Menu
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.
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
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.
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.
Interact with Langfuse and access its documentation. Use when needing to (1) query or modify Langfuse data programmatically via the CLI — traces, prompts, datasets, scores, sessions, and any other API resource, (2) look up Langfuse documentation, concepts, integration guides, or SDK usage, or (3) understand how any Langfuse feature works. This skill covers CLI-based API access (via npx) and multiple documentation retrieval methods.
| name | sem-ai-cli |
| description | 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. |
Reference for Semaphore's agent-oriented sem-ai CLI. For active CI triage,
use semaphore-debugging; this skill is the command map.
sem-ai connect simplepractice.semaphoreci.com "$SEMAPHORE_API_TOKEN"
sem-ai context show
sem-ai discover
sem-ai defaults to JSON output and supports --format table and
--format yaml. It shares ~/.sem.yaml with the legacy sem CLI.
# Context and auth
sem-ai connect <host> <token>
sem-ai context list
sem-ai context show
sem-ai context switch <name>
# Project and CI state
sem-ai project list
sem-ai status --project <project> --branch <branch>
sem-ai health --project <project>
sem-ai workflow list --project <project>
sem-ai workflow show <workflow-id>
sem-ai pipeline list --project <project>
sem-ai pipeline show <pipeline-id>
sem-ai job list
sem-ai job show <job-id>
# Logs and failure analysis
sem-ai diagnose <workflow-id>
sem-ai troubleshoot workflow <workflow-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>
sem-ai pipeline topology <pipeline-id>
# Recovery and mutation
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>
# Deploys and operations
sem-ai pipeline promote <pipeline-id> --target <promotion-name> --confirm
sem-ai promote-and-wait <pipeline-id> --target <promotion-name> --confirm
sem-ai deploy targets --project <project>
sem-ai secret list
sem-ai notification list
sem-ai task list --project <project>
sem-ai artifact list --scope jobs --id <job-id>
sem-ai artifact get --scope jobs --id <job-id> --path <path>
sem-ai testbox warmup --project <project>
sem-ai testbox run --id <testbox-id> "<command>"
sem-ai testbox ssh --id <testbox-id>
sem-ai testbox stop --id <testbox-id>
sem-ai yaml validate --file .semaphore/semaphore.yml
sem get workflows -p <project> -> sem-ai workflow list --project <project>
sem get workflow <workflow-id> -> sem-ai workflow show <workflow-id>
sem get pipelines -p <project> -> sem-ai pipeline list --project <project>
sem get pipeline <pipeline-id> -> sem-ai pipeline show <pipeline-id>
sem get jobs -> sem-ai job list
sem logs <job-id> -> sem-ai job log <job-id>
sem stop job <job-id> -> sem-ai job stop <job-id>
sem stop pipeline <pipeline-id> -> sem-ai pipeline stop <pipeline-id>
sem rebuild pipeline <pipeline-id> -> sem-ai pipeline rebuild <pipeline-id>
sem rebuild workflow <workflow-id> -> sem-ai workflow rerun <workflow-id>
Keep legacy sem only for interactive shells that sem-ai does not replace:
sem attach <job-id>
sem debug <job-id>
--confirm; verify target, parameters, and
pipeline id first.sem-ai <command> --help or sem-ai discover over guessing flags.sem-ai yaml validate before pushing pipeline config changes.Reference: https://docs.semaphore.io/reference/sem-ai-cli