How do I install the Autonomous Content Pipeline skill?

Run npx skillmds@latest add knuckles-team/autonomous-content-pipeline in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Autonomous Content Pipeline safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Autonomous Content Pipeline?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Autonomous Content Pipeline free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Autonomous Content Pipeline?

Knuckles-Team (@knuckles-team) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Autonomous Content Pipeline by knuckles-team

Name: Autonomous Content Pipeline
Author: Knuckles-Team

Autonomous Content Pipeline

Research, outline, draft, verify, edit, and preflight a batch of sourced content pieces by composing the catalog's atomic research and content skills, unattended. Use when a user has supplied a topic list, audience, objective, and publication requirements and wants review-ready drafts produced without manual handoffs between steps; this workflow never publishes.

Knuckles-Team c9326dc 2 files · 2.8 KB Updated Sep 17, 2026

File contents

Autonomous Content Pipeline Workflow

Compose the named atomic skills without adding editorial or publication logic here.

Inputs

Provide the topic list, audience, objective, channel and length constraints, voice guide, citation style, and publication requirements.

Steps

Step 0: web-search [skill: web-search]

Invoke $web-search with the workflow inputs for each topic.

Expected: source_packet

Step 1: content-outline-builder [skill: content-outline-builder] [depends_on: Step 0]

Invoke $content-outline-builder with the workflow inputs and source_packet.

Expected: approved_outline

Step 2: content-draft-writer [skill: content-draft-writer] [depends_on: Step 1]

Invoke $content-draft-writer with the workflow inputs, source_packet, and approved_outline.

Expected: sourced_draft

Step 3: citation-auditor [skill: citation-auditor] [depends_on: Step 2]

Invoke $citation-auditor with sourced_draft and source_packet.

Expected: citation_audit

Step 4: copy-editor [skill: copy-editor] [depends_on: Step 3]

Invoke $copy-editor with sourced_draft, citation_audit, and the workflow inputs.

Expected: edited_draft

Step 5: publication-preflight [skill: publication-preflight] [depends_on: Step 4]

Invoke $publication-preflight with edited_draft, citation_audit, and the publication requirements.

Expected: readiness_decision

Output

Return edited_draft, citation_audit, and readiness_decision for each topic. Do not publish, schedule, send, or upload any piece.

Execution

Run first: Step 0 — $web-search.
After level 0: Step 1 — $content-outline-builder.
After level 1: Step 2 — $content-draft-writer.
After level 2: Step 3 — $citation-auditor.
After level 3: Step 4 — $copy-editor.
After level 4: Step 5 — $publication-preflight.

Execution: If graph-os is reachable, offload the whole DAG via graph_orchestrate action=execute_workflow (or the kg-delegate skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet depends_on in parallel, then their dependents.

---name: autonomous-content-pipelinedescription: Research, outline, draft, verify, edit, and preflight a batch of sourced content pieces by composing the catalog's atomic research and content skills, unattended. Use when a user has supplied a topic list, audience, objective, and publication requirements and wants review-ready drafts produced without manual handoffs between steps; this workflow never publishes.license: MIT---# Autonomous Content Pipeline WorkflowCompose the named atomic skills without adding editorial or publication logichere.## InputsProvide the topic list, audience, objective, channel and length constraints,voice guide, citation style, and publication requirements.## Steps### Step 0: web-search [skill: web-search]Invoke `$web-search` with the workflow inputs for each topic.Expected: `source_packet`### Step 1: content-outline-builder [skill: content-outline-builder] [depends_on: Step 0]Invoke `$content-outline-builder` with the workflow inputs and`source_packet`.Expected: `approved_outline`### Step 2: content-draft-writer [skill: content-draft-writer] [depends_on: Step 1]Invoke `$content-draft-writer` with the workflow inputs,`source_packet`, and `approved_outline`.Expected: `sourced_draft`### Step 3: citation-auditor [skill: citation-auditor] [depends_on: Step 2]Invoke `$citation-auditor` with `sourced_draft` and `source_packet`.Expected: `citation_audit`### Step 4: copy-editor [skill: copy-editor] [depends_on: Step 3]Invoke `$copy-editor` with `sourced_draft`, `citation_audit`, and theworkflow inputs.Expected: `edited_draft`### Step 5: publication-preflight [skill: publication-preflight] [depends_on: Step 4]Invoke `$publication-preflight` with `edited_draft`,`citation_audit`, and the publication requirements.Expected: `readiness_decision`## OutputReturn `edited_draft`, `citation_audit`, and `readiness_decision` for eachtopic. Do not publish, schedule, send, or upload any piece.## Execution- **Run first:** Step 0 — `$web-search`.- **After level 0:** Step 1 — `$content-outline-builder`.- **After level 1:** Step 2 — `$content-draft-writer`.- **After level 2:** Step 3 — `$citation-auditor`.- **After level 3:** Step 4 — `$copy-editor`.- **After level 4:** Step 5 — `$publication-preflight`.**Execution:** If graph-os is reachable, offload the whole DAG via `graph_orchestrate action=execute_workflow` (or the `kg-delegate` skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet `depends_on` in parallel, then their dependents.

Frequently asked questions