메뉴
Writing and modifying scripts; read for any shell/bash/zx/node.js/ansible/Makefile-type tasks
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Dispatch a foreign (non-Anthropic) model as a subagent — OpenAI Codex/GPT-5.6-Sol, DeepSeek V4-Pro, or Google Antigravity — either as a write-authorized agentic worker in a worktree or a read-only reviewer. Codex and DeepSeek explore, edit when authorized, and self-report; Antigravity is a single-packet headless reviewer. Use when you (the conductor) want to offload agentic work to another harness, get a cross-lineage second opinion, or run a correlated-blind-spot check same-lineage Claude subagents can't give. This is the dispatch/wrapping layer — how to split work across foreign models of unequal intelligence, prompt each to its level, and wrap them safely to save tokens. Also where adversarial-crosscheck's foreign lane routes; not every dispatch is a crosscheck.
Take a prompt or task the user is about to give Claude — especially a judgment they're invested in ("is this plan sound?", "review my design", "should we adopt X?", "poke holes in this", "am I fooling myself here?") — and run it through two opposing rewrites in clean contexts (a neutralised pass and a disowned-and-inverted adversarial pass), then present both for the user to reconcile. Use this whenever the user wants to pressure-test their own thinking, worries they're being flattered or agreed-with, asks to "red-team", "cross-check", "steelman against", or "sanity-check" something, or hands over work they clearly want to succeed and asks for an honest assessment. It counters sycophancy by widening coverage — it does NOT produce a single "unbiased" or "debiased" answer, and it deliberately refuses tasks it can't honestly automate.
Deep, source-graded investigation for substantial questions — casts a wide net of primary sources, grades each for quality and relevance, and works from the graded base instead of guessing. A good default for most questions worth more than a snap answer: tool/library/architecture choices, approach tradeoffs, trustworthiness or maintenance judgments, root-causing unfamiliar behaviour, or any "which way and why" that rewards real evidence.
Reviews prompt-engineering artifacts (SKILL.md files, CLAUDE.md, AGENTS.md) against a built-in checklist of effectiveness criteria for steering Claude, and proposes only substantively-justified edits with a brief rationale per change. The criteria carry a "criteria-as-of" date; when stale (>180 days), the audit still runs against the current criteria but recommends the user trigger the (separate, heavyweight) refresh procedure in a fresh max-effort session — refresh is never run inline. Explicitly designed to be token-expensive and slow; compounding value because the audited artifacts are read by Claude across many future sessions. Read after writing or substantively editing any SKILL.md, CLAUDE.md, or AGENTS.md.
The user's idiosyncratic commit-message style — `(label1 label2) terse message` with the mandatory `AI` tag for AI-authored commits, using the `.gitlabels` convention. Two-mode operation — autonomous-commit on `ai/*` branches (or with a `.claude-commit` sentinel), message-only on others. Read whenever drafting a commit message, staging a commit, or finishing a chunk of work that will produce a commit.
End-of-work hygiene pass for AI-edited code, focused on stripping the overly-verbose code comments that AIs habitually generate. The user wants ~90% of AI-added comments deleted, the remaining ~10% rewritten for brutal brevity. Read this before declaring an autonomous task complete, before drafting a commit on substantive edits, or whenever the user asks for a "review pass", "cleanup", or "wrap-up".
| name | shell-scripting-and-automation |
| description | Writing and modifying scripts; read for any shell/bash/zx/node.js/ansible/Makefile-type tasks |
"Scripting" (single-file, task-focused automation; as opposed to multi-file software with architecture, coherent goals, and collaborators) is one of the few exceptions to my general programming priorities - in particular, my preference for 'simplicity' and readability. As much of my scripting is for my-eyes-only, or isn't meant to be modified/maintained over time by a team, I prefer terse shell-scripts that rely heavily on builtin shell-features and deep knowledge of shell behaviour, even if that makes them harder to read for a casual reader. If you don't understand something in a shell-script, please ask me about it; and feel free to generate 'clever' code (ensuring that you explain to me in detail what's going on in your changes if they're non-obvious, so I don't miss them; including word-splitting, parameter expansion, and the like.)
Recently, I've started to lean towards the zx Node.js-based scripting environment for autmation tasks in my own projects, over the traditional POSIX-sh or makefiles. Where present/available, write automation/scripts in .zx.mjs files instead of .sh files; but don't be afraid to fall back to POSIX-sh for portability or when clearly already the project-local preference.
For modifying (or where appropriate, generating) shell-script, see ./POSIX-SHELL.md. Else, refer to ./ZX-NODEJS.md for instructions.
