### Context package
+
+Compile a complete summary for the user:
+
+1. **Alert details:** type, severity, when it fired, affected tables
+2. **TSA findings:** whatever root cause analysis was available (even if partial)
+3. **Blast radius:** downstream consumers, key assets affected
+4. **Table state:** current freshness, row counts, schema
+5. **Recent queries:** pipeline activity, any anomalous patterns
+6. **Monitoring coverage:** what monitors exist, any gaps
+7. **Your assessment:** what you think might be wrong and why, with confidence level
+
+### What to do
+
+Present the context package to the user and ask how they'd like to proceed. They may want to:
+- Notify their team via Slack or PagerDuty
+- Investigate further with specific queries
+- Assign the alert to a specific person
+- Take a manual remediation action you can help with
+
+**Document on the alert regardless:**
+```
+createOrUpdateAlertComment(
+  alert_id="<alert_uuid>",
+  comment="## Investigation Summary\n\n[full context package]\n\n**Why automated remediation was not attempted:** [reason]\n**Recommended next steps:** [specific actions]"
+)
+
+updateAlert(
+  alert_id="<alert_uuid>",
+  status="WORK_IN_PROGRESS"
+)
+```
+
+### When to use this pattern
+
+- TSA failed or returned unclear results
+- Root cause spans multiple systems (e.g., infrastructure + pipeline + data)
+- The fix requires access or permissions you don't have
+- You're not confident the proposed fix won't cause additional problems
+- The issue is intermittent and the current state looks normal
+- Multiple alerts are firing simultaneously on related tables (likely a systemic issue)