Menu
Research a topic, draft the content, and package the approved publication bundle.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Governed runtime for agent skills: discover and install portable skills, run bounded skill graphs with explicit authority, and inspect signed receipts for what happened.
Audit a sealed runx receipt for governance, comparing the authority a run exercised against what it was granted, and flag over-reach, ungated mutation, unrecorded refusals, or exposed secret material.
Verify the receipt ids behind a normalized authority-usage summary, compare that evidence with granted scopes, and propose the narrowest grant the evidence supports.
Answer a cross-run audit question against the receipt ledger, returning matched receipts and a chain-verification result.
Read durable reflect projections, group repeated signals by skill, and emit validated handoffs to skill-lab improve when the evidence clears configured floors.
Review receipts and harness failures to propose bounded skill improvements.
| name | content-pipeline |
| description | Research a topic, draft the content, and package the approved publication bundle. |
| runx | {"category":"content"} |
This is the standard publish lane for runx-authored public content.
It keeps evidence collection, drafting, and publication packaging as separate steps so the operator can approve one concrete draft before anything is turned into a publish packet.
The research packet must support every substantive public claim. Draft in the
declared channel's vocabulary for its actual readers; do not turn the graph
trace into generic thought leadership. A useful result should change something
for the reader—understanding, a decision, trust, adoption, or a concrete
follow-up. Return needs_more_evidence, needs_review, or
not_worth_publishing when the topic is stale, duplicative, weakly supported,
or true but not useful.
research_packet: bounded sources, verified claims, inference, and gaps.draft_content: the reader-facing artifact grounded in that packet.approval_decision: the operator's decision on the exact draft.publish_packet: approved content and channel metadata, never an implicit publish.objective (required): what the content should accomplish.audience (optional): intended reader or operator segment.channel (optional): publication channel; defaults to blog.domain (optional): ecosystem or market area to research.operator_context (optional): constraints, voice, or campaign context.target_entities (optional): structured list of products, projects, or
actors the research pass should keep in view.