Automated summary
Orchestrates a full 5-phase pipeline from requirements to release, invoking sub-skills sequentially.
Strengths
- End-to-end automation from requirements to release
- Strict gate checks with immediate stop on failure
- Direct skill invocation without nested complexity
Limitations
- Requires all sub-skills to be properly configured
- Can be lengthy for complex projects with many iterations
When you need to run a complete and standardized pipeline from requirement gathering to delivery.
For isolated tasks or micro-changes that do not require the full workflow.
Security analysis
CautionThe skill orchestrates a pipeline by invoking other skills and running Node scripts. While not inherently malicious, the use of Bash to execute scripts could be leveraged if those scripts are compromised or if environment variables allow injection. The skill itself does not perform destructive actions, but caution is warranted due to the power of bash execution.
- •Uses Bash to execute Node.js scripts for logging and instrumentation; ensure these scripts are trusted and paths are secured.
Examples
/factory-runExécute le pipeline complet /factory-run avec instrumentation activée.name: factory-run description: "Pipeline complet requirements → release" allowed-tools: Read, Glob, Grep, Bash, Task, Skill
Factory Run - Pipeline Complet
Tu es l'orchestrateur master du pipeline complet requirements → release.
Workflow
Exécuter les 5 phases séquentiellement en invoquant chaque skill directement.
Chaque skill a son propre context: fork et gère sa délégation d'agent.
Initialisation
# Instrumentation (si activée)
node tools/instrumentation/collector.js skill '{"skill":"factory-run"}'
# Log démarrage
node tools/factory-log.js "PIPELINE" "started" "Démarrage du pipeline"
Phase 1 - BREAK
Invoque /factory-intake et attends le résultat.
Si Gate 1 échoue → STOP et rapport d'erreur.
Phase 2 - MODEL
Invoque /factory-spec et attends le résultat.
Si Gate 2 échoue → STOP et rapport d'erreur.
Phase 3 - ACT (planning)
Invoque /factory-plan et attends le résultat.
Si Gate 3 échoue → STOP et rapport d'erreur.
Phase 4 - ACT (build)
Invoque /factory-build et attends le résultat.
Si Gate 4 échoue → STOP et rapport d'erreur.
Phase 5 - DEBRIEF
Invoque /factory-qa et attends le résultat.
Si Gate 5 échoue → STOP et rapport d'erreur.
Finalisation
node tools/factory-log.js "PIPELINE" "completed" "Pipeline terminé avec succès"
Règles critiques
- Séquentiel strict : Chaque phase DOIT réussir (gate OK) avant la suivante
- Si un gate échoue → STOP immédiat, logger l'erreur, retourner rapport
- Pas de nesting : Invoquer les skills directement, ils gèrent leur propre fork
Rapport final
À la fin du pipeline, produire un résumé complet :
- Phases complétées avec statuts
- Artefacts générés (liste des fichiers créés)
- Issues détectées (si applicable)
- Prochaines étapes recommandées
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/factory-run-complete-pipeline-mm78nmxb/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/factory-run-complete-pipeline-mm78nmxb' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/factory-run-complete-pipeline-mm78nmxb/download' --output '.skill-downloads/factory-run-complete-pipeline-mm78nmxb/SKILL.md.part' && mv '.skill-downloads/factory-run-complete-pipeline-mm78nmxb/SKILL.md.part' '.skill-downloads/factory-run-complete-pipeline-mm78nmxb/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Read, Glob, Grep, Bash, Task, Skill
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/factory-run-complete-pipeline-mm78nmxb/SKILL.md' && test -s '.skill-downloads/factory-run-complete-pipeline-mm78nmxb/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/factory-run' && cp -R '.skill-downloads/factory-run-complete-pipeline-mm78nmxb' '.claude/skills/factory-run'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/factory-run-complete-pipeline-mm78nmxb'openskills read 'factory-run-complete-pipeline-mm78nmxb'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/factory-run-complete-pipeline-mm78nmxb/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Configure a Chat Channel with SecretRefs
DevOps
Set up chat channels using non-interactive commands, with secrets only as SecretRefs. Covers gather, mutate, repair, and prove steps for reliable delivery.
Investigate ClickHouse CI Failures
DevOps
Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL. Fetches failed tests, classifies flaky vs real regression, and checks for existing issues/fixes.
Ansible PR Review
DevOps
Reviews an Ansible PR following the project's standardized process, including changelog checks, test coverage validation, and feedback tracking.