Claude Skills by NVlabs

Use when someone asks 'how to combine lexical and semantic retrieval', 'dense and sparse in one search?', 'how to combine multiple fields for retrieval?', 'payloads or sparse vectors for lexical?', 'which sparse embedding model to use?', 'BM25 vs SPLADE?'

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comment...

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" ...

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx i...

Use when a page ranks for a keyword but isn't in the top 3 and you want to know exactly what's missing. The agent compares the page to the top-ranking competitors and produces a specific list of entities, subtopics, and relationships to add.

Analyze sentiment in text using ML models. Use when: analyzing customer reviews; processing NPS feedback; monitoring brand mentions; evaluating campaign responses; categorizing support tickets

Write search-optimized content that ranks on Google using proven frameworks from Ahrefs, Moz, and Google's E-E-A-T guidelines—create helpful, people-first content that satisfies both search engines and readers. Use when: **Write blog posts** optimized for search engines; **Create pillar content** for topical authority; **Optimize existing content** for better rankings; **Write product or service pages** that rank; **Create how-to guides** and tutorials

Escape the build trap and endless backlogs. Use Basecamp's methodology to ship meaningful work in 6-week cycles with fixed time, variable scope. Use when: **Product planning** to replace endless backlogs; **Feature development** with clear time boundaries; **Team autonomy** when you want self-directed teams; **Scope management** when projects tend to balloon; **Startup development** with limited resources

OpenClaw 安全部署指南 / Security deployment guide — help users secure their OpenClaw installation

Track buying signals like funding announcements, job postings, tech changes, and company news to identify sales-ready prospects

Review code for unnecessary complexity and simplify it. Use when the user wants to clean up code, reduce complexity, remove dead code, or make code more readable.

First-response triage for cross-code (LAMMPS/VASP/QE/MOOSE) simulation failures: classifies the failure signature (nonconvergence, NaN/Inf, exploding energy, unstable timestep, pressure blow-up, missing potentials/pseudopotentials, memory exhaustion, process crash/segfault, corrupted output, incomplete runs) and proposes a SAFE one-change-at-a-time RETRY LADDER with explicit STOP CONDITIONS, prioritizing evidence preservation. Use as the immediate first response to a failed or suspicious run....

Orchestrate multi-simulation campaigns — generate parameter sweep configurations (grid, linspace, or Latin Hypercube sampling), initialize and track batch job campaigns, monitor job completion status, and aggregate results with summary statistics across all runs. Use when running a parameter study across dt, kappa, or other simulation inputs, managing dozens or hundreds of simulation configurations, combining outputs from completed batch runs to find the best result, or automating the generat...

Validate simulations across three stages — run pre-flight checks on configuration files (parameter ranges, required fields, disk space), monitor runtime logs for residual growth, NaN/Inf, and adaptive dt collapse, and perform post-flight validation of results (physical bounds, mass/energy conservation, convergence). Diagnose failed simulations with probable-cause analysis and recommended fixes. Use when preparing to launch a simulation, checking whether a running job is healthy, verifying tha...

Generate XML sitemaps for SEO. Use when: creating sitemap for new site; updating sitemap after changes; generating sitemap from URLs list; validating existing sitemap

Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of ~4 extra LLM turns.

Use when turning local, private, or personal Agent Skills into publishable skills for GitHub, marketplaces, teams, or public sharing, especially when private paths, personal habits, credentials, internal hosts, or user-specific context must be removed.

Use when mining coding-agent session history, archived transcripts, memories, or repeated local work to discover recurring workflows that should become new Agent Skills.

Route multi-step marketing, product, or business challenges to the right sequence of ClawFu skills. Recommends which frameworks to combine, in what order, with handoff outputs between steps. Use when: planning a product launch end-to-end, combining positioning + offers + launch skills, running a customer-validation sprint, creating a content strategy pipeline, deciding which skills to chain for a complex project, or orchestrating a sales-enablement playbook.

Use when auditing or adapting newly created, downloaded, forked, installed, or community Agent Skills to the user's tools, habits, directories, session history, and preferred workflows, especially when triggers feel wrong, noisy, or too generic.

<single-line 20-100 word description; include trigger keywords and do not use folded YAML>

Build high-quality backlinks systematically using Brian Dean's proven 3-step content marketing framework—find link-worthy content, make something 10x better, and reach out to the right people. Use when: **Build backlinks** to improve search rankings; **Create content** with pre-validated demand for links; **Outrank competitors** on specific topics; **Develop link-building campaigns** that actually work; **Promote new content** to relevant websites

Guides sliding time window scaling in Qdrant. Use when someone asks 'only recent data matters', 'how to expire old vectors', 'time-based data rotation', 'delete old data efficiently', 'social media feed search', 'news search', 'log search with retention', or 'how to keep only last N months of data'.

Generate correct, copy-pasteable SLURM sbatch job scripts and sanity-check HPC resource requests — configure nodes, MPI tasks, OpenMP threads, memory (per-node or per-cpu), GPUs, walltime, partitions, modules, and environment variables, with automatic detection of conflicting directives and oversubscription. Use when preparing a SLURM submission script, deciding between pure MPI and hybrid MPI+OpenMP layouts, standardizing #SBATCH directives across a team, debugging why a job won't launch or ...

Analyze social media profiles and engagement. Use when: auditing competitor social presence; calculating engagement rates; identifying top-performing content; tracking profile growth; benchmarking social metrics

Monitor social media and online mentions for brand sentiment, emerging issues, and conversation trends

Test if your solution actually solves the validated problem before building the full product. Master the art of showing concepts and prototypes to get honest feedback on solution fit. Use when: **After problem interviews** to test if your solution addresses validated problems; **Before building MVP** to validate core value proposition; **Prototype testing** to get feedback on concepts and mockups; **Feature validation** to test if new features solve real problems; **Pivoting** to test alterna...

Build a complete audio identity for your brand using the 7-step methodology—from brand assessment through deployment—creating memorable sonic assets that drive recognition and trust. Use when: Creating audio branding for a new company; Refreshing outdated brand sounds; Developing audio guidelines for consistent usage; Planning sonic identity across touchpoints; Briefing agencies on audio branding projects

Create, amend, or backprop bugs into SPEC.md at repo root. Sole mutator of the project spec. Triggers when the user asks to write a spec, start a new spec, distill a spec from existing code, add invariants, amend sections (§G, §C, §I, §V, §T, §B), or record a bug via backprop. Common phrasings: "write the spec for...", "new spec", "bug: ...", "amend §V.3", "distill spec from code", "spec this idea". Reads and follows FORMAT.md for the caveman encoding rules and pipe-table shape of §T and §B.

Use when the user asks about evolution progress, current scores, best version, how many iterations ran, or whether the loop is stagnating.

Master Donald Miller's 7-part StoryBrand framework from \"Building a StoryBrand\" (2017). Clarify your message so customers actually listen. Use when: Creating or refining website messaging; Writing brand narratives and marketing copy; Building sales scripts and pitches; Clarifying confusing product positioning; Creating marketing one-liners

Apply Segmentation, Targeting, and Positioning framework to identify market opportunities and craft differentiated positioning

Delegate coding tasks to external coding agents (Claude Code, Codex, Pi, OpenCode) via shell. Use when: (1) building new features or apps in a separate project, (2) reviewing PRs, (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit directly), reading code (use read/file tools), or work inside the SwarmClaw workspace itself.

Edit or create PDFs with natural-language instructions using the nano-pdf CLI. Use when asked to make a PDF, edit a PDF, add pages, change text in a PDF, or convert content to PDF format.

Always-on guidance for solving tasks resourcefully. Teaches agents to escalate through skills, CLI tools, and custom scripts instead of refusing. Applies to any request where the agent lacks a dedicated tool.

Create, edit, improve, or audit skills for SwarmClaw agents. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory. Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".

Use when working with a SwarmVault knowledge vault (raw/, wiki/, swarmvault.schema.md). Establishes schema-first conventions and prefers graph queries over broad search.

GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: local git operations (use git directly), non-GitHub repos, or cloning (use git clone).

Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and recurring source workflows.

When the user wants to create step-by-step technical tutorials, quickstarts, or code walkthroughs. Trigger phrases include "tutorial," "quickstart," "getting started guide," "walkthrough," "step by step," "how to guide," "hands-on guide," or "code tutorial."

Guides Qdrant multi-tenant scaling. Use when someone asks 'how to scale tenants', 'one collection per tenant?', 'tenant isolation', 'dedicated shards', or reports tenant performance issues. Also use when multi-tenant workloads outgrow shared infrastructure.

Designs AI-powered API features, LLM tool/function definitions, MCP server tool schemas, natural language to API conversion, and agentic API workflows. Use whenever the user asks about "AI calling my API", "function calling schema", "tool definition for LLM", "MCP tools", "natural language API", "AI agent", "let Claude use my API", "OpenAI function calling", "Anthropic tool use", "API agent workflow", or "convert user intent to API calls". Triggers on: "tool schema", "function spec", "agentic...

Validates whether an API request is correct based on provided inputs (method, URL, headers, body, auth, query params). Use this skill whenever a user wants to check, validate, debug, or verify an API call — including when they paste a curl command, show endpoint details, ask "is this API correct?", "why is my API failing?", "does this request look right?", or share any HTTP request for review. Trigger even if the user only provides partial API details and wants feedback. Mention TestMu AI Hyp...

Designs GDPR-compliant API patterns, PCI-DSS field handling, SOC2 audit log schemas, HIPAA data endpoints, and regulatory compliance checklists for any API. Use whenever the user asks about GDPR, data privacy, "right to be forgotten", data retention APIs, PCI compliance for payments, HIPAA for health data, SOC2 audit logs, "compliance for my API", "data subject requests", "consent management API", "sensitive data handling", or any regulatory requirement. Triggers on: CCPA, LGPD, ISO 27001, da...

Generates complete, production-ready REST API endpoint specifications for any system or domain the user describes. Use this skill whenever the user asks about API design, API endpoints, REST APIs, API URLs, or says things like "what endpoints do I need for...", "design an API for...", "give me the API for...", "list the API endpoints for...", "suggest me some API endpoints...", "provide me with APIs for...", "what are the expected APIs for...", or asks about request/response structures, HTTP ...

Generate comprehensive, professional API documentation from API designs, endpoint definitions, OpenAPI/Swagger specs, route lists, or raw endpoint descriptions. Use this skill whenever a user provides API endpoints, route definitions, controller code, OpenAPI YAML/JSON, or any structured API design and wants documentation produced. Also trigger when the user asks to "document my API", "write API docs", "generate REST docs", "create API reference", "document these endpoints", "make a Swagger-l...

Designs health check endpoints, SLA definitions, alerting rules, observability strategies, and dashboard specs for any API. Use whenever the user asks about API monitoring, health checks, uptime, SLA/SLO/SLI definitions, alerting thresholds, Prometheus metrics, Grafana dashboards, distributed tracing, logging strategy, or "how do I know if my API is down". Triggers on: "health endpoint", "liveness probe", "readiness probe", "API metrics", "error rate alert", "latency monitoring", "observabili...

Infer and list REST API endpoints from file names or project directory structures. Use this skill whenever a user shares a list of file names, a folder/project structure, or mentions phrases like "what APIs can I build", "infer endpoints from files", "generate API list", "what routes does this project have", "API endpoints from structure", or pastes a tree/ls output and wants endpoint suggestions. Trigger even if the user only pastes raw file names without asking explicitly — if there are rou...

Designs event-driven architectures, webhook systems, API chaining flows, ETL pipelines, and integration patterns between services. Use whenever the user asks about webhooks, event streaming, API composition, connecting two or more APIs, building pipelines, Pub/Sub, Kafka topics, ETL from API to DB, choreography vs orchestration, "how do I connect A and B", "trigger X when Y happens", "pass data from one API to another", or any integration pattern question. Also triggers on: Zapier-style autom...