メニュー
Write, design, or review agent-friendly CLIs and agentic interfaces for humans, scripts, and coding agents, with progressive disclosure, structured output, actionable errors, stdout/stderr separation, and explicit non-interactive modes.
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。
Fork one isolated Codex worktree thread per Beads issue and start each with a dependency-aware completion contract. Use when the user asks to start, fork, split, parallelize, or create separate chats for beads, tickets, issues, or a backlog with the goal of fixing them all.
This skill should be used when the user asks to "bump a package", "update an upstream revision", "refresh a Nix source hash", "rebase local patches", "carry fork changes as patches", "hack on upstream software in this repo", or fix a package whose patches no longer apply.
Jujutsu version control through jut, a human and agentic framework around jj. Use for: check status, view changes, commit work, create branches, push, pull, create PRs, squash commits, reword messages, absorb changes, undo operations, view history. Complements jj — use jut for opinionated workflows, drop into raw jj for everything else.
Create, manage, and verify healthchecks.io monitors via the REST API. Use when adding monitoring to a new cron job or service, auditing existing checks, wiring ping URLs into configs, or verifying a check fired correctly.
Control live Herdr workspaces, tabs, panes, agents, worktrees, layouts, plugins, and waits. Use when running inside Herdr (`HERDR_ENV=1`) to inspect sibling agents, delegate work—including dedicated Pi workspaces—run services, debug agent detection, or coordinate terminal state.
Structural code search, refactoring, and repository lint-rule setup with ast-grep. Use when searching by syntax shape, writing or testing ast-grep rules, configuring sgconfig.yml, enforcing coding standards, selecting rule severity, or adding ast-grep to project checks and CI.
SOC 職業分類に基づく
| name | writing-agent-friendly-clis |
| description | Write, design, or review agent-friendly CLIs and agentic interfaces for humans, scripts, and coding agents, with progressive disclosure, structured output, actionable errors, stdout/stderr separation, and explicit non-interactive modes. |
Use this skill when building, reviewing, or redesigning a CLI or agentic interface meant to serve both humans and coding agents. Do not use it merely to decide whether to prefix an arbitrary command with environment variables.
Model the CLI after Notion's ntn: one tool that is pleasant for humans, scriptable for shells, and predictable for agents.
--json for structured output on list/get/status commands.--plain.tool workers list, tool pages get <id>.--help at every level.doctor for auth/config/network checks.--verbose for source chains and request/response metadata.--yes for destructive confirmations in non-interactive runs.--no-watch, --no-browser, --no-install, or equivalent escape hatches for commands that would otherwise block.--data or --file for scriptable payloads.api ls, --spec, --docs, --json.--json exists for agent parsing.