Loading...
Loading...
Found 1,032 Skills
Systematic debugging methodology — binary search isolation, hypothesis-driven debugging, reproducing issues, and root cause analysis. Use when debugging errors, unexpected behavior, or test failures.
Use when managing perf baselines, consolidating results, or comparing versions. Ensures one baseline JSON per version.
Database migration best practices — schema changes, zero-downtime migrations, rollback strategies, and data migration patterns. Reference when modifying database schemas.
Save a concise handoff summary only when the user explicitly requests it. Use this for resumable progress notes in generic agent environments where a real session importer is not guaranteed.
Train custom AI models (LoRA) on fal.ai — personalize image generation for specific people, styles, objects, or video generation. Use when the user requests "Train model", "Train LoRA", "Fine-tune", "Custom model", "Train on my images", "Portrait training".
Restore and fix image quality — deblur, denoise, dehaze, fix faces, restore documents. Use when the user requests "Fix blurry image", "Remove noise", "Fix face", "Restore photo", "Enhance document", "Deblur", "Denoise".
OSINT-based technology stack identification. Discovers company tech stacks using passive reconnaissance across 17 intelligence domains. Given a company name (and optional domain hint), infers frontend, backend, infrastructure, and security technologies using publicly available signals.
Build consistent character designs and character media with genmedia. Use this for original characters, reference sheets, expression sheets, outfit variations, identity-preserving edits, and character-to-video workflows.
FastAPI best practices, async patterns, and Pydantic validation
Build professional CLI tools with Node.js, commander, and Ink
Domain reconnaissance coordinator that orchestrates subdomain discovery and port scanning to build comprehensive domain attack surface inventory
Analyze and reduce the bundle size of rspeedy/Lynx (ReactLynx) apps — the size / `.lynx.bundle` lever (not runtime perf, types, or CI). Use when the user wants to optimize 包体积 / bundle size, find what is making a rspeedy bundle large, decide which size lever to pull, or shrink `main-thread.js` by stripping background-only code (jsb / telemetry / request / monitor SDKs) out of the render path via `__BACKGROUND__` / `'background only'` gating. Covers media, JS-background, and main-thread layers, plus mangle/eval-poisoning bloat, i18n-locale duplication, duplicate-package dedup, extractStr/compile knobs, and lazy/dynamic-component splitting (first-screen vs total size). Measure-first and evidence-based — produces a prioritized report; changes code only when asked.