Align reusable Content skills with demo and proof conversion #889

Open
opened 2026-08-05 00:40:31 +00:00 by coilyco-ops · 0 comments
Member

Parent

coilyco-flight-deck/agent-compose#186

What to build

Audit and update AOS's reusable public-safe content capabilities for the Sales, Content, and Outreach trifecta.

The capability gap is not generic writing. Content Manager needs a repeatable method for turning real technical work into reusable proof that compounds across market conversations: demos, walkthroughs, case studies, architecture narratives, presentations, and channel adaptations.

Run the skill-admission test against the existing writing, documentation, visualization, presentation, and voice-adaptation surfaces. Extend or add only the smallest source that creates a demonstrated behavioral delta.

Required capability

The admitted update must cover:

  • selecting a real artifact and defining the audience decision it should support
  • separating observed facts, inferences, and unsupported claims
  • demo and walkthrough narrative design
  • technical case studies with decisions, tradeoffs, failures, evidence, and outcomes
  • architecture explanations that remain accurate under compression
  • reusable source material plus channel-specific adaptations
  • handoff shapes for Outreach personalization and Sales evidence selection
  • provenance, claim review, and publication authority boundaries

Do not add a new voice system, duplicate presentation or visualization instructions, or invent customers, revenue, adoption, scale, production impact, or commercial outcomes.

Placement boundary

Keep generalizable proof-building and content-reuse methods in AOS ordinary skills. Keep role identity in Agent Compose. Keep Kai's voice, portfolio claims, hiring narrative, private history, and live campaign state in AOSK or runtime retrieval.

Acceptance criteria

  • Existing content, writing, documentation, visualization, and presentation skills are mapped before any new source is admitted.
  • Every changed or new skill passes the admission test and has a precise trigger boundary.
  • The smallest coherent update supports demos, case studies, architecture narratives, and reusable channel adaptations without becoming a generic writing encyclopedia.
  • The workflow separates source evidence, audience decision, reusable core, channel adaptation, claims requiring qualification, and publication state.
  • Outreach and Sales handoffs consume Content artifacts without transferring ownership of the reusable source.
  • Should-trigger and should-not-trigger prompt sets include adjacent voice-editing, documentation-only, design, sales, and outreach near misses.
  • Objective assertions require provenance and reject invented commercial or production claims.
  • Matched cold-versus-skilled task evaluation uses an approved cost-controlled model route, or execution is explicitly skipped without claiming measured improvement.
  • Documentation and feature inventory reflect only a material shipped capability change.
  • Repository validation passes through declared Ward verbs.

Blocked by

## Parent https://forgejo.coilysiren.me/coilyco-flight-deck/agent-compose/issues/186 ## What to build Audit and update AOS's reusable public-safe content capabilities for the Sales, Content, and Outreach trifecta. The capability gap is not generic writing. Content Manager needs a repeatable method for turning real technical work into reusable proof that compounds across market conversations: demos, walkthroughs, case studies, architecture narratives, presentations, and channel adaptations. Run the skill-admission test against the existing writing, documentation, visualization, presentation, and voice-adaptation surfaces. Extend or add only the smallest source that creates a demonstrated behavioral delta. ## Required capability The admitted update must cover: * selecting a real artifact and defining the audience decision it should support * separating observed facts, inferences, and unsupported claims * demo and walkthrough narrative design * technical case studies with decisions, tradeoffs, failures, evidence, and outcomes * architecture explanations that remain accurate under compression * reusable source material plus channel-specific adaptations * handoff shapes for Outreach personalization and Sales evidence selection * provenance, claim review, and publication authority boundaries Do not add a new voice system, duplicate presentation or visualization instructions, or invent customers, revenue, adoption, scale, production impact, or commercial outcomes. ## Placement boundary Keep generalizable proof-building and content-reuse methods in AOS ordinary skills. Keep role identity in Agent Compose. Keep Kai's voice, portfolio claims, hiring narrative, private history, and live campaign state in AOSK or runtime retrieval. ## Acceptance criteria * [ ] Existing content, writing, documentation, visualization, and presentation skills are mapped before any new source is admitted. * [ ] Every changed or new skill passes the admission test and has a precise trigger boundary. * [ ] The smallest coherent update supports demos, case studies, architecture narratives, and reusable channel adaptations without becoming a generic writing encyclopedia. * [ ] The workflow separates source evidence, audience decision, reusable core, channel adaptation, claims requiring qualification, and publication state. * [ ] Outreach and Sales handoffs consume Content artifacts without transferring ownership of the reusable source. * [ ] Should-trigger and should-not-trigger prompt sets include adjacent voice-editing, documentation-only, design, sales, and outreach near misses. * [ ] Objective assertions require provenance and reject invented commercial or production claims. * [ ] Matched cold-versus-skilled task evaluation uses an approved cost-controlled model route, or execution is explicitly skipped without claiming measured improvement. * [ ] Documentation and feature inventory reflect only a material shipped capability change. * [ ] Repository validation passes through declared Ward verbs. ## Blocked by * The updated Content Manager boundary must land from https://forgejo.coilysiren.me/coilyco-flight-deck/agent-compose/issues/186. * High-volume model evaluation is cost-gated by https://forgejo.coilysiren.me/coilyco-bridge/agentic-os-hardware/issues/83 and any approved downstream Agent Proxy route.
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference
coilyco-flight-deck/agentic-os#889
No description provided.