メニュー
Use sem for semantic, entity-level code diffs, impact analysis, blame, entity listing, history logs, and compact AI context generation.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Do not use unless the user explicitly requests it. Dispatch each requested task to a new Codex session in a newly allocated dedicated worktree, then coordinate rebasing and fast-forward integration into local main without implementing, reviewing, or archiving the task in the coordinator session.
Use only when explicitly requested by the user or, during an explicit debugging session, after other relevant checks such as typecheck, lint, and tests have been exhausted.
Use only when the user explicitly requests this skill.
Use when building greenfield React SPA UI with Lisse (`@lisse/react` or `@lisse/core`) for Figma-style smooth/squircle corners, choosing `SmoothCorners` vs `useSmoothCorners`, configuring corner smoothing, borders, gradient borders, shadows, styling hooks, auto-effects, client-side path generation, performance, or limitations.
Use React Aria and React Stately hooks to build accessible custom React components, including choosing the right hook, wiring refs/state/props, preserving ARIA and keyboard behavior, excluding React Aria i18n and SSR utilities, and checking hook-specific guidance in bundled category docs.
Design, review, and optimize PostgreSQL and SQLite schemas, queries, migrations, transactions, indexes, and data-access code, especially when SQL should remain portable between both engines.
| name | sem |
| description | Use sem for semantic, entity-level code diffs, impact analysis, blame, entity listing, history logs, and compact AI context generation. |
sem reports changes, dependencies, affected tests, blame, history, and AI-ready context at semantic entity granularity.
sem diff reports additions, modifications, deletions, renames, and moves at the entity level, such as functions, classes, properties, config keys, Markdown sections, and data rows.
# Working tree changes.
sem diff
# Staged changes only.
sem diff --staged
# One commit.
sem diff --commit <sha>
# Commit range.
sem diff --from <ref> --to <ref>
# Restrict by extension.
sem diff --file-exts .ts .tsx
# Include inline before/after content when useful.
sem diff --staged --verbose
sem diff --stdin can analyze supplied file-change input without requiring a git repository.
Use impact analysis before changing or reviewing an entity to find directly related code.
sem impact <entity>
sem impact <entity> --file path/to/file.ts
sem impact <entity> --deps
sem impact <entity> --dependents
sem impact <entity> --tests
sem impact <entity> --file-exts .ts .tsx
Use --file when multiple entities share the same name.
Use blame for file-level authorship/change information, and log for entity history across recent commits.
sem blame path/to/file.ts
sem log <entity>
sem log <entity> --file path/to/file.ts --limit 100
sem log <entity> --file path/to/file.ts --verbose
Use sem entities to list entities under a file or directory path.
sem entities
sem entities path/to/file.ts
sem entities path/to/directory
Use context generation to gather a bounded, entity-centered context bundle before asking an AI agent to implement or review a change.
sem context <entity>
sem context <entity> --file path/to/file.ts --budget 12000
sem context <entity> --file-exts .ts .tsx
sem parses source code and structured files. Common supported families include TypeScript/JavaScript, Python, Go, Rust, Java, C/C++, C#, Ruby, PHP, Swift, Elixir, Bash, HCL/Terraform, Kotlin, Fortran, Vue, XML, ERB, Svelte, JSON, YAML, TOML, CSV/TSV, and Markdown.