Results for “demixing”

Systematically tear down and remove a service, package, or infrastructure component

当需要基于外部信息源创作具有个人特色的原创内容时

Validates that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after deploying a disagg or multi-node recipe to confirm KV transport is correct, or use troubleshoot for already-failed pods.

Diagnose failed or unhealthy Dynamo deployments by collecting a read-only debug bundle, classifying failures, and providing step-by-step remediation guidance.

Record, search, and analyze music and audio sessions with playback tracking. Use when logging audio sessions, searching metadata, analyzing listening data.

Learn to combine DeFi protocols safely: Uniswap V4 hooks, Aave flash loans, ERC-4626 vaults, Aerodrome on Base, GMX/Pendle on Arbitrum, and dominant DEX per L2.

Build an automated pipeline to defang indicators of compromise (URLs, IPs, domains, emails) for safe sharing and distribute them in STIX format through TAXII feeds and threat intelligence platforms.

Systematic debugging — reproduce, read the error, isolate, hypothesize, fix, verify, document. Use when tracking down a bug, unexpected behavior, or test failure — including phrases like "this doesn't work", "why is this failing", or "help me debug".

Run a reproduce → isolate → verify debugging workflow for concrete bugs, regressions, flaky failures, and environment-specific behavior. Use when the user already has a failing command, test, request, UI flow, or narrowed symptom and needs root-cause diagnosis or fix verification rather than raw log-line selection, broad test-policy design, PR review, or generic performance tuning.

Use when investigating a bug, runtime error, unexpected behavior, test failure, or crash. For systematic root cause analysis, error message interpretation, stack trace reading, reproduction steps, and targeted fixes. Activate when the user says "it's broken", "this doesn't work", "I'm getting an error", or "help me debug".

Investigate a problem, log it to the debug changelog, cross-check past issues, and suggest a non-duplicate fix.

Builds or debugs Google Gemini features using @google/generative-ai, covering generateContent, function calling, grounding, multimodal input, and streaming, with guidance for editing src/lib/ai/clients/google.ts.

Demystifying CLIP Data

Strip AI-generated tells from a draft and rewrite it in Heath's personal voice (GTM Juice). Fire whenever the user asks to "humanize", "de-AI", "clean up", "rewrite in my voice", "make this sound like me", "kill the AI tells", or "polish this draft". Also fires as the mandatory final pass inside juice-content-dispatch — every LinkedIn post, newsletter, and video script drafted there must run through this skill before the Notion write. Applies the 29-pattern Wikipedia "Signs of AI writing" catalog (em dashes, significance inflation, promotional language, rule of three, synonym cycling, inline-header lists, sycophantic tone, hyphenated word pairs, persuasive-authority tropes, signposting, etc.), then applies a hardcoded Heath-voice calibration: self-implicating first, failure-derived, plain declaratives over bumper-sticker aphorisms, no bow-tied endings, never Mixmax corporate brand voice. Forked from blader/humanizer (MIT).

Fix broken or failing functionality through structured reproduction, root-cause analysis, minimal fix, and verification. Load when the user asks to fix a bug, debug an error, resolve an issue, or work on a Linear ticket. Also triggers on "this is broken", "fix this bug", "why is this failing", "debug this", "resolve this error", "what went wrong", or any request to diagnose and fix a problem.

Perform nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP workflows using the umap-learn library.

A stakeholder asks to make search faster.

Scan installed skills to extract cross-cutting principles and distill them into rules files.

LEMON v2.0 — The Degen Fader. Identifies historically reckless traders (DEGEN activity + CHOPPY consistency) on Hyperliquid, monitors their live positions, and counter-trades them when they're bleeding at high leverage. If a cluster of degens goes max-leverage long on a coin and starts losing, LEMON shorts it — betting on their inevitable liquidation cascade. DSL exit managed by plugin runtime via runtime.yaml.

Deduplicating Training Data Makes Language Models Better

Systematically diagnose and fix software bugs by analyzing error messages, stack traces, logs, and runtime behavior across multiple languages. Use when the user requests debugging or provides relevant inputs for this workflow.

Remix patterns including loaders, actions, nested routing, progressive enhancement, and deployment strategies.

Reproduces failures, gathers evidence, tests hypotheses, fixes root causes, and adds regression coverage.

Comprehensive guide to qmix. Master the concepts, implementation, best practices, and real-world applications of qmix in professional environments.

Provides a structured debugging workflow for non-technical founders, covering reproduction, diagnostic gathering, and AI-assisted fixes.

Combines multiple pipe-format blocks from conversation context into one unified output, handling deduplication, source attribution, and confidence upgrades.

Debug LLM applications using the Phoenix CLI: fetch traces, analyze errors, structure trace review with open and axial coding, inspect datasets, review experiments, and query the GraphQL API.

Hard Negative Mixing for Contrastive Learning

Guiding workflows by decomposing complex tasks (Epics) into Atomic Steps under 15 minutes each, with progress tracking and drift prevention. Use when complex decomposition is needed.

Live developer experience audit. Uses the browse tool to actually TEST the developer experience: navigates docs, tries the getting started flow, times TTHW, screenshots error messages, evaluates CLI help text. Produces a DX scorecard with evidence. Compares against /plan-devex-review scores if they exist (the boomerang: plan said 3 minutes, reality says 8). Use when asked to "test the DX", "DX audit", "developer experience test", or "try the onboarding". Proactively suggest after shipping a developer-facing feature. (gstack) Voice triggers (speech-to-text aliases): "dx audit", "test the developer experience", "try the onboarding", "developer experience test".

Level 2+ task decomposition. Use when a single task from tasks.md is STILL too complex (affects 3+ files or requires multiple logic blocks). Breaks tasks into MICROTASKS (1 file/function each) for granular implementation. NOT for initial task breakdown - OpenSpec already does that.

Build and debug Retrieval-Augmented Generation pipelines — chunking, embedding, retrieval, reranking

Decompose work into small, verifiable tasks with explicit acceptance criteria, ordered by dependencies and sliced vertically for reliable implementation.

4-phase systematic debugging methodology with root cause analysis and evidence-based verification. Use when debugging complex issues.

Configure debugging, bundle analysis, and ecosystem tools for React applications. Use when setting up Vite/webpack build tooling, analyzing bundle size, debugging re-renders with React DevTools, or configuring ESLint and StrictMode for React projects.