Menü
Guides an autonomous blog manager agent to propose topics, draft articles, and skip topics with structured JSON output for a Leaflet.pub publication.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | blog-manager |
| description | Guides an autonomous blog manager agent to propose topics, draft articles, and skip topics with structured JSON output for a Leaflet.pub publication. |
| license | MIT |
| metadata | {"author":"greedychipmunk","version":"1.0"} |
Guide an autonomous blog manager that proposes topics, researches and writes articles, and publishes them to a Leaflet.pub blog.
Always respond with exactly one JSON block wrapped in ```json fences. The JSON must have an "action" field that identifies the operation.
When asked to generate topic ideas:
{
"action": "propose_topics",
"topics": [
{"title": "Specific Topic Title", "subject": "AI agents"},
{"title": "Another Topic", "subject": "workflow automation"}
]
}
Provide 3-5 topics. Each topic must:
"title" (string) that is specific and teaches one concrete idea"subject" (string) that matches one of the blog's defined subjectsWhen asked to write an article:
{
"action": "draft_article",
"title": "Article Title",
"subject": "AI agents",
"body_markdown": "Full article in Markdown..."
}
The article must:
#, ##), paragraphs, lists, inline code, and linksWhen a proposed topic is too vague, already covered, or not worth a full article:
{
"action": "skip_topic",
"topic_title": "Topic Title",
"reason": "Short explanation of why this topic is being skipped"
}
"subject" field must always match one of the blog's defined subjectsDesign and build AI agents with persistent memory, tool use, and multi-turn conversation. Covers architecture selection, memory design, model selection, tool configuration, and implementation patterns across agent frameworks. Use when creating, debugging, or improving AI agents.
Automate configuration management and application deployment with Ansible. Use when tasks mention ansible-playbook, inventory files, Ansible roles, ad-hoc commands, ansible-galaxy, or agentless SSH automation.
Deploy Kubernetes apps declaratively with Argo CD applications and projects. Use when tasks mention argocd, Argo CD, argocd app sync, Application CRD, AppProject, or GitOps with Argo CD.
Query Datadog observability data including logs, metrics, monitors, dashboards, hosts, APM spans, and incidents via direct API. Use when investigating production issues, checking monitors, searching logs, alerting, or accessing Datadog data.
Build, run, debug, and manage Docker containers, images, compose files, networking, volumes, registries, Buildx/Bake, Scout/SBOM, Swarm, and Docker AI tooling. Use when the user mentions docker, containers, containerizing, Dockerfile, compose, image registry, volumes, or any docker subcommand.
Write and maintain GitHub Actions CI workflows, including workflow YAML structure, triggers, runners, matrix builds, caching, testing patterns, and secrets management. Use when working with .github/workflows, GitHub Actions, CI pipelines, workflow dispatch, or action configuration.