Skip to content

[skill] Propose issue-ledger-followup for amendment-aware work loops #113

@auscaster

Description

@auscaster

Objective

Propose a portable issue-ledger-followup skill that turns one living work issue ledger into the next high-signal machine update or maintainer handoff packet.

Why

We want one issue per unit of work. Human amendments in that same thread should sharpen the next run instead of fragmenting context across dispatch UIs, separate proposal issues, or hidden memory.

Desired Contract

  • Input is portable subject memory, with GitHub issue threads as one adapter surface.
  • The skill reads the work issue ledger plus trusted amendment comments.
  • It emits a bounded follow-up packet for one next action: clarifying comment, approval request, maintainer handoff, or draft PR refresh request.
  • It must preserve receipts and keep the issue thread as the human-visible ledger.
  • It should stop at an explicit handoff boundary, not silently publish.

What We Want To Learn

  • Whether skill-lab now treats the issue thread as the canonical living ledger.
  • Whether the generated proposal stays tight around subject memory, outbox, receipts, and handoff boundaries.
  • Whether a later human amendment comment in this same issue cleanly retriggers the lane and sharpens the proposal.

Constraints

  • Prefer one skill with a small, legible surface.
  • No provider-locked nouns in the core contract.
  • Keep the proposal grounded in the current runx / aster vocabulary.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions