skills/pipeline/SKILL.md
Automated multi-agent pipeline for any project. Use when ANY task needs rigorous Bug Fix, Feature, User Story, Audit, or UX Simulation execution with TDD, adversarial review, and gate enforcement. Invoked via `/pipeline-orchestrator:pipeline [task]`.
npx skillsauth add fernandoxavier02/pipeline-orchestrator pipelineInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill's ONLY job is to spawn the pipeline-controller agent. All orchestration logic lives in the controller's prompt, running in an isolated subagent context. This design eliminates main-LLM bypass of the pipeline protocol.
Invoke the controller agent with the user's full request as prompt:
Agent(
subagent_type: "pipeline-orchestrator:core:pipeline-controller",
description: "Orchestrate pipeline for the user request",
prompt: "{{arguments}}"
)
edit-guard-hook will block you. Delegate all edits to the controller./pipeline-orchestrator:pipeline, they want the pipeline. If it's truly too small, the controller will propose SIMPLES+DIRETO and ask for confirmation.The controller returns a PIPELINE COMPLETE block as its tool result. Pass it to the user verbatim.
Legacy orchestration spec (900 lines) is preserved at skills/pipeline/SKILL.v3-reference.md. The controller agent's prompt (agents/core/pipeline-controller.md) inherits and updates this spec.
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.