Results for “long-put”

Runs a side-by-side walk-forward backtest of a Bull Put Spread strategy with and without a FearScore entry signal, comparing performance metrics over ~8 years of daily data.

Long-form and episodic video production pipeline (1-10 min, YouTube/web). Use when user requests 'long-form video', 'YouTube video', 'episodic video', or 'video series'.

Track multi-step work with todo, plan mode, kanban, and missions, each suited to different lifespans.

Validate and configure packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs with correct context parallelism constraints.

DreamLIP: Language-Image Pre-training with Long Captions

Run shell commands in the background with output capture and completion callbacks. Use when a command might take more than ~30 seconds (builds, tests, deployments, data processing) and you want to keep working while it runs.

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

Composite skill — safely refactor a module end-to-end with sequencing, parallel implementation, post-refactor cleanup, and rationale capture. Chains refactor-plan (phased plan + rollback) → three-man-team (architect/builder/reviewer in parallel) → fix-the-suite post-refactor → adr-write → docs-sync. Use for non-trivial refactors that need both careful sequencing and durable record.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Publishes long-form articles to hum.pub, handling registration, authentication, SEO metadata, and audience engagement.

Composite skill — promote the long-lived `release` branch to `main`, cut a single version that batches every PR accumulated since the last tag, then clean up. Chains pr-merge-readiness (on release→main PR) → version-bump (semver from commits) → changelog-update (promote [Unreleased] → versioned) → ship (tag + GitHub release) → stale-branch cleanup → optional ship-it for deploy. Use this INSTEAD of releasing every small fix individually. Many small commits become one well-scoped release.

Publish long-form articles that rank on Google and reach real human readers. Earn revenue, build reputation, engage with your audience. Not a playground — a publishing platform.

Repurpose long-form content into multiple formats including social media posts, newsletters, videos, and quote cards using the inference.sh CLI.

Fine-tune LLMs using LoRA, QLoRA, and PEFT with Hugging Face, including dataset preparation, hyperparameter tuning, evaluation, and deployment.

Build a rolling 30/60/90-day cash forecast from AR/AP aging and fixed outflows, flag floor breaches, and model liquidity levers.

Publishes long-form articles to hum.pub, handling registration, authentication, SEO metadata, and audience engagement for AI authors.

LaCLIP: Improving CLIP Training with Language Rewrites

AI 原生的潜在客户情报和外联流水线。用 agent 驱动的信号评分、共同关系人排名、暖场路径发现、来源语音建模和多渠道外联（邮件、LinkedIn、X），替代 Apollo、Clay 和 ZoomInfo。在用户想找到、评估并联系高价值联系人时使用。

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques for processing long documents and implementing efficient positional encodings.

Expert prompt optimization system for the prompts INSIDE an AI product you are building — system prompts, LLM feature prompts, chatbot/agent instructions. Use when the user wants to write or improve a system prompt for an AI feature they're shipping, review/critique an LLM prompt, apply prompt-engineering techniques (chain-of-thought, few-shot, structured output, hard constraints) to a product prompt, or optimize cost/latency of a production prompt. Do NOT use this to clarify or structure the user's own vague request to Claude Code — that is `prompt-clarifier`'s job, not this skill's.

smart-output

Runs a structured three-question lazy-check on significant output before submission, forcing root-cause analysis, alternative consideration, and outcome verification.

Write long-form content such as blog posts, guides, tutorials, and newsletters with a distinctive voice derived from supplied examples or brand guidance, ensuring structure, pacing, and credibility.

Drafts long-form content such as blog posts, guides, tutorials, and newsletters with a distinctive voice, emphasizing concrete examples and evidence over generic filler.

Runs a relentless interview that sharpens a plan or design. Use when the user wants to be grilled on an idea, pressure-test a plan, or refine a design through questioning.

Produce displace/team/ghost talk tracks for the incumbent on a recompete pursuit. Use when user wants competitive angles saved to the pursuit vault; optional multi-turn LLM for customer-facing phrasing.

Turn a long video into viral-ready short clips with a single API call, including transcription, highlight ranking, and auto-crop.

Create a structured H2/H3 outline with BLUF openers and MECE coverage, bound by the research dossier's beat spec. Triggered after /research and /brand-reference.

Generates optimized prompts for any AI tool. Use when writing, fixing, improving, or adapting a prompt for LLM, Cursor, Midjourney, image AI, video AI, coding agents, or any other AI tool.

Finds, scores, and reaches high-value contacts through social graph analysis and warm path discovery, generating personalized outreach drafts for email, LinkedIn, and X.

Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active session

Launches long-running evaluation batches in isolated tmux sessions with pre-flight verification, monitoring, and post-flight analysis for unattended runs.