Menu
Debug and triage Semaphore CI pipelines/jobs with `sem-ai`, falling back to the legacy `sem` CLI only for interactive attach/debug flows that `sem-ai` does not cover.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Cuts a new release of ai-sdk — creates a Linear issue, branches, bumps version, updates changelog, runs checks, commits, opens a PR, and returns to main. Merging the PR triggers CI to auto-tag. Use when the user wants to release a new version of the ai_sdk gem.
References Semaphore's sem-ai CLI command set, output formats, safety defaults, and legacy sem replacement patterns. Use when exact sem-ai commands or flags are needed before inspecting or mutating Semaphore state.
Debugs and triages Semaphore CI pipelines and jobs with sem-ai first, falling back to legacy sem only for interactive attach/debug shells. Use when CI is failing, flaky, stuck, queued, or needs logs, reruns, stops, or deployment-state inspection.
Find an unreserved staging namespace and promote a Semaphore pipeline into it. Use when a user asks to pick a free `revNN`/`qaNN` server, trigger `Deploy to EKS staging`, or validate that promotion/deploy completed.
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
Promote an Amadeus PR to the shared `data` staging namespace using Semaphore `Deploy to Staging`, then verify the SLSA-backed artifact flow, deployed image, and live log contract through Kubernetes.
| name | semaphore-debugging |
| description | Debug and triage Semaphore CI pipelines/jobs with `sem-ai`, falling back to the legacy `sem` CLI only for interactive attach/debug flows that `sem-ai` does not cover. |
Use this skill for CI troubleshooting, stuck pipelines, flaky jobs, log inspection, and safe recovery actions.
Prefer sem-ai for structured inspection and mutation. Use the legacy sem
CLI only when there is no equivalent sem-ai command, mainly interactive job
shells.
sem-ai connect simplepractice.semaphoreci.com "$SEMAPHORE_API_TOKEN"
sem-ai context show
Fallback if env var is missing:
sem-ai connect simplepractice.semaphoreci.com <YOUR_API_TOKEN>
sem-ai shares the same ~/.sem.yaml context file as the legacy sem CLI.
# Let sem-ai collect the first pass of evidence.
sem-ai diagnose <workflow-id>
# If the workflow id is not known yet:
sem-ai status --project simplepractice --branch <branch>
sem-ai workflow list --project simplepractice --branch <branch>
# Drill down when diagnose is not enough.
sem-ai workflow show <workflow-id>
sem-ai pipeline show <pipeline-id>
sem-ai job log <job-id>
sem-ai test summary --pipeline <pipeline-id>
# Recovery after inspection.
sem-ai pipeline rebuild <pipeline-id>
sem-ai workflow rerun <workflow-id>
sem-ai watch <workflow-id>
# Discovery
sem-ai status --project simplepractice --branch <branch>
sem-ai workflow list --project simplepractice
sem-ai pipeline list --project simplepractice
sem-ai job list
# Inspection
sem-ai workflow show <workflow-id>
sem-ai pipeline show <pipeline-id>
sem-ai pipeline topology <pipeline-id>
sem-ai job show <job-id>
sem-ai job log <job-id>
sem-ai test summary --pipeline <pipeline-id>
sem-ai test report --pipeline <pipeline-id>
sem-ai blast-radius <pipeline-id>
sem-ai critical-path <pipeline-id>
# Recovery
sem-ai job stop <job-id>
sem-ai pipeline stop <pipeline-id>
sem-ai pipeline rebuild <pipeline-id>
sem-ai workflow rerun <workflow-id>
sem-ai rerun-failed <pipeline-id>
sem-ai watch <workflow-id>
sem FallbackUse sem only when the needed workflow is not available in sem-ai.
# Running jobs only.
sem attach <job-id>
# Finished jobs only; then source the reproduced command environment.
sem debug <job-id>
source ~/commands.sh
Do not use sem get or sem logs by default anymore. The equivalent
inspection path is sem-ai workflow show, sem-ai pipeline show, and
sem-ai job log.
sem-ai diagnose, sem-ai workflow show,
sem-ai pipeline show, or sem-ai job log before stop/rerun/rebuild.sem-ai defaults to JSON. Use --format table for human scanning and JSON
for scripts.--confirm; do not add it until the target,
parameters, and pipeline id have been verified.sem-ai <command> --help or
sem-ai discover before guessing.CI behavior is defined by repo files. Confirm before assumptions:
<app-repo>/.semaphore/ci.yml<app-repo>/.semaphore/*.sh<app-repo>/scripts/*ci*For simplepractice, treat change_in and branch-specific rules as the source
of truth from CI config.
Reference: https://docs.semaphore.io/reference/sem-ai-cli