Menu
Diagnose and fix CI pipeline failures. Step-by-step debugging with sem-ai.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Deploy via Semaphore promotions. Manage deployment targets, promote pipelines, deploy-and-wait.
Manage Semaphore infrastructure — secrets, notifications, agent types, scheduled tasks, artifacts.
Diagnose sem-ai plugin issues when the sem-ai binary isn't installed yet, and guide the user through binary install. Use when the user reports sem-ai not working, MCP tools missing, slash command not found, `sem-ai connect` failing, or sees "command not found: sem-ai".
Triage and FIX flaky tests on a Semaphore project end-to-end — find the worst offenders, pull history, locate the test in the code, diagnose the root cause, write a fix or justified quarantine, and verify by re-running. Use whenever the user wants to fix/investigate flaky tests, de-flake CI, reduce intermittent failures, asks "why is CI randomly red", wants to quarantine a flake, or after `sem-ai flaky list` surfaces offenders. Goes BEYOND detection (test-intelligence) to root-cause + code change + verification.
Translate a repo's GitHub Actions workflows into an equivalent Semaphore pipeline. ONLY covers the GHA→Semaphore mapping and conversion procedure; for Semaphore-side depth (cache CLI, test-results, blocks structure, sharding, promotions) defer to the linked skills. Use when the user asks to convert/port/migrate GitHub Actions to Semaphore, says "translate this workflow" or "convert ci.yml", or the repo has `.github/workflows/` and the user wants Semaphore instead. Can be invoked directly as `/sem-ai:gha-to-semaphore` (or via the broader `/sem-ai:init` orchestrator).
Initialize Semaphore CI/CD for the current repository — bootstrap the Semaphore project, write a working `.semaphore/semaphore.yml` (translating from GitHub Actions if present, or from scratch), wire required secrets, validate, and watch the first workflow. Applies Semaphore-side defaults automatically — agent image, toolbox CLIs, `test-results` epilogue rule, sharding heuristics — by routing through the linked skills. Use when the user wants to set up CI on Semaphore, says "initialize", "bootstrap CI", "prepare CI/CD for this project", "create a workflow on Semaphore", "make a `.semaphore` config", or runs `/sem-ai:init`.
| name | debug-pipeline |
| description | Diagnose and fix CI pipeline failures. Step-by-step debugging with sem-ai. |
| user-invocable | false |
sem-ai diagnose <workflow-id>
# or auto-detect from git:
sem-ai diagnose
sem-ai diagnose --project my-app --branch main # --project/--branch optional, auto-detected from origin + HEAD
Returns: pipeline result, failed blocks, failed jobs with log tails AND parsed test results (file:line:message).
sem-ai workflow list --branch feature-x # --project/--branch optional, auto-detected from origin + HEAD
sem-ai pipeline show <pipeline-id>
# Shows blocks and jobs. Look for "result": "failed"
sem-ai job log <job-id> # structured JSON
sem-ai job log <job-id> --format table # human-readable
sem-ai test summary --pipeline <id>
Example output:
{
"verdict": "failed",
"total": 11, "passed": 10, "failed": 1,
"failures": [{"job": "go test", "test": "Test_timeHandler_statusCode", "file": "main_test.go", "line": 243, "message": "expected status 201, got 200"}]
}
sem-ai troubleshoot workflow <id>
sem-ai troubleshoot pipeline <id>
sem-ai troubleshoot job <id>
sem-ai test flaky --count 10 # --project optional, auto-detected from origin
sem-ai workflow rerun <id> # full rerun
sem-ai rerun-failed <pipeline-id> # rebuild failed blocks only
sem-ai watch <new-workflow-id> # wait for completion
sem-ai test summary --pipeline <id> # verify
sem-ai watch <id> is for when you already hold the id from workflow rerun output. To re-find and watch the rerun for your exact commit (e.g. after pushing the fix), use the watch-after-push pattern: find the run by commit_sha, then sem-ai watch it.
| Log pattern | Cause | Next step |
|---|---|---|
exit_code: 1 on test command | Test failure | sem-ai test summary --pipeline <id> |
Pipeline stuck initializing | YAML error | sem-ai yaml validate --file .semaphore/semaphore.yml |
result_reason: "stuck" | No agent available | sem-ai agent types |
| All blocks empty | Compile failed | sem-ai troubleshoot pipeline <id> |
cache errors | Cache not configured | Environment issue, not code |