CI Validate — Cross-Platform Workflow Runner
SkillDev toolsTrigger a CI workflow for a package, wait for completion, and report results
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the CI Validate — Cross-Platform Workflow Runner skill
What this skill tells your AI
The instructions your AI receives, as published by tetherto/qvac in packages/ocr-ggml/.agent/skills/ci-validate/SKILL.md and read by ahel’s review.
Trigger a CI workflow for a package, wait for it to complete, and report results.
Argument
The argument $ARGUMENTS is the package short name. See the CI Package Mapping table in .agent/knowledge/ci-validation.md for valid short names and their corresponding package directories.
The workflow name is: On PR Trigger (<short-name>) where <short-name> is the argument.
Steps
Step 1: Validate and push
- Confirm
$ARGUMENTSmatches one of the valid package names above. If not, show the list and stop. - Make sure all changes are committed. If there are uncommitted changes, warn and stop.
- Push the current branch to origin:
git push origin HEAD
Step 2: Trigger the workflow
Run: gh workflow run "On PR Trigger ($ARGUMENTS)" --repo tetherto/qvac --ref $(git branch --show-current)
If the trigger fails, show the error and stop.
Wait 5 seconds for the run to register, then find the run ID:
gh run list --repo tetherto/qvac --workflow "On PR Trigger ($ARGUMENTS)" --branch $(git branch --show-current) --limit 1 --json databaseId,status,conclusion,createdAt
Step 3: Monitor the run
Wait for the run to complete: gh run watch <run-id> --repo tetherto/qvac
Step 4: Report results
After the run completes, get the result:
gh run view <run-id> --repo tetherto/qvac
- If all jobs passed: Report success with a summary of platforms/jobs that passed.
- If any job failed:
- Get failed logs:
gh run view <run-id> --repo tetherto/qvac --log-failed - Show the user which jobs/platforms failed and the relevant error logs
- Ask if they want you to investigate and fix the issue
- Get failed logs:
For failure analysis, platform details, and troubleshooting: see .agent/knowledge/ci-validation.md.
Important: Only attempt to fix infra/CI failures (environment, config, workflow issues). If the failure is a code logic error (compilation error, test assertion, lint violation, type error), report the failure back to the user with the relevant logs — do not attempt to fix application code.
Step 5: Retry loop (if called by an agent, not interactively)
If running as part of an automated pipeline (not interactive):
- Analyze the failure logs using the classification guide in
.agent/knowledge/ci-validation.md - If infra failure: fix the CI/config issue, commit and push, re-trigger (go to Step 2)
- If code logic failure: stop and report back with the error logs, affected platforms, and which source files need attention
- If the same infra failure persists more than 5 times after fixes: document on the Asana task with full error logs, what was tried, and which platforms are affected — then STOP
Signals
- GitHub stars
- 601
- Forks
- 111
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
ci-validate- Source
- github.com/tetherto/qvac