Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Benchmark PocketJS demos on PSP or PPSSPP, including per-frame timing, renderer phase costs, bundle and pak sizes, arena high-water memory, and minimum passing arena scans. Use when asked to profile PSP performance, compare demo frame budgets, measure memory headroom, find the minimum safe heap for demos, or preserve benchmark evidence in dist/bench.
Enable an existing or newly-added markuplint rule on the nu-validator bench by editing tests/external/bench/config.ts. Covers the flat-rule case (rules: { '<name>': true }) and the severity override case (rules: { '<name>': { severity: 'error' } }) that bench-virtual-rule does not. Use when a rule exists in the registry but the relevant nu fixtures stay nu-only because the rule is not enabled in the bench config, or when a rule's default severity is warning but the spec text it mirrors is a MUST / MUST NOT. Trigger keywords: enable bench rule, bench config flat rule, severity override bench, rule not flagging on bench, warning vs error in bench, escalate severity bench, wai-aria-implicit-props bench, bench coverage missing rule.
Mirror a preset virtual rule (selectors under `nodeRules` in preset.html-standard.jsonc and similar) into bench/config.ts so the benchmark exercises it. Use when a new disallowed-element / similar selector lands in a preset and the matching nu fixtures remain stuck at nu-only despite the new rule existing in markuplint. Trigger keywords: virtual rule, nodeRules, disallowed-element, preset html-standard, bench config mirror, rule does not fire on bench, preset rule not exercised.
Reference knowledge for Markuplint HTML linter. Covers violation interpretation, CLI usage, config patterns, and documentation URLs. Auto-loaded when working with HTML linting.
Capture and visually inspect Qt GUI widgets using screenshots. Use when asked to verify GUI rendering, test widget appearance, check layouts, or visually inspect any PySide6/Qt component. Enables Claude to "see" Qt interfaces by capturing offscreen screenshots and analyzing them with vision.
Investigate native React Native crashes (Fabric/Hermes/iOS) in ledger-live-mobile when JS error logs are missing or unhelpful. Use when the app dies silently, throws an NSException on iOS, or shows only a native stack trace.
Add E2E tests for new coins or update existing Playwright tests for ledger-live-desktop. Use when the user wants to add send/receive e2e tests for a new cryptocurrency, update test configurations, or work with Speculos device simulator.
Interactive setup wizard for running desktop E2E (Playwright + Speculos) tests locally
Check, update, and RUN Earn E2E tests for Ledger Wallet Desktop (Playwright) and Mobile (Detox). Covers the Earn v2 dashboard, the native + redirect staking flows, and the delegate specs (owned by the Earn team). Use to run earn.v2 / delegate locally, adapt earn page objects/flows, and triage failures.