Operate persistent quintet worker teams — spawn coding-agent CLIs (claude/codex/agy/copilot/qwen/opencode) as long-lived tmux workers, distribute scoped subtasks, monitor, and shut down. Use proactively when running a multi-agent CLI team in tmux, when distributing work across AI workers, for building or refactoring in parallel, or when recovering a stuck or orphaned quintet team. Trigger on "quintet team", "tmux worker team", "parallel AI workers", "spawn agent workers", "run codex and agy in parallel to build", "distribute subtasks across models". Not for one-shot multi-model questions — use quintet-fleet-dispatch.

Revalidate persistent agent knowledge by classifying why it can become stale and how quickly it changes, then retain, revise, externalize, or retire it. Use when reviewing skills, stored instructions, facts, preferences, assumptions, or workflows; when an owner, decision, or dependency changes; or when self-improvement captures, reviews, or promotes a learning. Works independently of self-improvement. Not for runtime context-window degradation, unsaved task observations, or age-based deletion.

Revalidate persistent agent knowledge by classifying why it can become stale and how quickly it changes, then retain, revise, externalize, or retire it. Use when reviewing skills, stored instructions, facts, preferences, assumptions, or workflows; when an owner, decision, or dependency changes; or when self-improvement captures, reviews, or promotes a learning. Works independently of self-improvement. Not for runtime context-window degradation, unsaved task observations, or age-based deletion.

Meta-skill para criar, editar, avaliar e otimizar skills do kit. Use quando adicionar nova skill, refatorar skill existente, ou medir qualidade de descoberta de skill (description triggering). Trigger em: "criar nova skill", "nova capacidade", "skill author", "skill creator", "editar skill", "avaliar skill", "skill eval", "otimizar description", "meta-skill", "kit governance".

Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to bridge their ARIS paper directory with an Overleaf project.

Audit Claude Code and Codex hooks for validity, safety, and correctness across settings.json, hooks.json, config.toml, plugin, and skill or agent frontmatter hooks. Resolves each command, checks event names, handler types, matchers, exit-code and JSON decision strategy, and timeouts against each host's documented rules, then reviews hooks one by one. Use when setting up hooks, debugging a hook that never fires, never blocks, or hangs the agent, or doing a periodic hooks hygiene pass. Not for writing a new hook from scratch.

Generate a single photoreal or designed image with OpenAI gpt-image via fal.ai. Supports gpt-image-1 (default, fixed sizes — the FAL fallback for Higgsfield's `gpt_image_2`) and gpt-image-2 (`openai/gpt-image-2`, custom output sizes up to 3840px). Routes to text-to-image or the edit variant depending on whether a reference image is provided. Use for photoreal character anchors, scene keyframes, and designed sheets (e.g. storyboards) where precise layout and legible text matter.

Use this skill to triage an incoming issue on the EF Core repo (bug report or feature request). Sets the issue type (bug/feature), assigns EF area labels, attempts to arrive at a minimal repro reproducing the bug, checks whether it represents a regression, finds possible duplicates, etc.

Adds a new LLM provider implementing LLMProvider interface with call() and stream() methods. Integrates with provider factory in src/llm/index.ts, config detection in src/llm/config.ts, and error handling via tracking and recovery. Use when adding a new model backend, integrating a third-party LLM API, or extending LLM platform support. Do NOT use for fixing bugs in existing providers, modifying existing provider behavior, or changing the LLMProvider interface.

Analyze the current branch's diff against main and determine which changes are testable via CLI-based end-to-end tests. Outputs a concrete test plan with runnable test case sketches using the uc-e2e-tests harness. Use when the user wants to think about, plan, or evaluate e2e test coverage for their current work.

Inspect uniclipboard logs from BOTH the macOS host and the mounted Windows peer when debugging cross-platform sync, pairing, transfer, or daemon issues. Use whenever the user asks to "check logs", "see what's happening on both sides", or describes a symptom that involves the Windows peer (e.g. "Windows didn't receive...", "Mac sent but...", pairing/transfer/sync failures during dual-side dev).

Lightweight outcome tagging for meetings — won, lost, stalled, great, or noise. Use whenever the user says "tag this meeting", "mark that as a win", "that one was a loss", "tag yesterday's call as stalled", "mark this great", "that meeting was noise", "label that meeting", or any time they describe a meeting outcome in passing. Tagging takes 5 seconds and unlocks /minutes-mirror correlation analysis — the more meetings get tagged, the smarter mirror gets at telling the user what behavior patterns lead to wins. Surface this skill any time the user mentions a meeting result, win, loss, or wasted time.

Implements a feature or bug fix test-first: write one failing test, run it and watch it fail, write the minimal code to pass, then refactor with the tests green. Use when a change alters code behavior: a new feature, a bug fix, or a behavior change, whether the request comes alone or through delivery-flow.

Implements a feature or bug fix test-first: write one failing test, run it and watch it fail, write the minimal code to pass, then refactor with the tests green. Use when a change alters code behavior: a new feature, a bug fix, or a behavior change, whether the request comes alone or through delivery-flow.

Implements a feature or bug fix test-first: write one failing test, run it and watch it fail, write the minimal code to pass, then refactor with the tests green. Use when a change alters code behavior: a new feature, a bug fix, or a behavior change, whether the request comes alone or through delivery-flow.

Implements a feature or bug fix test-first: write one failing test, run it and watch it fail, write the minimal code to pass, then refactor with the tests green. Use when a change alters code behavior: a new feature, a bug fix, or a behavior change, whether the request comes alone or through delivery-flow.

Implements a feature or bug fix test-first: write one failing test, run it and watch it fail, write the minimal code to pass, then refactor with the tests green. Use when a change alters code behavior: a new feature, a bug fix, or a behavior change, whether the request comes alone or through delivery-flow.

Implements a feature or bug fix test-first: write one failing test, run it and watch it fail, write the minimal code to pass, then refactor with the tests green. Use when a change alters code behavior: a new feature, a bug fix, or a behavior change, whether the request comes alone or through delivery-flow.

Ship user-facing PocketHost features with a blog post instead of semver release notes. Use when landing feat/enh work, finishing a customer-visible change, or when the user asks to announce a feature. Pair with blog-voice for writing style.

Register an existing GitHub issue so the current Codex or Claude Code session is woken when its first future comment arrives. Use when work is genuinely blocked on a GitHub reply and the session must resume asynchronously.