メニュー
Communication style, audience awareness, and AI-authorship markers for human-facing prose — load when composing chat messages, review comments, merge request descriptions, emails, doc bodies, or ticket descriptions
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
OpenCode agent runtime — manage sessions, dispatch tasks, repair DB issues, and reset diffs
Look up people, projects, products, and decisions locally first: contact info (email, Slack ID, GitHub handle), titles and teams, project/product status, who works on what, and past decisions. Check before searching Slack, email, calendar, or GitHub — this is the first stop for any contact detail, project context, or decision-history question.
Load when reviewing a diff, naming a code smell or anti-pattern, deciding refactoring direction, or grading review-comment severity. Required reading when a named pattern is cited — load explicitly rather than paraphrasing from memory.
Load before creating, restacking, or landing a branch in a git-spice–managed stack — branch naming, stack navigation, and conflict/restack recovery. Use instead of raw git commands whenever the repo has a git-spice stack.
Load when investigating production errors, latency, or trace data that requires querying Elasticsearch/APM directly — index patterns, field names, auth setup, and time-range syntax. Use before hand-rolling a query DSL call or guessing field names.
Manage dotfiles via chezmoi — apply safely, destroy files, manage LaunchAgents and externals, config and template gotchas
| name | communication |
| description | Communication style, audience awareness, and AI-authorship markers for human-facing prose — load when composing chat messages, review comments, merge request descriptions, emails, doc bodies, or ticket descriptions |
| license | MIT |
Apply these rules to all human-facing prose: chat messages, review comments, merge request descriptions, emails, doc bodies, ticket descriptions.
When writing to a specific person, tailor to them — their role, communication style, technical depth, and your relationship. Some people prefer direct and brief; others need more context.
Before sending: would the recipient learn something? Is anything in here padding? Is anything stated where a question would do?
When posting composed prose through an integration on the user's behalf, append an italicized attribution line at the very end naming the model that composed it: *Co-authored with <model id>* (e.g. *Co-authored with anthropic/claude-sonnet-4-6*).
Omit when relaying the user's words verbatim. Skip on commit messages and merge request descriptions (Co-Authored-By trailer signals AI authorship) and on titles. Skip on Slack — its own send attribution already covers it.
