Menu
Produce architecture improvement advice from architecture evidence and source inspection.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Fix bugs by reproducing the failure first, making the smallest correction, and proving the regression is covered. Use for bug reports, failing tests, and regressions.
Fix failing tests or CI by reading logs, identifying the smallest failing surface, making a minimal change, and rerunning targeted verification. Use when given CI logs, failing commands, or broken checks.
Scan relevant source, tests, commands, and existing project patterns before editing code. Use before non-trivial implementation, bug fixing, or refactoring when the right local pattern is unclear.
Control error handling, defaults, retries, compatibility paths, and fallback behavior. Use before adding catch blocks, defaults, shims, optional values, retries, or graceful degradation.
Prevent large-file growth and mixed-responsibility edits. Use when adding significant logic to a large file, mixed-purpose module, or file with repeated conditionals.
Implement the smallest safe repo-native code change for the requested behavior. Use for feature work, small refactors, and multi-file implementation tasks.
| name | archi-advice |
| description | Produce architecture improvement advice from architecture evidence and source inspection. |
Use this skill to turn architecture evidence into an actionable improvement plan.
archi-evidence-map when selecting optional tools or when Architec is
unavailable.improve-codebase-architecture when advice should identify
deepening opportunities or compare interface shapes.receiving-code-review when advice is based on external
review feedback that needs verification before action.Current Position
- baseline score:
- current reading:
Immediate
- ...
Next
- ...
Later
- ...
Validation
- ...
Advice must be grounded in evidence. Do not produce a roadmap from diff context alone when the user is asking about long-term architecture. If no tool evidence exists, ground the roadmap in source inspection, module docs, tests, and explicit residual risk.