422 skills · sorted by relevance
Review code changes and pull requests for correctness, security, performance, and test quality. The skill helps prioritize issues, write specific and constructive feedback, and create shared review checklists and standards for a development team.
Review whether a proposal, specification, or design decision addresses the right problem and follows from its goals and constraints. Receive prioritized findings with supporting evidence, confidence, and concrete alternatives or questions that would resolve each concern.
Build, improve, or review SwiftUI interfaces using Liquid Glass on iOS 26 and later. It guides native glass effects, grouped elements, interactive controls, animated transitions, and fallback interfaces for earlier iOS versions.
Audit multilingual and regional websites for hreflang errors, the tags that identify language alternatives. Check reciprocal links, language codes, canonical URL conflicts, and targeting signals when search results show the wrong language or country version.
Add or update Pallas/Mosaic kernels, specialized computation routines for JAX. The skill covers reference implementations, output and gradient checks, public wrappers, fallback behavior, performance benchmarks, and hardware-specific tuning when requested.
Review a specified Marin pull request for newly introduced defects, repository instruction violations, and concrete maintenance problems. Receive findings backed by code evidence, with optional posting of review comments to GitHub.
Review PipesHub code changes for bugs, scaling risks, missing-value handling, reuse, design, and tests. Get specific findings tied to files and lines, with the most serious problems addressed first and a concise review verdict.
Review code or pull requests for likely bugs, readability, maintainability, and risks to existing behavior. Supporting scripts and reference checklists help analyze code quality, identify missing tests, and organize findings into a review report.
Study the mathematics behind computer science through a structured learning path and practice problems. Covers logic, proofs, sets, functions, counting, and number theory, connecting these foundations to algorithm correctness and computational thinking.
Test changed screens or explore an entire app in a real browser. Check interactions, accessibility, and mobile layouts, then document failures with screenshots, reproduction steps, expected results, and suggested fixes.
Diagnose NVSHMEM launch failures, crashes, hangs, and communication problems using exact commands and complete logs. Separates observations from likely causes, checks version-specific documentation, and prepares a Markdown bug report for the user to submit.
Diagnose GPU bugs in CUDA applications with NVIDIA Compute Sanitizer. Select the appropriate tool for memory access errors, shared-memory races, uninitialized reads, or synchronization faults, then build for source locations and interpret the diagnostic report.
Integrate PhysicsNeMo domain parallelism, splitting one input across GPUs, into training or inference scripts. Guides DDP or FSDP2 integration, adds support for new operations, and checks distributed outputs and gradients against single-GPU results.
Tune adaptive behavior in an instrumented NeMo Relay application using runtime data. Configure tool parallelism, prompt caching, and state storage, then compare changes against a baseline to check latency, correctness, and failure rates.
Audit openai-go during scheduled or repeated maintainer runs for correctness bugs, security weaknesses, performance problems, rough edges, non-idiomatic Go, test gaps, code organization, and architecture, then report one prioritized recommendation with evidence. Use for recurring proactive repository maintenance and rotating whole-codebase review; do not use for feature work, code changes, autonomous publishing, or pull-request stewardship.
The English summary is being prepared. Showing the original description.
Exhaustively review committed openai-go pull requests, branches, and commit ranges, or provide best-effort review of uncommitted local changes, for Go correctness, SDK compatibility, generated-code ownership, provider security, and repository-specific gotchas.
The English summary is being prepared. Showing the original description.
Comprehensive security and correctness audit of a branch's changes. Use for thermo nuclear, thermonuclear, or deep review requests, or branch/PR diff audits focused on bugs, breaking changes, security issues, devex regressions, and feature-gate leaks.
The English summary is being prepared. Showing the original description.
Manually review the implementation diff for the current Comet change. Report correctness, security, and edge-case issues without advancing the workflow.
The English summary is being prepared. Showing the original description.
Trigger a pre-merge release readiness review on a GitHub PR, GitLab MR, or local branch. Use when the user wants to analyze code changes for risk, correctness, and potential rollback issues before merging. Trigger words include release readiness, analyze PR, analyze MR, review PR, risk analysis, pre-merge, safe to ship, ready to merge, ready to commit, any risks, before merging, validate changes, release management.
The English summary is being prepared. Showing the original description.
Drive a change through a red-green-refactor loop - failing test first, minimal code to pass, then clean up. Use when implementing a feature or fixing a bug where correctness matters and a test can pin the behavior. Says "TDD", "test first", "red green refactor", "write the test first".
The English summary is being prepared. Showing the original description.
Audit a target's CORS posture — Access-Control-Allow-Origin handling, reflected-origin bypass, credentials+wildcard mismatch, preflight OPTIONS behavior, Vary header correctness. Use when: a third-party integration is failing CORS preflight and someone proposes "just set Allow-Origin to *" as the fix, OR your bug-bounty inbox has a credential-reuse exploit chain. Threshold: any reflection of arbitrary Origin into Allow-Origin, Allow-Credentials:true with wildcard origin (browser-rejected combo but server config wrong), missing Vary:Origin on per-origin responses, preflight cached over 86400s, OR Allow-Origin trust of attacker- controlled subdomain pattern. Trigger with: "audit cors", "check cors policy", "cors bypass", "preflight check".
The English summary is being prepared. Showing the original description.
Analyze and improve Attio integration latency and throughput from measured query shape, pagination, concurrency, retry, and cache evidence while preserving correctness. Use when Attio requests are slow or queues are backing up. Trigger with "Attio performance", "speed up Attio sync", or "Attio query tuning".
The English summary is being prepared. Showing the original description.
Derive a safe Adobe workload envelope from synthetic load, queue/backpressure behavior, current service constraints, spend, and output correctness. Use when the task requires adobe capacity and load envelope. Trigger with "load test Adobe", "scale Firefly jobs", or "Adobe capacity plan".
The English summary is being prepared. Showing the original description.
Improve Adobe integration latency and throughput from measurements while preserving correctness, policy, and spend boundaries. Use when the task requires adobe measured performance tuning. Trigger with "tune Adobe performance", "reduce Firefly latency", or "optimize PDF jobs".
The English summary is being prepared. Showing the original description.