القائمة
Perform code reviews following best engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use when reviewing a Supaterm branch for product-requirement alignment before PR submission. Checks user-facing app, CLI, website, docs, release, and integration-skill surfaces for drift without editing them.
Comprehensive correctness and security audit of a branch's changes. Use for thermo nuclear correctness review, thermonuclear review, deep correctness review, or branch/PR diff audits focused on bugs, breaking changes, security issues, devex regressions, and feature-gate leaks.
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear maintainability review, thermonuclear review, deep maintainability audit, or especially harsh maintainability review.
Prepare and ship Supaterm CalVer stable releases. Use when the user asks to bump a Supaterm version, cut a stable release, write or publish release notes, update announcement cards, update the `supaterm.com` changelog, or run `make bump-and-release`. Always draft the changelog and confirm the announcement-card decision before editing `apps/supaterm.com`, creating GitHub release notes, or running the release command.
Native macOS/iOS app performance profiling via xctrace/Time Profiler and CLI-only analysis of Instruments traces. Use when asked to profile, attach, record, or analyze Instruments .trace files, find hotspots, or optimize native app performance without opening Instruments UI.
Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, macOS-specific APIs, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.
| name | review |
| description | Perform code reviews following best engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality. |
Run the three review passes as parallel subagents, then synthesize their results.
Use the host agent's subagent mechanism. Prefer exact keys where the host defines them:
spawn_agent once per reviewer with agent_type: "thermo-nuclear-correctness-review-subagent", agent_type: "thermo-nuclear-maintainability-review-subagent", and agent_type: "product-requirement-alignment-review-subagent". The spawned agents run in the background; wait for all three agent ids before synthesis. Codex custom agent files use name, description, and developer_instructions.name values are thermo-nuclear-correctness-review-subagent, thermo-nuclear-maintainability-review-subagent, and product-requirement-alignment-review-subagent. Use background: true when that frontmatter field is supported.subagent_type: "thermo-nuclear-correctness-review-subagent", subagent_type: "thermo-nuclear-maintainability-review-subagent", and subagent_type: "product-requirement-alignment-review-subagent". Use run_in_background: true only when that host exposes the field.thermo-nuclear-correctness-review-subagent for bugs, breakages, security, devex regressions, feature-flag leaks, and other branch-audit risks.thermo-nuclear-maintainability-review-subagent for maintainability, structure, file-size growth, spaghetti, abstractions, and codebase-health risks.product-requirement-alignment-review-subagent for PRD alignment, requirement/evaluation drift, missing product-doc updates, and untracked scope changes before PR submission.If individual background summaries are already visible to the user, do not restate them wholesale. Surface the unified verdict, the highest-signal findings, and any remaining uncertainty.