Neocarta Add Source Connector
neo4j-labs/neocarta
Scaffold, build, and verify a neocarta source or format connector against the connector contract.
A skill your agent uses when executing any BigQuery CI data query — provides the shared safety protocol, cost controls, bq CLI patterns, and caching workflow
Install Foundations
$ npx skills add openshift-eng/ai-helpers --skill foundations -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install openshift-eng/ai-helpers foundations --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/foundations .claude/skills/foundations && 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 "foundations" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/bigquery-ci-data/skills/foundations into .claude/skills/foundations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foundations", 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/foundationsType 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 foundations -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install openshift-eng/ai-helpers foundations --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/foundations .agents/skills/foundations && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "foundations" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/bigquery-ci-data/skills/foundations into .agents/skills/foundations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foundations", 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 foundations -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install openshift-eng/ai-helpers foundations --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/foundations .cursor/skills/foundations && 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 "foundations" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/bigquery-ci-data/skills/foundations into .cursor/skills/foundations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foundations", 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/foundations--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 foundations -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install openshift-eng/ai-helpers foundations --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/foundations .gemini/skills/foundations && 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 "foundations" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/bigquery-ci-data/skills/foundations into .gemini/skills/foundations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foundations", 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 foundationsInstalls 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 foundations -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/foundations .github/skills/foundations && 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 "foundations" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/bigquery-ci-data/skills/foundations into .github/skills/foundations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foundations", 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 foundations -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 foundations --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/foundations .opencode/skills/foundations && 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 "foundations" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/bigquery-ci-data/skills/foundations into .opencode/skills/foundations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foundations", 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
foundations- GitHub stars
- 120
- Token cost
- ~1.2k tokens
- SKILL.md length
- 575 words
- Files
- 1
- Skills in repo
- 118
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A skill your agent uses when executing any BigQuery CI data query — provides the shared safety protocol, cost controls, bq CLI patterns, and caching workflow
- Works in 5 steps: Understand the Question → Build the Query → Show, Dry-Run, Confirm Cost → …
- Executing any BigQuery CI data query — provides the shared safety protocol
- SKILL.md covers Prerequisites, Projects and Datasets, Cost Safety Protocol and Partition and Clustering Filters, plus 5 more sections
- Calls bq and gcloud
What it does
Foundations is an agent skill from openshift-eng/ai-helpers. Use when executing any BigQuery CI data query — provides the shared safety protocol, cost controls, bq CLI patterns, and caching workflow
Its SKILL.md is about 1.2k 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, Caching and Budgeting and forecasting. 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
- Executing any BigQuery CI data query — provides the shared safety protocol
- Bq CLI patterns
- Caching workflow
Example prompts
- “/foundations”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
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
Shell commands in SKILL.md call:
bqgcloud
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gcloud, which can reach the network depending on how they are called.
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
Foundations loads about 1.2k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 575 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). 575 words, ~1,174 tokens.
Download SKILL.mdSave it as
.claude/skills/foundations/SKILL.md (or your agent's skills folder).- name
- foundations
- description
- Use when executing any BigQuery CI data query — provides the shared safety protocol, cost controls, bq CLI patterns, and caching workflow
BigQuery CI Data Foundations
Shared foundations for all CI data BigQuery skills. Every skill in this plugin follows these protocols.
Prerequisites
bqCLI installed and authenticated (gcloud auth login)- BigQuery read access to the relevant projects
Projects and Datasets
| Project | Dataset | Purpose |
|---|---|---|
openshift-gce-devel | ci_analysis_us | Primary engineering CI data (jobs, junit, variants, labels) |
openshift-gce-devel | ci_analysis_qe | QE CI data (same schema as ci_analysis_us, smaller) |
openshift-ci-data-analysis | ci_data_autodl | Auto-collected data from test runs (disruption, CPU, audit logs, risk analysis, etc.) |
Always pass --project_id=<project> explicitly to all bq commands.
Cost Safety Protocol
Non-negotiable. Every query follows this flow:
- Show the query to the user before doing anything
- Dry-run to get bytes scanned:
bash bq query --project_id=<project> --dry_run --use_legacy_sql=false '<query>' - Calculate cost:
bytes / 10^12 * $6.25(on-demand pricing) - If cost > $1.00: show estimated cost and bytes, ask user to confirm
- If cost <= $1.00: proceed, report cost in results
- Never loop or repeat queries. Run once, cache locally, analyze from cached data.
Partition and Clustering Filters
When a table is partitioned, every query MUST include a filter on the partition column to avoid full-table scans. Use tight date ranges. Not all tables are partitioned (e.g. job_variants is small and unpartitioned).
When a table is clustered, filter on the clustering column too for major cost reduction.
Caching Results Locally
After executing a query, save results to .work/bigquery-ci-data/ as JSON or CSV. Name files descriptively.
Always query fresh — never skip a query because a cached file with a similar name already exists. CI data changes continuously; stale cache files produce misleading results. Use cached files only for follow-up analysis of the same data within the same conversation, and re-query if more than 4 hours have passed since the cache was written.
Execution Workflow
For every user request:
Step 1: Understand the Question
Identify which table(s), date range, and filters are needed. Ask if date range is not specified — suggest a narrow range.
Step 2: Build the Query
- Include partition column filter with tight date range
- Include clustering filters when applicable
- Use
--use_legacy_sql=false - Select only needed columns on large tables
Show full SKILL.md (237 more words)Show less
Step 3: Show, Dry-Run, Confirm Cost
Present query, run dry-run, calculate and report cost. Confirm with user if over $1.00. Strongly recommend narrowing if over $10.00.
Step 4: Execute and Cache
mkdir -p .work/bigquery-ci-data
bq query --project_id=<project> --use_legacy_sql=false --format=json --max_rows=10000 '<query>' > .work/bigquery-ci-data/<descriptive-name>.jsonRow limit caveat: --max_rows=10000 truncates output. Prefer SQL-level aggregation (GROUP BY, COUNT, AVG) or LIMIT so the query returns complete results within the cap. If raw rows are needed and the result hits 10,000 rows, increase --max_rows or add tighter filters before reporting totals or rankings from the output.
Step 5: Analyze and Report
Parse cached results. Include summary statistics, notable patterns, links to prow jobs when relevant, and suggestions for follow-up queries.
Autodl Loader Columns
All tables in ci_data_autodl automatically include three columns added by the ci-data-loader (not in the Go source schemas):
| Column | Type | Notes |
|---|---|---|
| JobRunName | STRING | Prow job run identifier |
| PartitionTime | TIMESTAMP | Partition column — always filter on this |
| Source | STRING | Data source identifier |
Query Optimization Tips
- Narrow date ranges first: Start with 7 days. Widen only if needed.
- Select only needed columns: Don't
SELECT *on large tables. - Filter early: Put the most selective filters in the WHERE clause.
- Avoid repeated queries: Cache results and analyze locally.
- Use exact match over LIKE: When you have exact IDs, use
=notLIKE.
Error Handling
- "BigQuery not enabled": Pass
--project_id=<project>explicitly - Authentication errors: Ask user to run
! gcloud auth login - Timeout on large queries: Suggest narrowing the date range
- No results: Verify names/IDs exist, check date range
© 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/foundations of openshift-eng/ai-helpers.
Open the folder on GitHubat commit a627176
Compare with similar skills
Foundations 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 |
|---|---|---|---|---|---|---|
| Foundations this skillopenshift-eng/ai-helpers | 120 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Neocarta Add Source Connectorneo4j-labs/neocarta | 146 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Write Script Bigquerywindmill-labs/windmill | 18k | — | ~2.2k | Automated safety check: Pass | Custom licence | |
| Bigquery Sentimentinfometa/workbuddyskills | 344 | — | ~3.3k | Automated safety check: Warn | None | |
| Ga4 Bigquery Schemacognyai/claude-code-marketing-skills | 104 | — | ~4.7k | Automated safety check: Notes | None | |
| Gx Ga4 Expertcriptogus/agent-evolve-network | 288 | — | ~749 | Automated safety check: Pass | MIT |
Similar skills
Write Script Bigquery
windmill-labs/windmill
MUST use when writing BigQuery queries.
Bigquery Sentiment
infometa/workbuddyskills
Core skill for game sentiment querying and analysis. An agent skill from infometa/workbuddyskills.
Ga4 Bigquery Schema
cognyai/claude-code-marketing-skills
GA4 BigQuery Export Schema Reference — complete field reference, nested structures, query patterns, and performance tips
Gx Ga4 Expert
criptogus/agent-evolve-network
Configure GA4 properties, GTM, custom events, conversions, audiences, and BigQuery export.
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.
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 Foundations
What does Foundations do?
A skill your agent uses when executing any BigQuery CI data query — provides the shared safety protocol, cost controls, bq CLI patterns, and caching workflow. Foundations is an agent skill from openshift-eng/ai-helpers.
When should I use Foundations?
Foundations fits situations like: executing any BigQuery CI data query — provides the shared safety protocol; bq CLI patterns; caching workflow.
How do I install Foundations in Claude Code?
Run `npx skills add openshift-eng/ai-helpers --skill foundations -a claude-code`. Or copy the skill folder (plugins/bigquery-ci-data/skills/foundations in openshift-eng/ai-helpers) into .claude/skills/foundations in your project. Claude Code loads it when a task matches its description.
How do I install Foundations in Codex?
Run `npx skills add openshift-eng/ai-helpers --skill foundations -a codex`. Or copy the skill folder (plugins/bigquery-ci-data/skills/foundations in openshift-eng/ai-helpers) into .agents/skills/foundations in your project. Codex loads it when a task matches its description.
Can I use Foundations 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 foundations -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/foundations, .gemini/skills/foundations, .github/skills/foundations and .opencode/skills/foundations in your project.
What does Foundations need to run?
Going by SKILL.md and its folder, Foundations needs the command-line tools its instructions call (bq and gcloud).
Does Foundations 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 Foundations 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 Foundations use?
Foundations 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 Foundations use?
About 1.2k tokens (SKILL.md is roughly 4.7k 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 Foundations?
Skills that share tags, products or a category with Foundations: Neocarta Add Source Connector (neo4j-labs/neocarta, 146 stars), Write Script Bigquery (windmill-labs/windmill, 18k stars), Bigquery Sentiment (infometa/workbuddyskills, 344 stars) and Ga4 Bigquery Schema (cognyai/claude-code-marketing-skills, 104 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Foundations?
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.