メニュー
Create and maintain end-user or public-facing documentation. Use for user guides, product docs, API consumer docs, onboarding docs, tutorials, release notes for users, and documentation meant to be read outside the engineering team.
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
| name | docs |
| description | Create and maintain end-user or public-facing documentation. Use for user guides, product docs, API consumer docs, onboarding docs, tutorials, release notes for users, and documentation meant to be read outside the engineering team. |
Use this skill for user-facing documentation.
Do not use this skill for internal technical memory, architecture notes, contracts, runbooks, or agent-facing project context. Use the wiki skill for those.
wiki instead.Use docs/ unless the project already has a public documentation convention.
README.md is the project entrypoint. Keep installation, quick start, and navigation there. Move deeper or audience-specific material into docs/.
Common pages:
docs/index.md: entrypoint and reading order.docs/getting-started.md: first successful user path.docs/configuration.md: public configuration and environment options.docs/api.md: public API, CLI, or integration contract.docs/concepts/: concepts users need before operating the product.docs/how-to/: task-oriented workflows.docs/reference/: API, CLI, file format, or integration reference.docs/tutorials/: task-oriented guides.docs/troubleshooting.md: known user-facing failures and fixes.docs/release-notes.md: user-visible changes.Build and maintain an internal technical LLM wiki when the user requests wiki work or a verified major or architectural change qualifies for automatic wiki review. Use for project memory, architecture notes, contracts, runbooks, decisions, glossary, incremental ingest, delta status, and wiki health. Do not use merely because a routine task or plan completed.
Explore ambiguous ideas and solution directions before evidence-backed research or implementation planning. Use for ideation, framing, assumption checks, option generation, product or architecture trade-offs, and deciding whether research or a plan is needed.
Research technical options with source-backed recommendations. Use for technology evaluation, architecture trade-offs, library/framework choices, best practices, scalability, security, maintainability, or when current external facts matter.
Create implementation plans, architecture decisions, and phased roadmaps. Use for Standard or Complex changes, new pipelines, schema changes, migrations, multi-file features, technology choices, or when acceptance criteria and verification strategy are unclear.
Review code and data pipeline changes for correctness, security, performance, maintainability, contract breaks, and missing verification. Use before merge, after implementation, for PRs, commits, pending diffs, or codebase risk scans.
Design data ingestion into landing/bronze layers. Use for source onboarding, transfer pattern selection, full/incremental/CDC scope, change detection, landing zones, schema drift, idempotent file or batch processing, and ingestion quality gates.