Loading...
Loading...
Found 10,840 Skills
Add visuals to edited voiceovers: Overlay HTML layers on screen recordings (key point circling / full-screen black animation / zoom-in), bind layers to subtitle screens, drive frame by frame via the player, and preview directly. Use this when users mention creating storyboards, adding visuals, animations, key point annotations, B-roll, or making storyboards. Do NOT use for word-cutting editing, subtitle creation, physical clipping, or final video rendering.
Make Sentry stack traces readable — upload source maps for JavaScript/TypeScript, or debug files for native and mobile (dSYM, ProGuard/R8, NDK symbols, Dart obfuscation maps, .NET PDBs). Use when frames in Sentry show minified names, bundled paths, hex addresses, "unknown", or method names with no file/line, instead of your original source.
GCC compiler skill for C/C++ projects. Use when selecting optimization levels, warning flags, debug builds, LTO, sanitizer instrumentation, or diagnosing compilation errors with GCC. Covers flag selection for debug vs release, ABI concerns, preprocessor macros, profile-guided optimization, and integration with build systems. Activates on queries about gcc flags, compilation errors, performance tuning, warning suppression, or cross-standard compilation.
Use this when you need to execute R4 (generate an interactive Demo project based on requirements/prototype.md) in the sdlc-dev product requirement Spec process, and need to avoid skipping spec-context, proceeding when prototype.md is missing or the runnable Demo project root directory is missing, or creating custom pages/directories that lead to untraceability and inability to close the loop.
Compress PNG and JPEG screenshots in place using pngquant and jpegoptim, keeping the original format for maximum compatibility.
When the user wants to create, optimize, or audit features page content. Also use when the user mentions "features page," "product features," "capabilities," "what it does," "feature list," "feature comparison," "product capabilities," or "features section."
Simulate a senior high school grade 3 science tutor in China, using progressive teaching methods to tutor math, physics, chemistry, biology and other science problems. Used when students ask science questions, request explanations, say "I don't understand" or "Teach me". Suitable for Gaokao preparation, problem-solving guidance, and concept understanding.
Create, review, and manage first-class goal artifacts that turn a broad ambition into an externally verifiable outcome. Goals are optional, long-lived workflow artifacts stored at goals/<slug>.md. They own intent, a validation contract, lifecycle, concise review evidence, and linked work. Use when the user wants to set a goal, review a goal, pause or reactivate a goal, achieve or abandon a goal, or change what a goal means. Not for specs, plans, memory, or checkpoints.
Rework a change as if the intended UX and architecture existed from day one, deleting compatibility cruft and accidental complexity.
General Chinese Creation and Revision Skill. Applicable to Zhihu answers, forum long posts, official account articles, blogs, comments, character stories, historical narratives, news and industry interpretations, popular science, tutorials, reviews, personal narratives, novels, stories, dialogues, oral broadcasts, and speeches. Defaults to writing in the voice of someone who has experienced things, checked materials, and is willing to explain the ins and outs clearly, focusing on retaining the authentic human touch and natural Chinese rhythm of long answers and posts on the Chinese internet, while avoiding empty institutional tones, slogan-style speech tones, marketing tones, and AI model tones. For non-fiction long articles, first check if the materials are sufficient; if not, conduct research, ask questions, or shorten the article, and never pad the word count with repetitive explanations. Verify facts, quotes, data, and user experiences for real-world content; for fictional content, characters, scenes, dialogues, psychology, and plots can be created. Colons, dashes, phrases like "not...but..." and similar counterargument structures are strictly prohibited in the final draft, and business jargon and AI model jargon should be removed. Do not create author profiles, personal rule libraries, or personal writing Skills.
Use when the user asks to "optimize entity presence", reconcile an entity identity, or update canonical Knowledge Graph facts; audits and maintains machine-facing identity, sameAs, schema, disambiguation, and AI-recognition evidence through the entities registry. Not for page-level AI-citation readiness - use geo-content-optimizer; not for human-facing brand canon - use narrative-registry. 实体注册/知识图谱
Bulk-regenerate broken test selectors after a UI refactor or redesign. Detects drift between old and new DOM with an aria-snapshot diff, maps old locators to new equivalents using role-first + region scoping, validates against the new build, and produces a single PR with grouped per-file selector updates and per-change evidence. Assumes Playwright >= 1.50 (trace viewer DOM-snapshot panel, getByRole filtering, ariaSnapshot). Use when: "UI refactor broke tests," "redesign broke tests," "bulk update selectors," "regenerate selectors after refactor," "selector drift," "fix N broken tests after redesign." Not for: healing one flaky test at runtime — use test-reliability. Not for: writing a new test suite from scratch — use playwright-automation. Not for: re-recording tests after a framework switch (Selenium to Playwright) — use test-migration. Related: test-reliability, playwright-automation, test-migration, ci-cd-integration, visual-testing.