Databrain Intelligence
infometa/workbuddyskills
DataBrain intelligence data query assistant. An agent skill from infometa/workbuddyskills.
A skill your agent uses when querying auto-collected CI data from test runs in BigQuery (cidataautodl dataset) including risk analysis, disruption, CPU metrics, audit logs, operator state, and retry…
Install Autodl
$ npx skills add openshift-eng/ai-helpers --skill autodl -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install openshift-eng/ai-helpers autodl --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/bigquery-ci-data/skills/autodl .claude/skills/autodl && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "autodl" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/bigquery-ci-data/skills/autodl into .claude/skills/autodl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autodl", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/openshift-eng/ai-helpers/tree/main/plugins/bigquery-ci-data/skills/autodlType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add openshift-eng/ai-helpers --skill autodl -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install openshift-eng/ai-helpers autodl --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/bigquery-ci-data/skills/autodl .agents/skills/autodl && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "autodl" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/bigquery-ci-data/skills/autodl into .agents/skills/autodl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autodl", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add openshift-eng/ai-helpers --skill autodl -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install openshift-eng/ai-helpers autodl --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/bigquery-ci-data/skills/autodl .cursor/skills/autodl && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "autodl" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/bigquery-ci-data/skills/autodl into .cursor/skills/autodl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autodl", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/openshift-eng/ai-helpers.git --path plugins/bigquery-ci-data/skills/autodl--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add openshift-eng/ai-helpers --skill autodl -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install openshift-eng/ai-helpers autodl --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/bigquery-ci-data/skills/autodl .gemini/skills/autodl && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "autodl" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/bigquery-ci-data/skills/autodl into .gemini/skills/autodl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autodl", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install openshift-eng/ai-helpers autodlInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add openshift-eng/ai-helpers --skill autodl -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/bigquery-ci-data/skills/autodl .github/skills/autodl && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "autodl" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/bigquery-ci-data/skills/autodl into .github/skills/autodl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autodl", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add openshift-eng/ai-helpers --skill autodl -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install openshift-eng/ai-helpers autodl --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/bigquery-ci-data/skills/autodl .opencode/skills/autodl && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "autodl" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/bigquery-ci-data/skills/autodl into .opencode/skills/autodl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autodl", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
autodl- GitHub stars
- 120
- Token cost
- ~2.9k tokens
- SKILL.md length
- 1,097 words
- Files
- 1
- Skills in repo
- 118
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A skill your agent uses when querying auto-collected CI data from test runs in BigQuery (cidataautodl dataset) including risk analysis, disruption, CPU metrics, audit logs, operator state, and retry…
- Works in 4 steps: Monitor tests in openshift/origin… → Data is written as *autodl.json files in… → The ci-data-loader picks up these files… → …
- Querying auto-collected CI data from test runs in BigQuery (cidataautodl dataset) including risk analysis
- SKILL.md covers When to Use This Skill, Common Columns, Tables and Query Examples, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Autodl is an agent skill from openshift-eng/ai-helpers. Use when querying auto-collected CI data from test runs in BigQuery (cidataautodl dataset) including risk analysis, disruption, CPU metrics, audit logs, operator state, and retry statistics
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Databases, covering Data warehousing and Statistics. It works with Google BigQuery. The repository describes itself as: Developer productivity tools for Claude Code & other AI assistants. The licence is Apache-2.0.
When your agent uses it
- Querying auto-collected CI data from test runs in BigQuery (cidataautodl dataset) including risk analysis
- Retry statistics
Example prompts
- “/autodl”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Monitor tests in openshift/origin collect data during test execution
- Data is written as *autodl.json files in job artifacts
- The ci-data-loader picks up these files and uploads to BigQuery
- New columns in schemas are auto-added to existing tables; removed columns are never deleted (cross-release integrity)
What it can do on your machine
Read from SKILL.md and the folder at commit a627176. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are sql).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Autodl loads about 2.9k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 1,097 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from openshift-eng/ai-helpers at commit a627176, republished under its Apache-2.0 licence (© openshift-eng). 1,097 words, ~2,935 tokens.
Download SKILL.mdSave it as
.claude/skills/autodl/SKILL.md (or your agent's skills folder).- name
- autodl
- description
- Use when querying auto-collected CI data from test runs in BigQuery (ci_data_autodl dataset) including risk analysis, disruption, CPU metrics, audit logs, operator state, and retry statistics
Autodl Tables
Query data automatically collected during OpenShift CI test runs, stored in openshift-ci-data-analysis.ci_data_autodl. This data is generated by monitor tests and analysis code in openshift/origin and uploaded by the ci-data-loader after each job run.
Follow the foundations skill for cost safety, caching, and execution workflow.
When to Use This Skill
- Investigating risk analysis verdicts for job runs
- Analyzing test retry behavior and flake patterns
- Examining kube-apiserver audit log patterns (latency, request counts, watch storms)
- Tracking operator state transitions during test runs
- Correlating CPU usage with test failures
- Understanding DNS disruption during tests
- Checking cluster instance types and configuration
Common Columns
All autodl tables include three columns added by the ci-data-loader:
| Column | Type | Notes |
|---|---|---|
| JobRunName | STRING | Prow job run identifier — join key to other datasets |
| PartitionTime | TIMESTAMP | Partition column — always filter on this |
| Source | STRING | Data source identifier |
The JobRunName can be used to correlate autodl data with job runs in openshift-gce-devel.ci_analysis_us.jobs (match against prowjob_build_id or extract from prowjob_url).
Tables
Risk Analysis
risk_analysis_overall_results
Overall risk analysis verdict for a job run — the aggregate risk level across all tests.
| Column | Type | Notes |
|---|---|---|
| RiskLevel | INTEGER | Numeric risk level |
| RiskName | STRING | Human-readable risk name |
| JobRunTestCount | INTEGER | Total tests in the run |
| JobRunTestFailures | INTEGER | Total test failures |
| NeverStableJob | STRING | Whether this job has ever been stable |
| HistoricalRunTestCount | INTEGER | Historical test count for comparison |
Use case: Find job runs with high risk levels, correlate risk verdicts with actual job outcomes.
risk_analysis_test_results
Per-test risk analysis — the risk level assigned to each individual test based on historical pass rates.
| Column | Type | Notes |
|---|---|---|
| TestName | STRING | Full test name |
| TestID | INTEGER | Stable test identifier |
| RiskLevel | INTEGER | Numeric risk level |
| RiskName | STRING | Human-readable risk name |
| CurrentRuns | INTEGER | Recent run count for this test |
| CurrentPasses | INTEGER | Recent pass count |
| CurrentPassPercentage | FLOAT | Recent pass rate |
Use case: Identify which tests contributed most to a run's risk assessment, find tests with declining pass rates.
risk_analysis_api_requests
Metadata about HTTP requests to the Sippy risk analysis API during test runs.
| Column | Type | Notes |
|---|---|---|
| RequestCount | INTEGER | Number of API requests made |
| StartTime | TIMESTAMP | When the request started |
| DurationSeconds | FLOAT | Request duration |
| Error | STRING | Error message if request failed |
| BytesRead | INTEGER | Response size |
Use case: Debug risk analysis API performance issues or failures.
Test Execution
retry_statistics
Per-test retry statistics when tests are retried during a run.
| Column | Type | Notes |
|---|---|---|
| TestName | STRING | Full test name |
| RetryStrategy | STRING | Strategy used for retries |
| TotalAttempts | INTEGER | Total attempts made |
| SuccessfulAttempts | INTEGER | Passing attempts |
| FailedAttempts | INTEGER | Failing attempts |
| FinalOutcome | STRING | Final test result |
| TotalDurationMilliseconds | INTEGER | Total time across all attempts |
| MaxRetriesAllowed | INTEGER | Retry limit |
| FirstAttemptDurationMilliseconds | INTEGER | Duration of first attempt |
| AverageAttemptDurationMilliseconds | INTEGER | Average attempt duration |
| JobName | STRING | Prow job name |
| JobType | STRING | periodic, presubmit, postsubmit |
| PullNumber | STRING | PR number (presubmits) |
| RepoName | STRING | GitHub repo |
| RepoOwner | STRING | GitHub org |
| PullSha | STRING | Commit SHA |
| ReleaseImageLatest | STRING | Target release image |
| ReleaseImageInitial | STRING | Initial release image (upgrades) |
Use case: Analyze retry effectiveness, find tests that always fail on first attempt but pass on retry, measure retry overhead.
run_suite_options
Configuration used to run the test suite.
| Column | Type | Notes |
|---|---|---|
| ClusterStability | STRING | Cluster stability mode |
| RandomSeed | INTEGER | Random seed for test ordering |
| WorkerNodes | INTEGER | Number of worker nodes |
| TotalNodes | INTEGER | Total cluster nodes |
| Parallelism | INTEGER | Test parallelism level |
Use case: Correlate test failures with cluster size or parallelism settings.
high_cpu_e2e_tests
Tests that overlapped with high CPU usage intervals.
| Column | Type | Notes |
|---|---|---|
| TestName | STRING | Full test name |
| Success | INTEGER | 1 = pass, 0 = fail |
Use case: Find tests that fail due to high CPU or cause high CPU on the cluster.
duration-metrics
Named duration metrics (install time, upgrade time, etc.).
| Column | Type | Notes |
|---|---|---|
| name | STRING | Metric name (e.g. "install", "upgrade") |
| duration | INTEGER | Duration in milliseconds |
Use case: Track install/upgrade duration trends across releases and platforms.
Kube-APIServer Audit Analysis
audit_latency_counts
Histogram-bucketed latency counts for kube-apiserver requests, from audit logs.
| Column | Type | Notes |
|---|---|---|
| LatencyType | STRING | Type of latency measurement |
| Resource | STRING | API resource |
| Verb | STRING | HTTP verb |
| Bucket | FLOAT | Latency bucket threshold |
| Count | INTEGER | Requests exceeding this bucket |
Use case: Identify API resources with high latency, find slow verbs, detect apiserver performance regressions.
Show full SKILL.md (426 more words)Show less
audit_resource_requests_per_user
API request counts per user/service-account, from audit logs.
| Column | Type | Notes |
|---|---|---|
| User | STRING | User or service account (cleaned) |
| Resource | STRING | API resource |
| Verb | STRING | HTTP verb |
| HttpStatus | INTEGER | Response status code |
| RequestCount | INTEGER | Number of requests |
Use case: Find noisy controllers, identify unexpected API callers, detect request storms.
operator_watch_requests
Watch request counts per operator against the kube-apiserver, from audit logs.
| Column | Type | Notes |
|---|---|---|
| ControlPlaneTopology | STRING | e.g. "HighlyAvailable", "SingleReplica" |
| PlatformType | STRING | Cloud platform |
| Operator | STRING | Operator name |
| WatchRequestCount | INTEGER | Number of watch requests |
Use case: Detect watch storms, find operators with excessive watch counts, compare across topologies.
Cluster Health
operator_state_metrics
ClusterOperator state transitions (Available, Progressing, Degraded) during the test run.
| Column | Type | Notes |
|---|---|---|
| Operator | STRING | ClusterOperator name |
| State | STRING | "Available", "Progressing", "Degraded" |
| Count | INTEGER | Number of transitions |
| TotalSeconds | FLOAT | Total time in this state |
| MaxIndividualDurationSeconds | FLOAT | Longest single period in this state |
Use case: Find operators that flap between states, track degraded duration across releases.
dns_disruption_stats
DNS disruption summary during the test run.
| Column | Type | Notes |
|---|---|---|
| IntervalCount | INTEGER | Number of disruption intervals |
| TotalDurationSeconds | INTEGER | Total disruption time |
Use case: Track DNS disruption trends, correlate with network configuration variants.
node_cpu_usage_timeline
Time-series per-node CPU usage sampled during the test run.
| Column | Type | Notes |
|---|---|---|
| Timestamp | TIMESTAMP | Sample time |
| NodeName | STRING | Node name |
| NodeRole | STRING | master, worker, etc. |
| CPUUsage | FLOAT | CPU usage percentage |
Use case: Correlate CPU spikes with test failures, identify resource-starved nodes.
interval_duration_sum
Total duration of monitor intervals by source type.
| Column | Type | Notes |
|---|---|---|
| IntervalSource | STRING | "MetricsEndpointDown", "CPUMonitor" |
| TotalDurationSeconds | INTEGER | Total duration |
Use case: Track metrics endpoint availability, CPU monitoring coverage.
cluster_instance_types
Cloud instance types used by nodes in the cluster (AWS, Azure, GCP).
| Column | Type | Notes |
|---|---|---|
| Platform | STRING | Cloud provider |
| Region | STRING | Cloud region |
| Zone | STRING | Availability zone |
| Role | STRING | Node role |
| InstanceType | STRING | Instance type (e.g. m5.xlarge) |
| Suite | STRING | Test suite |
Use case: Correlate failures with instance types, track what hardware CI uses.
Query Examples
Find high-risk job runs in the last week
SELECT
JobRunName,
RiskLevel,
RiskName,
JobRunTestCount,
JobRunTestFailures
FROM `openshift-ci-data-analysis.ci_data_autodl.risk_analysis_overall_results`
WHERE PartitionTime >= TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 7 DAY)
AND RiskLevel >= 3
ORDER BY RiskLevel DESC, JobRunTestFailures DESCFind tests with worst retry rates
SELECT
TestName,
COUNT(*) AS total_runs,
COUNTIF(TotalAttempts > 1) AS runs_with_retries,
ROUND(COUNTIF(TotalAttempts > 1) * 100.0 / COUNT(*), 1) AS retry_pct,
ROUND(AVG(IF(TotalAttempts > 1, TotalAttempts, NULL)), 1) AS avg_attempts_when_retried,
COUNTIF(FinalOutcome = 'passed') / COUNT(*) AS final_pass_rate
FROM `openshift-ci-data-analysis.ci_data_autodl.retry_statistics`
WHERE PartitionTime >= TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 7 DAY)
GROUP BY TestName
HAVING total_runs >= 5
ORDER BY retry_pct DESCFind operators with most degraded time
SELECT
Operator,
COUNT(*) AS run_count,
AVG(TotalSeconds) AS avg_degraded_seconds,
MAX(MaxIndividualDurationSeconds) AS worst_degraded_seconds
FROM `openshift-ci-data-analysis.ci_data_autodl.operator_state_metrics`
WHERE PartitionTime >= TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 7 DAY)
AND State = 'Degraded'
AND Count > 0
GROUP BY Operator
ORDER BY avg_degraded_seconds DESCFind noisiest API callers
SELECT
User,
Resource,
Verb,
SUM(RequestCount) AS total_requests
FROM `openshift-ci-data-analysis.ci_data_autodl.audit_resource_requests_per_user`
WHERE PartitionTime >= TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 7 DAY)
GROUP BY User, Resource, Verb
ORDER BY total_requests DESC
LIMIT 20Data Pipeline
The autodl data pipeline works as follows:
- Monitor tests in
openshift/origincollect data during test execution - Data is written as
*autodl.jsonfiles in job artifacts - The ci-data-loader picks up these files and uploads to BigQuery
- New columns in schemas are auto-added to existing tables; removed columns are never deleted (cross-release integrity)
Source code for all table definitions is in openshift/origin:
- Data loader framework:
pkg/dataloader/types.go - Individual monitor tests:
pkg/monitortests/subdirectories - Risk analysis:
pkg/riskanalysis/cmd.go - Retry statistics:
pkg/test/ginkgo/retries.go - Suite options:
pkg/test/ginkgo/cmd_runsuite.go - Duration metrics:
pkg/e2eanalysis/e2e_analysis.go
© openshift-eng, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in plugins/bigquery-ci-data/skills/autodl of openshift-eng/ai-helpers.
Open the folder on GitHubat commit a627176
Compare with similar skills
Autodl next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Autodl this skillopenshift-eng/ai-helpers | 120 | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| Databrain Intelligenceinfometa/workbuddyskills | 344 | — | ~8k | Automated safety check: Pass | None | |
| Data Warehouse Experimentationrampstackco/claude-skills | 940 | — | ~7.3k | Automated safety check: Pass | MIT | |
| Altimate Data Warehouse DelegateAltimateAI/data-engineering-skills | 128 | — | ~1.4k | Automated safety check: Pass | MIT | |
| dbt Snowflake to BigQuery Translatorgoogle/skills | 21k | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| Bigquery Bigframesgoogle/skills | 21k | 1 repos | ~1.3k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Data Warehouse Experimentation
rampstackco/claude-skills
Running experiments out of the data warehouse instead of via dedicated experiment platforms.
Altimate Data Warehouse Delegate
AltimateAI/data-engineering-skills
Delegates dbt and warehouse tasks such as lineage, migrations and cost attribution to the altimate-code CLI agent and relays its answer back.
- Official
dbt Snowflake to BigQuery Translator
google/skills
Translates Snowflake dbt SQL models into standardized BigQuery SQL, keeping Jinja constructs and tracking progress in a migration tasks file.
- Official
Bigquery Bigframes
google/skills
Generates Python code using BigQuery DataFrames (BigFrames).
Dbt Model Index
warpdotdev/oz-skills
Provide a lookup index of dbt models (BigQuery tables) to guide query writing against a data warehouse.
More from openshift-eng/ai-helpers
All 118 skills in this repoInvestigate CI Reliability
openshift-eng/ai-helpers
Find and independently validate actionable reliability defects across OpenShift release jobs and presubmits, then export portable issue handoffs.
Address Review PR
openshift-eng/ai-helpers
Fetch and address all PR review comments — categorize by priority, make code changes, post replies, and push.
Categorize Activity Types
openshift-eng/ai-helpers
Categorize Jira issues into Red Hat Sankey Activity Type categories using MCP Jira tools.
Has Review Work
openshift-eng/ai-helpers
Decide whether a GitHub PR has unanswered authorized review comments or new required CI failures worth a follow-up agent.
Must Gather Analyzer
openshift-eng/ai-helpers
Analyze OpenShift must-gather diagnostic data including cluster operators, pods, nodes, and network components.
Payload Autodl JSON
openshift-eng/ai-helpers
Schema for the autodl JSON data file produced by payload-analysis for database ingestion — you must use this skill whenever generating the autodl JSON file
Related
Works with
Categories
Questions about Autodl
What does Autodl do?
A skill your agent uses when querying auto-collected CI data from test runs in BigQuery (cidataautodl dataset) including risk analysis, disruption, CPU metrics, audit logs, operator state, and retry…. Autodl is an agent skill from openshift-eng/ai-helpers.
When should I use Autodl?
Autodl fits situations like: querying auto-collected CI data from test runs in BigQuery (cidataautodl dataset) including risk analysis; retry statistics.
How do I install Autodl in Claude Code?
Run `npx skills add openshift-eng/ai-helpers --skill autodl -a claude-code`. Or copy the skill folder (plugins/bigquery-ci-data/skills/autodl in openshift-eng/ai-helpers) into .claude/skills/autodl in your project. Claude Code loads it when a task matches its description.
How do I install Autodl in Codex?
Run `npx skills add openshift-eng/ai-helpers --skill autodl -a codex`. Or copy the skill folder (plugins/bigquery-ci-data/skills/autodl in openshift-eng/ai-helpers) into .agents/skills/autodl in your project. Codex loads it when a task matches its description.
Can I use Autodl in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openshift-eng/ai-helpers --skill autodl -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/autodl, .gemini/skills/autodl, .github/skills/autodl and .opencode/skills/autodl in your project.
What does Autodl need to run?
SKILL.md names no scripts, command-line tools or credentials: Autodl is instructions for the agent only.
Does Autodl access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Autodl safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Autodl use?
Autodl is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Autodl use?
About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Autodl?
Skills that share tags, products or a category with Autodl: Databrain Intelligence (infometa/workbuddyskills, 344 stars), Data Warehouse Experimentation (rampstackco/claude-skills, 940 stars), Altimate Data Warehouse Delegate (AltimateAI/data-engineering-skills, 128 stars) and dbt Snowflake to BigQuery Translator (google/skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Autodl?
openshift-eng (a GitHub organization) maintains it in openshift-eng/ai-helpers, which has 120 GitHub stars. The repository holds 118 skills in this directory. The repository was last updated on October 6, 2026.
Source: openshift-eng/ai-helpers on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.