Content

Longform to Asset Pack

Turn one dense source into a small, traceable distribution kit instead of posting chopped-up leftovers.

Use when

A valuable longform source should become multiple useful public artifacts without flattening nuance or leaking private context.

Intermediatedifficulty
Contentcategory
Mia daily expansionsource

Cadence

After publishing or recording a substantial essay, talk, podcast, demo, or research note

Verification

Each drafted asset traces to the source, preserves the original claim, strips private details, and stays unpublished until approved.

Structured loop spec

FieldValue
NameLongform to Asset Pack
CategoryContent
TriggerAfter publishing or recording a substantial essay, talk, podcast, demo, or research note
ObjectiveTurn one dense source into a small, traceable distribution kit instead of posting chopped-up leftovers.
Allowed inputsRelevant files, source notes, logs, tests, screenshots, metrics, or task state for this loop
Allowed actionsIdentify the source's strongest claims, examples, counterpoints, and audience-specific takeaways with timestamps or section links.; Choose 3-5 asset types that fit the source: short post, carousel outline, newsletter section, clip brief, FAQ, or sales enablement note.; Draft each asset with a source citation, intended audience, platform, hook, and safe redactions for names, numbers, clients, or unreleased plans.; Check that no asset adds unsupported claims, impersonates someone else, violates platform context, or publishes sensitive material.; Return the asset pack and approval queue; do not post, schedule, email, or share externally without explicit approval.
VerificationEach drafted asset traces to the source, preserves the original claim, strips private details, and stays unpublished until approved.
Stop conditionStop when the verifier passes, the budget is exhausted, no progress is made, a blocker appears, or approval is required.
BudgetSet a time, turn, token, retry, file, or dollar cap before running the loop.
Approval boundaryHuman approval required before publishing, sending, deleting, spending, changing accounts, touching production, or making reputational/legal/financial commitments.
Safe outputDraft, report, checklist, table, or approval-gated recommendation
Works withClaude, ChatGPT, Gemini, any tool-using AI assistant

Steps

  1. Identify the source's strongest claims, examples, counterpoints, and audience-specific takeaways with timestamps or section links.
  2. Choose 3-5 asset types that fit the source: short post, carousel outline, newsletter section, clip brief, FAQ, or sales enablement note.
  3. Draft each asset with a source citation, intended audience, platform, hook, and safe redactions for names, numbers, clients, or unreleased plans.
  4. Check that no asset adds unsupported claims, impersonates someone else, violates platform context, or publishes sensitive material.
  5. Return the asset pack and approval queue; do not post, schedule, email, or share externally without explicit approval.

Prompt

Run the Longform to Asset Pack loop. Given a substantial essay, talk, podcast, demo, transcript, or research note, extract the strongest claims, examples, counterpoints, and audience-specific takeaways with source anchors. Create 3-5 drafted assets such as a short post, carousel outline, newsletter section, clip brief, FAQ, or sales enablement note. For each asset, include audience, platform, hook, source trace, and required redactions. Do not add unsupported claims or publish, schedule, email, or share externally without explicit approval. Return the asset pack, evidence map, and approval queue.

Run in Claude Code

Paste this into Claude Code (or any tool-using agent) to run the loop bounded: one change per round, the same verification every round, durable state files, and explicit stop conditions.

Run the "Longform to Asset Pack" loop from AI Loop Library (https://ailooplibrary.com/loops/longform-to-asset-pack/) as a bounded loop.
Goal: Turn one dense source into a small, traceable distribution kit instead of posting chopped-up leftovers.
Rules: one change per round; run the same verification every round (Each drafted asset traces to the source, preserves the original claim, strips private details, and stays unpublished until approved.); append each round to docs/loops/longform-to-asset-pack/progress.md and update docs/loops/longform-to-asset-pack/state.json; stop on verifier pass, 8 rounds, 3 consecutive failed verifications, no progress, a blocker, or anything needing human approval (money, production, outbound, deletion). Finish with a proof report: rounds used, changes made, verification output, remaining risk, and the next human decision.

Get the MCP server + agent pack

Tags

repurposingcontent workflowapproval gateddistribution

Related

Back to all examples