Skill reviews

Re-review a GitLab merge request after new commits and reconcile the previous review

• References files that are not bundled: references/categories/README.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval

Convert existing docs diagram images to Mermaid, and author new Mermaid diagrams for Mastra docs. Use when replacing an Excalidraw or PNG/JPG/SVG diagram with Mermaid, when a docs

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop clie

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• 10 mutating operations with no state check

Coordinate a small team of Qwen Code teammates with enforced read-only workers, an optional worktree-pinned writer, shared tasks, peer messages, and existing Agent View tabs. Invok

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Stabilize a flaky test with a minimal, assertion-preserving fix — never by weakening or deleting the check.

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (4 tags): a typed call is more reliable
• Does not say what the result is

Create, use and clean up cua sandboxes (disposable Linux or macOS computers) on this computer with the `cua` CLI or the cua SDK, and browse the web inside one. Use when a task need

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Work inside cua Spaces through the cua MCP server. A Space is a remote or local computer the user can watch; you can run commands in it, move files in and out, show its desktop or

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (5 tags): a typed call is more reliable
• Does not say what the result is

Find when and why tests broke on main: bisect a Swift package suite on CI across old commits, read the failure matrix, and decide per test whether the test went stale or the code r

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (17 tags): a typed call is more reliable
• Does not say what the result is

Stripe checkout, pricing, subscription, Pro plan, webhook, and entitlement runbook for cmux billing work. Use when editing or debugging billing, pricing, Stripe Checkout, subscript

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Land a PR by monitoring conflicts, resolving them, waiting for checks, and squash-merging when green; use when asked to land, merge, or shepherd a PR to completion.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Generate engine-specific test helper libraries — assertion utilities, factory functions, mocks in the engine's test folder. Reduces boilerplate.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (3 tags): a typed call is more reliable

Develop and test Screenpipe Windows-native changes on a disposable Azure VM created from the prepared Screenpipe Windows dev image. Use for Windows compiler, process, service, loca

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start
• 7 mutating operations with no state check

Watch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or local WhisperX / cloud Whisper fallback),

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Autonomously improve a generated paper via Gemini review through gemini-review MCP → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环",

• References files that are not bundled: ../../shared-references/output-versioning.md, ../../shared-references/output-manifest.md, ../../shared-references/output-language.md
• The skill tells the model to perform an irreversible action with no human approval
• 3 referenced file(s) missing: ../../shared-references/output-versioning.md, ../../shared-references/output-manifest.md, ../../shared-references/output-language.md

Autonomous multi-round research review loop. Repeatedly reviews using Gemini via gemini-review MCP, implements fixes, and re-reviews until positive assessment or max rounds reached

• References files that are not bundled: ../../shared-references/output-versioning.md, ../../shared-references/output-manifest.md, ../../shared-references/output-language.md
• The skill tells the model to perform an irreversible action with no human approval
• 3 referenced file(s) missing: ../../shared-references/output-versioning.md, ../../shared-references/output-manifest.md, ../../shared-references/output-language.md

Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or

• References files that are not bundled: ../../shared-references/output-versioning.md, ../../shared-references/output-manifest.md, ../../shared-references/output-language.md
• The skill tells the model to perform an irreversible action with no human approval
• 3 referenced file(s) missing: ../../shared-references/output-versioning.md, ../../shared-references/output-manifest.md, ../../shared-references/output-language.md

Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says \"编译论文\", \"compile paper\", \"build PDF\", \"生成PDF\", or wants to compile LaTeX into a submission-rea

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Autonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhere it uses Codex, wh

• References files that are not bundled: ../shared-references/external-cadence.md, ../shared-references/reviewer-backends.md, ../shared-references/output-versioning.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill

Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running an

• References files that are not bundled: ../shared-references/reviewer-backends.md, ../shared-references/external-cadence.md, ../../tools/watchdog.py
• The skill tells the model to perform an irreversible action with no human approval
• 3 referenced file(s) missing: ../shared-references/reviewer-backends.md, ../shared-references/external-cadence.md, ../../tools/watchdog.py

Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says "编译论文", "compile paper", "build PDF", "生成PDF", or wants to compile LaTeX into a submission-ready PDF.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Embed Mermaid diagrams in generated wiki pages. Use whenever documenting a runtime or request flow, a call sequence, a state machine or lifecycle, a data model or entity relationsh

• The skill tells the model to perform an irreversible action with no human approval
• Prose only: no discrete steps
• Does not say what the result is

Update a QM source fork by merging upstream, or upgrade a package deployment dependency, and open a PR. Use when asked to "update qm", "sync from upstream", "pull in the latest qm"

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Drive a real stealth browser from your shell — act on websites (order food, file an expense, pull data behind a login), with per-person persistent sign-ins kept in the person's bro

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Simplify and refine recently modified code while preserving functionality. Use when asked to "deslop", "clean up code", "simplify code", or after making changes that could benefit

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when the user wants to m

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start