Menú
Produce an approved ecosystem briefing from bounded research and a governed content pass.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
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 | ecosystem-brief |
| description | Produce an approved ecosystem briefing from bounded research and a governed content pass. |
| runx | {"category":"research"} |
This graph is the specialized daily-brief variant of content-pipeline.
It is for one decision-ready ecosystem update: what changed, why it matters, and what the operator should do with that information. The output should feel like a sharp daily brief, not a generic article.
Lead with the operational implication, then show the sources, verified change,
inference, and uncertainty behind it. Connect a signal to product, catalog,
trust, distribution, or positioning only when the evidence supports that link.
Return needs_more_evidence for an unverifiable signal and
not_worth_publishing for a true update that gives the operator no useful next
posture.
ecosystem_brief: what changed, why it matters, evidence, implications, and recommendation.open_uncertainties: claims or movement that remain unverified.approval_decision: review of the exact brief.publish_packet: approved brief and channel metadata.objective (optional): specific question for the market scan.audience (optional): who will read the brief.channel (optional): output channel; defaults to brief.domain (optional): ecosystem slice to monitor.operator_context (optional): decision context or evaluation lens for the brief.target_entities (optional): structured list of projects or companies the scan
should compare or monitor.