Skill Claude CodeCodex
Use whenever a repo-local skill is being added, installed, or created for future Claude Code and Codex sessions, whether the user asked or you decided to write one; writing-skills covers authoring, not this repo's install contract.
Skill Claude CodeCodex
Use only when the user explicitly invokes $advocate to challenge a change just made before it lands. Do not trigger from natural-language requests.
Skill Claude CodeCodex
Spawn N parallel candidate attempts at one task, pick the strongest as base, graft the losers' best parts in. Use when the user says $arena, "arena this", or when one attempt at a non-trivial artifact would lock in the wrong shape.
Skill Claude CodeCodex
Use for "automate me", "$automate-me", or "turn my preferences / working style into a skill". Mines the current project's transcripts plus direct questions, then drafts a personal -mode skill.
Skill Claude CodeCodex
Watch a PR's checks and iterate on failures until green. Use for $babysit-ci, "watch CI", "fix CI", "get the checks green", or when a PR is waiting on failing or pending checks.
Skill Claude CodeCodex
Use when brainstorming or designing a product, interface, workflow, architecture, or behavior change with unresolved goals or material tradeoffs; not for routine or fully specified work.
Skill Claude CodeCodex
Restate the assistant's last message in plain human language, no jargon. Use when the user says $bro, "in plain english", "dumb it down", or "what does that actually mean".
Skill Claude CodeCodex
Ultra-compressed communication mode. Cuts token usage 75% by speaking like caveman while keeping full technical accuracy.
Skill Claude CodeCodex
Cross-vendor second-opinion review. Drives OpenAI Codex CLI (codex exec review, gpt-5.6-sol, high reasoning) over a PR, branch, commit, or uncommitted diff, then verifies each finding. Trigger: $codex-review, "have Codex/Sol review this".
Skill Claude CodeCodex
Use when the user asks to rewrite a rough request into a polished, copy/paste-ready prompt for another agent or a fresh session.
Skill Claude CodeCodex
Use proactively for hard layered work with dependent steps, load-bearing unknowns, repeated failures, or verification-sensitive handoff; also when the user asks for Fable mode.
Skill Claude CodeCodex
Use when the user wants a repository-specific UI or design skill synthesized from current agent skills; not for ordinary UI implementation or backend-only work.
Skill Claude CodeCodex
Use when the user asks for a self-contained audit prompt to paste into a separate fresh session for independent verification.
Skill Claude CodeCodex
Use when the user asks to humanize, de-AI, de-slop, voice-match, or review prose for AI tells before publishing.
Skill Claude CodeCodex
Use when the user asks to review, audit, or stress-test recent code changes with fresh independent agents; requires exposed multi-agent tools or an authenticated Codex CLI.
Skill Claude CodeCodex
Use once in a spawned starter repo when the user asks to initialize or configure it, or when FILL IN markers remain; never auto-run in a claude-starter template checkout.
Skill Claude CodeCodex
Use when the user explicitly asks to lab or prototype a visual, UI, motion, or game-feel element with live tuning before production implementation.
Skill Claude CodeCodex
Use for work too big for one context window: long multi-step tasks, progress lost to compaction or failed retries, work spanning hours or sessions, or when the user says $long-horizon or asks to run a task in verified rounds.
Skill Claude CodeCodex
Use only when the user explicitly asks to enable session-wide automatic commit, push, PR, and merge; not for one-shot shipping requests.
Skill Claude CodeCodex
Use when the user asks to reduce per-turn context or token load, trim kernels, skills, or connectors, or propagate a generic context optimization to the starter.
Skill Claude CodeCodex
Use when drafting or revising prose for a reader: application answers, emails, essays, bios, cover letters, proposals, memos, reports, product copy, speeches, or when a draft reads as machine-made or must match a writer's own voice.
Skill Claude CodeCodex
Use before unfamiliar project-area edits, when the user asks what the project knows or its pitfalls, or when saving durable project-specific learning.
Skill Claude CodeCodex
Use when a session or task is wrapping up ("wrap up", "that's everything", "done for today"), when the user invokes $refine, or after any task with friction: calls wasted rediscovering a fact, a skill that misfired, a user correction.
Skill Claude CodeCodex
Use when the user asks to pull template improvements into a spawned repo, compare starter drift, or push a generic improvement back to the starter.