Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.

Generates a comprehensive testing plan based on the current branch changes or a specific PR. Use when creating QA checklists, test plans, or verifying PR readiness.

Query the OFR (Office of Financial Research) Hedge Fund Monitor API for hedge fund data including SEC Form PF aggregated statistics, CFTC Traders in Financial Futures, FICC Sponsored Repo volumes, and FRB SCOOS dealer financing terms. Access time series data on hedge fund size, leverage, counterparties, liquidity, complexity, and risk management. No API key or registration required. Use when working with hedge fund data, systemic risk monitoring, financial stability research, hedge fund leverage or leverage ratios, counterparty concentration, Form PF statistics, repo market data, or OFR financial research data.

宠物成员注册主流程。**用户表达「登记/记住/让系统认识我家的猫/狗等宠物」意图就触发本 SKILL,不要求出现"注册/登记"字面词**——两条通路:①**描述它的样子**(纯文字,如"胖胖是我家橘猫,尾部有白毛、体型偏胖")→ 建花名册 + 写外观;②**发照片/视频** → 观察出多姿态候选参考图 + 共性外观 → 确认 → 落库(花名册 + 识别参照 + 外观)。也覆盖给存量宠物"补充素材"。**只用用户主动提供的信息**(文字或素材):宠物没有"陌生宠物池",不从摄像头挑、不模拟。纯改名 / 删宠物走 miloco-cli pet CRUD。

Verify a published release of the C# MCP SDK. Monitors the Release and Publish Docs workflows triggered by publishing a GitHub release, confirms the packages are listed on NuGet.org, and confirms the versioned documentation site reflects the release. Use when asked to verify a release, check whether a release published correctly, monitor the release or docs workflow, confirm packages on NuGet, or check whether the docs site updated.

Run MiniCPM5-1B or MiniCPM5-2B with Hugging Face Transformers for one-shot Python generation on GPU (bfloat16) or CPU (float32). Use when the user wants a quick Python script, no server, no extra deps, or asks for "Transformers", "AutoModelForCausalLM", "model.generate" with MiniCPM5.

Generate professional company tear sheets using S&P Capital IQ data via the Kensho LLM-ready API MCP server. Use this skill whenever the user asks for a tear sheet, company one-pager, company profile, fact sheet, company snapshot, or company overview document — especially when they mention a specific company name or ticker. Also trigger when users ask for equity research summaries, M&A company profiles, corporate development target profiles, sales/BD meeting prep documents, or any concise single-company financial summary. This skill supports four audience types: equity research, investment banking/M&A, corporate development, and sales/business development. If the user doesn't specify an audience, ask. Works for both public and private companies.

Explore and diagnose a PostHog endpoint's execution logs — error messages, failed runs, cache misses, slow runs, or unexpected row counts during endpoint invocations. Use when the user says "my endpoint is failing", "show me the logs for endpoint X", "what error did endpoint Y produce", "why did endpoint Z return no rows", "is this endpoint hitting cache", or "check the last N runs". Focused on a single named endpoint's runtime log entries, not project-wide auditing or query performance profiling.

Explore PostHog's Inbox and act on what it surfaces — the place where signal reports cluster into actionable issues and trends. Use when the user asks "what's in my inbox?", "what should I look at?", "which reports are actionable?", "what's PostHog flagged recently?", asks about a specific report by ID or title, wants to act on / fix / implement a report (turn it into a PR), wants to resolve, dismiss, or snooze a report, or wants to see which signal sources are configured. Covers listing, filtering, drilling into, and acting on reports, plus pointers to the deeper `signals` skill when raw signals or semantic search are needed.

Converts DeepWiki documentation from a GitHub repository into a reusable local skill (Cursor, Agent Zero, OpenCode, or any harness using SKILL.md + references/). Verifies DeepWiki tool access, captures raw wiki structure and contents, splits pages into stable reference files, rebuilds a linked hierarchy, and generates a concise SKILL.md with progressive disclosure. Use when the user asks to "convert DeepWiki to a skill", "make a skill from this repo's wiki", "turn DeepWiki into references", "document this GitHub repo as a skill", or wants reusable per-repo documentation derived from DeepWiki output. Do NOT use when the repo has no DeepWiki coverage, when generating skills from source code (use create-skill instead), or for ad hoc repo Q&A (call DeepWiki MCP directly).

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative testing,' 'ad performance optimization,' 'write me some ads,' 'Facebook ad copy,' 'Google ad headlines,' 'LinkedIn ad text,' or 'I need more ad variations.' Use this whenever someone needs to produce ad copy at scale or iterate on existing ads. For campaign strategy and targeting, see ads. For landing page copy, see copywriting.

Render Markdown from templates and structured data using Knap CLI. Use when the user asks to apply a Knap template, turn JSON or CSV data into notes, batch-generate Markdown files, or format Defuddle output into a note.

Doc-aware planning skill. Turns a PRD, ADR, existing plan, or raw idea into a tracer-bullet implementation plan via a relentless one-question-at-a-time interview. Reads accepted ADRs and a PRD together as constraints: ADRs fix architectural decisions; the PRD supplies goals, non-goals, and acceptance criteria that gate each phase. Drafts Proposed ADRs — asking whether a decision is new or supersedes an existing one — and updates CONTEXT.md as terms resolve. Optional tribunal stress-test before finalizing. Use when asked to "plan with docs", "plan this ADR", "turn this PRD into a plan", "break this down into phases", "tracer bullets", "review my plan", "stress test this approach", or /plan-with-docs.

Transforms loose ideas or refined concepts into structured PRDs that capture the what, who, and why — problem, target users, goals, non-goals, and testable acceptance criteria — while deliberately deferring the how (architecture, data models, APIs, delivery phasing) to the planning phase. Works through a progressive interview, light de-risking of risky assumptions, and optional codebase exploration. Use when asked to "write a PRD", "create a PRD", "design a feature", "flesh out this idea", "turn this into a spec", "product requirements", "spec this out", or /prd-designer. Outputs a markdown PRD at docs/prds/{name}.md. Optionally creates a GitHub issue via gh CLI. Dependencies: gh CLI (optional, for issue creation).

Post-push CI verification and fix workflow. Use when: (1) user says "pr-post", "check ci", "check actions", "fix ci", or "are checks passing", (2) after pushing code to a PR branch, (3) when the user wants to verify GitHub Actions status and fix any failures.

Pre-deployment security audit of Solidity smart contracts in a Foundry project. Combines static analysis (Slither, Aderyn), symbolic execution (Mythril), and property-based testing (forge fuzz + invariant tests with handlers) to catch reentrancy, access-control, oracle/price manipulation, and arithmetic bugs BEFORE deploying to an EVM chain. Also enforces key hygiene (no plaintext private keys, encrypted cast keystore) and a secure deploy workflow. Use when writing, reviewing, testing, or deploying Solidity/Foundry contracts, building a dApp, or working with forge/cast/anvil, MetaMask, or Web3/DeFi code.

Scaffold a one-command `dev-local` launcher for ANY codebase. Investigates the repo to find its services, ports, and infra dependencies, then generates a single `scripts/dev-local.sh` (up/down/status/logs/restart) that runs every dev server in one tmux session, plus a short skill doc describing it. Use when someone says "set up dev-local", "make a one-command dev launcher", "I want one script to start this repo", "scaffold dev-local for this project".

Query the Genome Aggregation Database (gnomAD). Use when determining the rarity or allele frequency of specific genetic variants, retrieving gene constraint metrics (pLI, LOEUF) to assess loss-of-function intolerance, finding variants in a genomic region or gene, or querying structural variants. Don't use for analyzing individual patient genomes, tracking somatic mutations in cancer (use COSMIC), or requesting raw sequencing reads (use ENA).

Review a batch or stack of pull requests, or run a recurring PR-review pass on a repo. Best with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.