Loading...
Loading...
Found 1,762 Skills
This skill is used when users explicitly request "LaTeX template optimization", "style parameter alignment", "pixel-level comparison", "make-latex-model" or the old notation "make_latex_model", or when they want to turn a project in ChineseResearchLaTeX into a high-quality template. It supports four product lines: NSFC / paper / thesis / cv; first determine whether to modify the project layer or the public package based on the actual hierarchy of packages/ and projects/, then use the official build entry of each product line for acceptance. If modification to the public packages under packages/ is necessary, a regression plan for affected templates must be generated first and relevant regression completed; the NSFC special tool is only used on demand when it clearly falls into the NSFC parameter alignment scenario.
General performance optimization techniques for Motoko. Reducing allocations, efficient Text building, fixed-width arithmetic, block processing, async patterns, and more. Load when you need to improve hot paths or reduce overhead without changing behavior.
Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI/CD quality gates, observability, or cost optimization. Triggers on: "evaluate my agent", "add evaluator", "measure quality", "quality gate", "run evals", "agent too slow", "why is it slow", "reduce latency", "set up observability", "CloudWatch dashboard", "how much does my agent cost", "cost optimization", "logs not showing up", "logs missing", "spans not found", "eval failing", "eval error", "dev traces", "local traces", "agentcore dev traces", "traces to CloudWatch". Not for debugging errors or crashes — use agents-debug. Slow but correct routes here; broken routes to debug.
Inventory management for TikTok Shop — demand forecasting, viral stock planning, FBT optimization
Vite build tool patterns including config, plugins, HMR, env variables, proxy setup, SSR, library mode, dependency pre-bundling, and build optimization. Activate when working with vite.config.ts, Vite plugins, or Vite-based projects.
Professional workflow for creating bespoke vector and complex raster icons. Professional icon design workflow including Design (visual), Path (vector), Desire (conceptual), and 3D chroma-key modes. Features AI prompt engineering, automated binarization, alpha cleanup, and SVG optimization.
Systematic GitHub Actions workflow authoring skill for AI coding agents. Analyzes repositories to determine project type, language ecosystem, and deployment targets, then generates production-grade CI/CD workflows with proper security hardening, caching, and optimization. Handles greenfield projects (no workflows exist), brownfield updates (modify, optimize, secure existing workflows), and workflow audits with workflow-specific guidance for each. Use when the user requests GitHub Actions workflows: CI pipelines, CD deployments, release automation, scheduled jobs, or any .github/workflows YAML authoring. Also use when existing workflows need auditing, optimizing, securing, or restructuring. Triggers on phrases like "set up CI", "add CI/CD", "GitHub Actions workflow", "release automation", "deploy on tag", "publish to npm/PyPI", "schedule a job", "cron workflow", "matrix build", "workflow.yml", "actions/checkout", "permissions", "harden this pipeline", "pin actions to SHA", "OIDC", "least privilege", "supply-chain", "audit my workflows", "speed up CI", or "cache dependencies". Triggers when creating or editing files under `.github/workflows/`, `action.yml`/`action.yaml` (composite or Docker actions), or `.github/dependabot.yml`. Triggers when the user mentions migrating from GitLab CI, CircleCI, Travis, Jenkins, Drone, or Buildkite to GitHub Actions. Do NOT use for non-GitHub CI systems (GitLab CI, CircleCI, Jenkins) unless the user is migrating TO GitHub Actions. Do NOT use for general bash scripting, Makefiles, or local-only build configuration.
Analyze a software codebase for algorithmic complexity and performance hotspots, then propose or implement safe optimizations without breaking behavior. Use when Codex is asked to scan many files, find inefficient loops, nested iteration, repeated scans, costly rendering/recomputation, N+1 queries, avoidable O(n^2) or O(n) operations, or reduce complexity such as O(n^2) to O(n log n) / O(n), while preserving tests, APIs, outputs, and maintainability.
Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper. Covers the Three Walls framework, parallel folding, recompute strategy, dispatcher choice, and CUDA-graph bring-up.
Code instrumentation for timing workloads. Two scenarios: (1) Training loop — inject manual timing to report per-iteration latency, throughput (samples/sec), and data load time. (2) Standalone kernel/op — write CUDA event timing code with warmup, per-iteration statistics, and anti-pattern avoidance. Also covers NVTX annotation for labeling profiler timelines. NOT for: running or analyzing profiler tools (nsys, ncu, Nsight Systems, Nsight Compute), writing kernels (Triton, CuTe, CUDA), applying optimizations (CUDA Graphs, gradient checkpointing, fusion), or interpreting roofline/SOL% metrics. Triggers: "measure throughput", "benchmark this function", "time my training loop", "samples per second", "NVTX annotate", "instrument my dataloader", "data load time", "kernel timing", "how do I time".
Compare and optimize shipping rates across carriers and fulfillment methods. UPS, FedEx, USPS, DHL rate comparison, zone optimization, and shipping strategy to maximize margins.
Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python tools.