code-refine

Solid

Use only when autopilot-code dispatches plan revision after user notes, plan-check feedback, or verification failure. Not for top-level user requests or primary capability routing.

AI & Automation 7 stars 1 forks Updated today MIT

Install

View on GitHub

Quality Score: 81/100

Stars 20%
30
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# code-refine > **Plan resolution**: Treat [arguments-and-decisions.md#plan-resolution](../autopilot-code/references/arguments-and-decisions.md) as the single authority for resolving `$ARGUMENTS`. Recognize both canonical `plan.md` and any existing companion such as legacy `plan_ko.md`; swap between known companion paths only when both files actually belong to the same plan. > **Language rule**: Follow the audience and artifact language contract in [arguments-and-decisions.md#language-rule](../autopilot-code/references/arguments-and-decisions.md). Preserve the canonical plan's selected language and synchronize only companions that already exist or are explicitly required. ## Delegate Refinement Re-enter the `plan/plan-author` unit boundary with this task: ```text Refine mode. Update an existing implementation plan from user memos, plan-check feedback, or verification-failure notes. Supplied plan: {$ARGUMENTS} Canonical plan: {resolved plan.md path} Existing companion plans: {resolved paths, or none} Read the supplied and canonical plan files and identify user memos per your refine-mode memo forms; additionally treat any HTML comment as a user memo. Do not treat original plan prose as a memo. Then follow your refine-mode procedure and return format. ``` Memo forms, in-place update, companion synchronization, and the single-line return contract are owned by the `plan/plan-author` unit persona; do not restate them in the prompt. ## Refine Assurance Derive verification ...

Details

Author
dmlguq456
Repository
dmlguq456/hearting
Created
5 months ago
Last Updated
today
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category