Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
Create and scaffold plugin directories for Codex with a required .codex-plugin/plugin.json, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries…
Verify your work by actually operating the app or website you changed, instead of assuming it works. Strongly recommended whenever you build, modify, or debug a web app, website, or desktop GUI app. Drive real browsers with the agent-browser CLI and native desktop apps with the cua-driver CLI. These are installed on…
Maintain or assess a large, mature repository when a proposed or existing change may cross modules, platforms, clients, installers, configuration, security boundaries, tests, or documentation. Use for incoming-change adoption decisions, consequential bug fixes, refactors, dependency upgrades, compatibility work…
Set up, verify, and troubleshoot spawning subagents on non-OpenAI models through codex-router. Use when the user wants Codex to delegate work to subagents, asks which models can act as subagents, says spawning a subagent fails or picks the wrong model, or wants to orchestrate parallel agents across routed providers.
Create, list, read, message, wait on, fork, rename, archive, and pin Codex threads (sidebar tasks), plus automations and app navigation, using the app-native codexapp tools. Use when the session uses a custom (non-OpenAI) model, for example deepseek-v4-flash or mimo-v2.5, and the user asks to create a thread or a new…
A writing guide for Bilibili, a Chinese video-sharing platform. It helps prepare video titles, descriptions, tags, category choices, cover concepts, and pinned comments.
A Chinese-English translation and localisation guide for technical text and product interfaces. Localisation means adapting wording and cultural references so they sound natural to users in the target language.
A guide for planning and designing PowerPoint presentations. It covers slide structure, layouts, visual choices, animation suggestions, and speaker notes.
Adversarial self-review of your own conclusion, fix, or root-cause verdict before handoff — alternative causes, neighboring cases, blast radius, environment gap, hypothesis lock, subtraction, and a scan for fake-competence patterns. Use as a compact author check before non-trivial handoff and as a structured attack at…
Decompose a hard or multi-part task into independently checkable pieces with explicit verification gates and risk-weighted ordering. Use when planning corridor-sized work, writing lane briefs for subagents or Codex, or whenever a task is too large to verify as a whole.
How to operate a pi-dispatch deployment through its tools, and how to use the operator-confirm gates on the write tools (changing limits, adding/editing/deleting triggers).
Call local Grok CLI, Kimi Code CLI, and Claude Code CLI with the strongest current default models and native tools. Use this qiaomu skill workflow when the user wants to run Grok 4.5 for X/web search, image/video generation, research, or multi-tool agent work; run Kimi K3 (1M) for frontend UI/CSS/React/Vue work; run…
Route implementation work-orders to Kimi k3 lanes via the Kimi Code CLI; Claude specs, orchestrates, reviews, verifies. Use when a task is a frozen-spec build, mechanical migration, test fill, bulk sweep, or CI fix — anything that reads as a work order rather than a design problem.
Use when module, package, or build dependencies may contain cycles, especially load-order failures, broad rebuilds, or a planned extraction: derive the real graph, compute strongly connected components, rank cycle clusters, choose the minimal feedback-edge cut, and add an acyclicity guard.
Use when an operator or stakeholder request is too vague or conflicting to convert directly into testable scope: ask a bounded question ladder, label assumptions DEFAULT or BLOCKING, turn adjectives into measurable outcomes, and confirm IN and OUT boundaries plus verification methods before decomposition.
Use when a rendered UI has been built or changed and is about to be accepted — at the S4 Verify gate of a web, game, or other visual capability, before any ship step. Drives the "seen, driven, and measured" acceptance pass; the pixel-diff half belongs to visual-regression-baseline.
Ask Kimi a read-only free-form question about the current repository. Use for prose explanations, flow tracing, module comparisons, or conceptual reasoning where Codex should delegate the answer to local kimi-code rather than perform implementation.
Run Kimi's autonomous goal mode for an explicitly requested hands-off multi-turn objective. This is write-capable and budget-bounded; use only when the user explicitly asks Kimi to pursue an objective autonomously.
Verify local Kimi companion readiness and manage the kimi-code PreToolUse hook plus optional review gate state. Use when explicitly requested to install, check, enable, disable, or uninstall the integration. Codex and Claude Code share one /.kimi-code/config.toml but each own a host-scoped block, so $kimi-setup here…
Generate and edit Word documents (.docx). Supports professional documents including covers, charts, track-changes editing, and more. Suitable for any .docx creation or modification task.