generation-quality-checklists
Use when reviewing generated images, videos, or audio before shipping — run the quality checklists before asking for approval.
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-04 00:13
13,114 results
Use when reviewing generated images, videos, or audio before shipping — run the quality checklists before asking for approval.
Read the review comments left by the known agent reviewers on the current PR, resolve and reply. Use when asked to deal with PR comments, review feedback, or…
Branch-local durable PR state -- issue brief, decisions log, and session handoffs. Read the brief, decisions, and latest handoff at session start; append…
Verify forward and backward numerical correctness of a handwritten low-precision GPU kernel against a high-precision oracle and an eager same-dtype baseline.…
Capture and compare per-op activations between two TorchTitan runs to spot numerics divergence (eager vs aot_fx_trace, FSDP vs no-FSDP, before vs after a…
QJudge quality-gate full responsibility skill. Use when the task involves naming lint, architecture lint, style prohibitions (.cds/.bx/!important), and CI gate configuration.
Use when a project needs containerized test environments, mock servers, custom mock binaries, or real service testing infrastructure
Interact with Qt/PySide apps via AT-SPI accessibility. Use when asked to "test the UI", "click a button", "inspect widgets", "take a screenshot", "read widget…
Interact with system tray icons, desktop notifications, and audio in Qt/PySide apps. Use when asked to "check the system tray", "click tray icon", "read tray…
ALWAYS LOAD THIS SKILL WHEN TESTING QT/PYSIDE UI, CLICKING BUTTONS, INSPECTING WIDGETS, OR TAKING SCREENSHOTS. Do not interact with Qt widgets directly — use…
ALWAYS LOAD THIS SKILL WHEN INTERACTING WITH SYSTEM TRAY, DESKTOP NOTIFICATIONS, OR AUDIO IN RUNNING QT/PYSIDE APPS. Do not interact with OS-level desktop…
ALWAYS LOAD THIS SKILL WHEN FILLING FORMS, HANDLING FILE DIALOGS, OR USING THE CLIPBOARD IN RUNNING QT/PYSIDE APPS. Do not automate multi-field input or file…
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
Develop business continuity plans and impact analysis. Implement BCP testing and communication procedures. Use when building organizational resilience.
Build reliable, fast, and maintainable end-to-end test suites that provide confidence to ship code quickly and catch regressions before users do.
Use the Obsidian CLI to read, create, search, and manage vault content, or to develop and debug Obsidian plugins and themes from the command line.
Provide a comprehensive command reference for penetration testing tools including network scanning, exploitation, password cracking, and web application…
Use when debugging any bug. Enforces a 5-phase protocol where code edits are blocked until root cause is confirmed. Prevents premature fix attempts.
Code review requires technical evaluation, not emotional performance.
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Test-Driven Development workflow principles. RED-GREEN-REFACTOR cycle.
Can you check out branch "{{ BRANCH_NAME }}", and run {{ TEST_COMMAND_TO_RUN }}.
Use when a bug, regression, or misbehavior has an unknown cause and the user wants iterative hypothesis-driven investigation — invoked by name ("prediction…