write-maintainable-code

Solid

Evaluate minimum-sufficient implementation routes and enforce the selected route for a fixed, authorized outcome: decide whether code is needed, compare existing behavior, configuration, reuse, deletion, documentation, and no-code routes, locate the smallest code ownership seam, control speculative concepts, and keep a nontrivial implementation or refactor proportionate and testable. Use only after outcome, acceptance evidence, scope, and authority are fixed. Do not use to select or reframe outcomes, set acceptance evidence, adjudicate governance authority, seat responsibility, scope, or publication, discover a repository without an authorized implementation decision, grade completed work, design tests only, conduct a security audit, write documentation-only copy with no implementation decision, or perform unrelated style cleanup.

AI & Automation 16 stars 2 forks Updated 2 days ago MIT

Install

View on GitHub

Quality Score: 80/100

Stars 20%
41
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Write Maintainable Code Use the fewest concepts that satisfy the already-approved result and its acceptance evidence. Minimize current maintenance burden, not raw line count. ## Keep the ownership boundary This skill is a subordinate implementation lens inside the public method: - During CONVERGE, generate code/no-code route alternatives and possible code ownership seams. Let `reasoning-doctrine` own the stage, recommendation, rejected alternatives, hard stops, safe outcome slice, and transition to execution. - During EXECUTE, apply this lens to the selected route. Do not redefine the selected outcome, acceptance evidence, safe slice, or mutation method. - During an authorized repair, apply only this execution lens. `run-review-repair-loop` continues to own review, scoring, and repair iteration. - When governance is active, let `governed-operator` own authority, seats, scope, the formal contract, verdicts, publication boundaries, and Done. If the outcome or acceptance evidence is unresolved, return to `reasoning-doctrine`. If authority, seat responsibility, scope, or publication authority is unresolved, return to `governed-operator`. If a finished change needs review-only grading, use `run-review-repair-loop` and keep its Builder self-review separate from the independent-review and Done boundaries owned by `governed-operator`; do not score or approve under this lens. Re-enter this skill only for an authorized repair. ## Compare routes before adding code ...

Details

Author
Ezra144israel
Repository
Ezra144israel/governed-agent-skills
Created
2 weeks ago
Last Updated
2 days ago
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category