Loading...
Loading...
Found 2,163 Skills
Diagnose failed Crontap schedule runs from saved configuration and retained execution history, separating scheduler, network, timeout, and endpoint failures. Use when a scheduled HTTP job is late, failing, or unexpectedly unauthorized.
Breaks an animation or interaction into a state machine and a timeline of every property, on a page you can scrub and edit.
Fixes a bug by building a runnable reproduction and finding the root cause before any fix. Use for errors, crashes, failing tests or builds, flaky behavior, or repeated failed fixes.
Debug from an error message or bug report: reproduce it, find the cause, propose the smallest fix, and say how to prevent it happening again. Use when something crashes, fails, or behaves wrongly and the user wants the cause and the fix. Do NOT use to explain a codebase, review a change, or build a feature — use the matching narrow skill for those, and this skill only for the bug itself.
Write and edit styles in a project that uses Panda CSS. Use when creating, changing, or reviewing code that calls css(), cva(), sva(), patterns, recipes, tokens, conditions, or JSX style props, when a style renders a class name but no CSS, or when styles do not apply at all. Covers Panda v2 (2.x) and v1 (1.x). Do not use for designing the theme or deciding when something becomes a recipe or slot recipe (use panda-css-theming), or for upgrading v1 to v2 (use panda-css-migrate).
Use when Claude Code should do something by itself - at session start (`SessionStart`), on every prompt (`UserPromptSubmit`), or after each response (`Stop`) - or when that automation misbehaves. Symptoms: a hook script that runs but whose output never reaches the model, a session that keeps restarting its own turn with no user input, a hook that works locally but does nothing in a web session. Also for writing or reviewing a `hooks` entry in `.claude/settings.json` or a script under `.claude/hooks/`.
Create, update, review, or discuss an LLM prompt — a system prompt, a skill, or an agent. Use when writing or improving a prompt, discussing a skill or agent, diagnosing prompt failures, or when the user says a prompt needs work.
Configure and troubleshoot Proxyman HTTPS capture across desktop systems, Apple and Android devices or simulators, browsers, runtimes, containers, frameworks, and HTTP clients, including Atlantis instrumentation for controlled apps.
Diagnoses and fixes 3D PhysX collision, trigger, and raycast problems. Use when asked to fix OnCollisionEnter or OnTriggerEnter not firing, objects passing through each other, raycasts that miss, or a misbehaving MeshCollider.
Build a world the human drives until how a thing behaves is intuitive. Use when the user needs to hold how something behaves and reading has not made it intuitive.
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.