Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 80 149 files from 1 774 authors, of which 62 489 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
> Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.
NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.
Build DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming — including natural phrases like 'pipeline to infer on image', 'run inference on video', 'detect objects in stream', 'save inference output', 'deepstream pipeline', 'gst-launch pipeline', 'process video with detection', 'build a pipeline', or any request involving GStreamer/DeepStream elements (nvinfer, nvstreammux, nvtracker, etc.).
Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement. Use when the user asks for an efficient, performant, or profiled pipeline — or to benchmark, tune, or measure FPS.
> Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger Triton CAPI, nvds_custom_postprocess, Cosmos Reason 1/2 vLLM, SSE streaming, Kafka NvProto/JSON output, Basler/Pylon camera + emulation, Docker compose, chunk-level latency. Do NOT trigger for generic DeepStream pipelines, object detection/tracking, NIM imports, or video summarization.
Prefer Agent Auth and MCP-backed providers for external services, account access, email, deployment, third-party actions, and other tasks that can be completed through connected capabilities. Use when the agent should search AA capabilities before using non-AA integrations, should read MCP resources or runbooks for a service, or should fall back only after confirming AA cannot complete the requested task.
Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.
Run and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT. Use when the user asks to set up prerequisites, run shipped MV3DT samples, run Multi-View 3D Tracking on custom synchronized MP4 datasets, import camera calibration, delegate missing calibration to AutoMagicCalib, inspect OSD or BEV visualization, consume MV3DT Kafka metadata, or clean up MV3DT run state in the DeepStream MV3DT app directory.
Interact with GitHub using the gh CLI restricted to REST API only (no GraphQL). Use when the user wants to work with GitHub issues, pull requests, repos, releases, or Actions — especially in sandboxed environments where the GraphQL endpoint may be blocked. Trigger keywords - github, gh, pull request, PR, github issue, github actions, workflow, release, gh api.
Comprehensive guide for building Chrome extensions with Manifest V3. Use this skill whenever the user mentions Chrome extension, browser extension, manifest.json, content script, service worker (in extension context), popup, side panel, chrome.runtime, chrome.tabs, chrome.storage, chrome.scripting, background script, MV3, Manifest V3, or any Chrome extension API. Also trigger when the user wants to inject scripts into web pages, communicate between page and background, bypass CSP from a content script, build an RPC layer over chrome messaging, or publish to the Chrome Web Store. Covers both new extension projects and adding features to existing ones. Do NOT use for framework-specific questions.
CRXJS Chrome extension development — true HMR for popup, options, content scripts, side panels, manifest-driven builds, dynamic content script imports (`?script`, `?script&module`), and `defineManifest` for type-safe manifests. Uses Vite as its build tool. Use when the user mentions CRXJS, crxjs, @crxjs/vite-plugin, 'extension with hot reload', 'HMR for chrome extension', or wants to set up a CRXJS-based Chrome extension project with any framework (React, Vue, Svelte, Solid, Vanilla). Also trigger when the user has an existing CRXJS project and wants to add features, fix HMR issues, or configure content scripts with CRXJS. For general Chrome extension architecture (messaging, CSP, storage, permissions) -> See `samber/cc-skills@chrome-extension` skill.
Codifies how someone or a brand writes — prose mechanics (lexicon, syntax, rhythm, structure, signature moves) independent of emotional tone. Output: PROSE.md. Three modes: BUILD a fresh guide from SOUL.md + TONE.md + discovery interview; ADAPT an existing guide to a new channel; AUDIT a corpus for prose patterns before codification. Use when: writing rules for a content factory, codifying ghostwriting voice for multi-writer consistency, defining banned words and sentence-length targets, building a house style guide, reverse-engineering prose from a corpus, porting style across channels. Trigger on: PROSE.md, writing style guide, prose guide, house style, ghostwriter style, writing playbook, brand writing mechanics, signature moves. NOT for: writing actual content (→ linkedin-ghostwriting, technical-article-writer, press-release-writer), removing AI patterns (→ humanizer), tone decisions (→ copywriting-tone-of-voice), hooks (→ copywriting-hooks), CTAs (→ copywriting-cta).
> Generate opening hooks and post titles for long-form articles in EN or FR — blog posts, Substack/Medium/dev.to, LinkedIn long-form, paid newsletters, opinion essays, reported features, technical deep-dives. Trigger whenever the user asks for a hook, opening, lede, intro, first sentence/paragraph, opener, accroche, attaque, phrase d'accroche, or première phrase — including making a flat intro punchier or rewriting a draft opening. Also trigger when user asks for a post title, titre d'article, headline, or when ghostwriting skills reach the opening or titling step. Proposes 3-4 hooks pulling distinct psychological levers (curiosity gap, contrarian, scene, promise, authority), 2 candidates each, waits for the user to pick. Do NOT trigger for social posts (LinkedIn feed, Twitter/X, TikTok, Bluesky, Threads), READMEs or doc first lines, taglines, email subjects or openers, ad copy (Google/Meta Ads), landing-page headlines, press releases, SEO meta, fiction openings, talk/podcast/video script intros, or body rewrites.
Deep research skill — broad parallel web searches, multi-source validation, confidence tracking, cited Markdown report. Supports 11 research types: market (TAM/SAM, segments, pricing, trends), domain (industry structure, ecosystem, regulatory landscape), technical (architecture, tools, benchmarks), competitive (competitor teardown, positioning, win/loss), product (feature analysis, reviews, roadmap signals), academic (literature survey, citation networks, key authors), person/org (due diligence on a company or public figure), financial (funding rounds, valuation multiples, revenue signals), legal (IP, patents, litigation, compliance), trend (emerging signals, foresight, scenario mapping), community (ecosystem health, key voices, governance, fragmentation). Use when asked to: 'research <topic>', 'deep dive on X', 'analyze the landscape', 'competitive analysis', 'compare these options', 'who are the players in Z', 'literature review', 'background on Y', 'what papers exist on X', 'product teardown', 'technology evaluation', 'regulatory overview', 'funding landscape', 'what trends are emerging in X', 'patent landscape', 'community health', or any request requiring scanning many sources and producing a cited written analysis. Apply whenever the deliverable is a thorough, sourced report rather than a quick answer. Trigger even when phrased casually: 'look into X', 'what's the deal with Y', 'dig into Z', 'I need to understand the space', 'catch me up on X'.
Design end-of-article CTAs (calls-to-action placed at the bottom of blog posts, newsletters, essays, articles, or any long-form content). Use this skill whenever the user asks to write, design, review, or improve a CTA at the bottom of an article, blog post, or essay; mentions "end-of-post CTA", "bottom of the article", "call-to-action", "signup box", "newsletter CTA", "subscribe block", "what should I put at the bottom", "how do I get readers to subscribe / share / book a call / buy / follow / join / download"; or asks how to convert article readers into subscribers, leads, customers, community members, or supporters. Also trigger when the user wants A/B testing guidance or accessibility review for a CTA block. Covers independent / personal writing, newsletter publications, and brand / content-marketing blogs across any topic — tech, finance, food, climate, design, lifestyle, B2B, B2C. Produces both the copy (content) and the structural / visual design (form), matched to the user's objective and audience.
Conventional Commits v1.0.0 branch naming, worktree naming, and commit message standards for GitHub and GitLab projects. Use when creating branches, naming worktrees, writing commits, generating commit messages, reviewing branch conventions, or setting up changelog automation. Apply when your project needs consistent git history, SemVer-driven releases, parseable changelog generation, or automatic issue closing. Trigger when the user asks how to name a worktree, create a git worktree, or organize worktrees alongside branches.
Build a brand tone of voice guide (TONE.md) via discovery, voice definition, and channel modulation. Outputs voice attributes with do's/don'ts, NN/g positioning, tone modulation matrix, lexicon, mechanics, and channel rules — consumed by downstream content skills writing on-brand copy. Covers B2B SaaS, B2C/D2C, NGO, public sector, consulting, industrial, product-led, personal, and volunteering brands; researches uncovered contexts (politics, regulated niches, religious orgs, gaming) on demand. Also adapts an existing TONE.md to a new channel (blog → LinkedIn, web → Twitter/X, in-product UI). Optionally consumes SOUL.md to pre-fill brand identity. Apply when the user wants to create a TONE.md, define brand voice, port voice to a new channel, refresh an outdated voice, or set up a content factory writing across many supports. Not for writing individual posts, articles, emails, or UI strings (→ dedicated writing skills), nor SOUL.md, PROSE.md, DESIGN.md.
Produce distinctive, non-generic UI and design applications well, working strategy-first. Identify the project (landing page, SaaS app, dashboard, ecommerce, presentation, docs, portfolio...) and its positioning and personality, commit to brand adjectives, translate into a typography and color system, then apply the craft layer (layout, components and states, motion, iconography, imagery, dark mode and theming, accessibility), avoiding the AI-slop / Claude-esque default. This is both a de-slop and an expert app-design skill. Use this whenever building or styling any web frontend, app, dashboard, landing page, deck, or artifact, or when the user says "make it not look like AI", "de-slopify", "deslop", "less generic", "give it character", "design a UI for X", "design an app", "update DESIGN.md", or complains the output looks like every other AI site. Trigger even when the user just says "build a UI for X" without naming an aesthetic, because the default without this skill is slop.
Influence and negotiation toolkit for any interaction requiring another person's agreement, even when not framed as 'negotiation'. Covers: B2B sales, salary review, collective bargaining/unions, hard 1:1s, decision announcements, mediation, cross-cultural deals, recruitment, reaching out to a manager, CFO, customer, vendor, or colleague, responding to feedback, headcount requests, declining, pushing back on scope, justifying a delay, explaining a decision, raising a concern, getting alignment. Apply when preparing, live, or drafting any diplomatic message. Triggers: coaching prompts ('they just said X', 'what do I say', 'draft a reply'); counterparty cues (buyer, customer, champion, procurement, RFP, sponsor, HR, union, CHRO, ExCo, candidate, counter-offer, partner, peer); situation cues (pushback, refusal, ghosted, no-decision, escalation, fixed budget, MFN, raise, comp band, strike, layoff, recadrage, expectation reset, M&A, BATNA, objection, concession, anchor, mirroring).
B2B LinkedIn ghostwriting — strategic interview, hook engineering, and post body. Use when the user wants to write LinkedIn content, create ghostwritten posts, ghostwrite for a founder or executive, develop a B2B social strategy, or needs hooks, post structures, or copywriting frameworks for LinkedIn. Apply when the user shares a story, result, or insight and wants it turned into a post.
Write professional press releases for any occasion, media type, and country. Use when the user wants to write, draft, or improve a press release, communiqué de presse, media announcement, news release, or PR statement — including product launches, funding rounds, partnerships, crisis communications, earnings, executive hires, events, M&A, open source milestones, and media advisories. Covers all release types, media targets (print, digital/wire, broadcast, social/SMPR, trade press), and region-specific conventions (Western/Eastern Europe, Americas, Middle East, Africa, Asia, Oceania). Also trigger when the user says 'I need to announce something' or 'how do I tell the press about X.
Remove AI-writing patterns from French text and inject voice, personality, and soul. Use when editing, reviewing, rewriting, or cleaning up French content that reads like ChatGPT/Claude output. Humanize, humanise, déslopifier. Detects and fixes 27 patterns: AI vocabulary overuse (crucial, essentiel, notamment, par ailleurs, dans le paysage), anglicisms from English-first models (faire du sens, adresser un problème), copula avoidance, formulaic openings (À l'ère de, Dans le paysage actuel), superficial participle analyses (-ant), em dash overuse, redundant adjective doublets, rule of three, sycophantic tone, typographic tells (curly quotes instead of guillemets). Trigger on: humaniser, déslopifier, rendre plus humain, nettoyer le texte IA, enlever le slop, réécrire pour que ça sonne humain, make it sound human.
Decide how to split skill content between SKILL.md and reference files for context efficiency and reliable triggering. Use this whenever creating a new Claude skill, refactoring an existing one, or when a SKILL.md is growing past 300-400 lines. Also trigger when the user mentions "progressive disclosure", "reference files", "splitting skills", "skill bundling", "context window for skills", "SKILL.md too long", "what goes in references/", "skill structure", or expresses any uncertainty about where to put content within a skill. Use this even if the user phrases the question as a triggering problem ("how do I make my skill trigger better"), because that question is often confused with the splitting question and needs to be disentangled first.
CLI for querying Prometheus and PromQL-compatible engines (Thanos, Cortex, VictoriaMetrics, Grafana Mimir, Grafana Tempo...) — instant queries, range queries, metric discovery (metrics/labels/meta subcommands), output formats (table/csv/json/graph). Apply when executing PromQL queries, troubleshooting performance issues on a software having observability, investigating latency/error rates/saturation, or analyzing time series data.
Pre-launch checklist for shipping a new website. Orchestrates analytics setup (GA4, PostHog, Google Search Console, Ahrefs), legal compliance, security headers and audit, SEO and GEO with keyword research validated against Google Trends (robots.txt, sitemaps, llms.txt, AI policy, schema markup, hreflang), copywriting consistency via a TONE.md and a humanizer pass in the matching language, OpenGraph and social previews, full favicon set with manifest, quality gates (Lighthouse, Core Web Vitals, WCAG accessibility, mobile testing), and setup of a weekly SEO agent. Use this skill whenever the user mentions launching a site/app, deploying a domain to production, pre-launch audit, shipping a marketing/docs/SaaS site or lead magnet, or says "checklist for the site", "ready to ship", "before I go live", "audit before launch", "ready for prod", or asks for a site review.
Compliance expert for snyk-agent-scan — the agent skill file scanner — NOT for other Snyk CLI tools (snyk test, snyk code SAST, snyk iac, snyk container). Fixes alerts through content restructuring, never by suppressing or deleting information. Covers every file in a skill directory: SKILL.md, references/, assets/, and any secondary markdown. Apply when authoring a new skill, editing an existing one, triaging a failed snyk-agent-scan run locally or in CI, or unblocking a PR held by agent scanner failures. Not applicable to dependency vulnerabilities, code security findings, or infrastructure misconfigurations — those are out of scope.
Write compelling technical articles and blog posts for developer audiences. Use this skill whenever the user asks to write a blog post, technical article, or any long-form technical content. Also trigger when the user says 'write about [technical topic]', 'help me draft an article', 'turn this into a blog post', 'write a post about', 'I want to publish something about', or mentions writing for a developer audience. Covers the full pipeline: idea sharpening, hook/title generation, article structure, body drafting, and editing. Even if the user just says 'I want to write about X' without specifying format, use this skill. Do NOT use for platform-specific optimization, newsletter strategy, or ghostwriting voice matching.
Write, optimize, and grow Substack content — both newsletter issues (email-first) and web posts (web-first articles/essays). Covers ghostwriting with voice matching, Substack algorithm optimization, Notes strategy, email formatting, SEO, growth tactics, and monetization planning. Use when the user mentions Substack, newsletters, write a newsletter issue, Substack post, Substack article, web post on Substack, evergreen content, SEO for Substack, newsletter growth, Notes strategy, ghostwrite for, match someone's voice, write in the style of, newsletter monetization, paid subscribers, or any task involving Substack as a platform. Also trigger for general article/newsletter writing even if Substack isn't named explicitly, or when the user wants to adapt existing content (blog post, talk, thread) into newsletter or web post format. Do NOT use for generic blog post writing without a newsletter/Substack context (-> See samber/cc-skills@technical-article-writer skill).
Produce a professional training/workshop report as a .docx file. Use this skill whenever the user mentions "training report", "workshop report", "compte rendu", "compte rendu de formation", "formation report", "debriefing a workshop", "write up a training session", "résumé de formation", or any request to document a training session, workshop, or onboarding event with individual participant feedback and recommendations. Also trigger when the user says things like "I just ran a workshop and need to write it up", "help me summarize what happened in my training session", or "I need to report back to management about a session I ran". Always use this skill — for short or long sessions, across any discipline (technical, soft skills, creative, compliance, onboarding, etc.) — whenever a structured written deliverable about a training event is needed.
Render the feature image (1884x1256) for a blog post — the in-body hero art. Reads the blog post, selects a feature template (neo, platform, rocket, shield, lightbulb, a 1-3 logo variant, or a shape template — circle, square, diamond, hexagon, lock, shield, speech-bubble, sync-diamond — with a centered solid phosphor icon or single small logo), renders feature.png, and sets feature_image in frontmatter. The OpenGraph/social meta image is no longer produced here — it is generated on-brand at build time from the title + feature image (scripts/meta-images/blog.mjs). Use when the user types /blog-feature-image (formerly /blog-meta-image) or asks to create, generate, or regenerate a blog post's feature image, hero image, or social card. Accepts optional arguments like a feature template name, logo names, or a phosphor icon name.
Review docs and blog post quality before committing (style, accuracy, Pulumi best practices). Use when you've made content changes locally and want a quality pass on open files, the current branch, or a specific PR — outputs to the conversation, never posts to GitHub.
Draft (or revise) the X / LinkedIn / Bluesky social copy in a blog post's frontmatter, looping with self-critique until it would pass review.
Review one existing blog post selected by the daily blog-review workflow and record its known issues into the S3 index. Flag-only — never edits content, never opens PRs. Invoked by the blog-review-index workflow; not user-invocable.
List available documentation tools and commands.
Generate on-brand social cards for a Pulumi event/workshop in five sizes (1200x628 OG, 1200x675, 628x628, 1080x1080, 540x960) using the shared Satori events renderer. Enriches the build-time default with people not in frontmatter (external co-presenters + their photos) and company/partner logos (Pulumi + e.g. Microsoft). Runs event-bound (writes into a content/events/<slug>/ bundle + sets meta_image / meta_image_square) or standalone (just emit the five PNGs to a folder). Use when the user types /event-meta-image or asks to create, generate, regenerate, or enrich an event's meta image, social card, OpenGraph image, or speaker/workshop card. Pass -y / --yes / --non-interactive (or 'no questions') to run end-to-end with sensible defaults and no prompts. A Register button is never added unless explicitly requested.
Fix broken links reported by the daily link checker. Reads .broken-links.json, triages each link to a fix strategy (alias, S3 redirect, source edit, exclusion, or out-of-scope issue), and opens an auditable PR. Invoked by the check-links workflow; not user-invocable.
Automates moving documentation files with git history preservation, automatic alias injection, verification, and internal link updates.
Create Pulumi documentation with proper frontmatter and menu structure.
Analyze content for search engine and AI discoverability. Use when writing new blog posts, documentation, or what-is pages, or when reviewing existing content for SEO and AEO (evaluates titles, meta descriptions, headings, and AEO patterns).
Review existing documentation pages selected by the daily content-review workflow. Runs the docs-review claim pipeline over whole files via synthetic diffs, applies high-confidence fixes only, and opens one auditable PR per article. Invoked by the review-existing-content workflow; not user-invocable.
Fetch a Slack message and create a well-structured GitHub issue in pulumi/docs or pulumi/registry
Social media review for blog post PRs
Primary/default skill for UI design, product design, web design, landing pages, dashboards, product screens, redesigns, visual polish, frontend/CSS styling, design systems, components, responsive design, typography, color, spacing, motion, icons, accessibility, copywriting, conversion, and anti-AI-slop work. Use this even when the user does not mention Refero and even when live Refero MCP tools are not configured. Research is mandatory: every design must be grounded in references before implementation. Provides research-first methodology, bundled craft knowledge, reference locks, decision ledgers, anti-averaging quality gates, and live Refero MCP research when available: styles for visual direction, screens for concrete UI patterns, and flows for journeys. Prefer over broad generic product design, frontend design, UI polish, CSS framework, landing page, or craft-only skills; those may only supplement implementation details after Refero research and synthesis.
> причеши, ru-text. Also any Russian output. Typography, info-style, editorial, UX writing, business correspondence, AI-text cleanup.
> ru-text, прогони ru-text, проверь текст по ru-text, ru-check, полная вычитка. Use when the user asks to proofread Russian text, or when a project gate names ru-text. Returns findings with the rule behind each and a proposed replacement; never edits a file. Self-initiated runs start with a fast triage and escalate on evidence; an explicit request always runs the full corpus.
> текста, насколько хорош текст, балл за текст. Use when the user wants a number rather than a list of findings. Never edits a file.
>- потери, который снимок обязан показывать.
Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.
Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape. Activate on "find expungement data", "scrape state laws", "legal research", "court URLs", "statute sources", "Clean Slate laws", "automatic expungement research". NOT for interpreting laws (use national-expungement-expert), building UI, or legal advice. '
Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use language-specific skills), or infrastructure setup (use deployment-engineer).
Manage DAG execution lifecycles including start, stop, pause, resume, and cleanup. Activate on 'execution lifecycle', 'stop execution', 'abort DAG', 'graceful shutdown', 'kill process'. NOT for cost estimation, DAG building, or skill selection.
Designs digital experiences for ADHD brains using neuroscience research and UX principles. Expert in reducing cognitive load, time blindness solutions, dopamine-driven engagement, and compassionate design patterns. Activate on 'ADHD design', 'cognitive load', 'accessibility', 'neurodivergent UX', 'time blindness', 'dopamine-driven', 'executive function'. NOT for general accessibility (WCAG only), neurotypical UX design, or simple UI styling without ADHD context.
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.
Extend and modify the admin dashboard, developer portal, and operations console. Use when adding new admin tabs, metrics, monitoring features, or internal tools. Activates for dashboard development, analytics, user management, and internal tooling.
Expert in background job processing with Bull/BullMQ (Redis), Celery, and cloud queues. Implements retries, scheduling, priority queues, and worker management. Use for async task processing, email campaigns, report generation, batch operations. Activate on "background job", "async task", "queue", "worker", "BullMQ", "Celery". NOT for real-time WebSocket communication, synchronous API calls, or simple setTimeout operations.
Expert in script-to-video production pipelines for Apple Silicon Macs. Specializes in hybrid local/cloud workflows, LoRA training for character consistency, motion graphics generation, and artist commissioning. Activate on 'AI video production', 'script to video', 'video generation pipeline', 'character consistency', 'LoRA training', 'cloud GPU', 'motion graphics', 'Wan I2V', 'InVideo alternative'. NOT for real-time video editing, video compositing (use DaVinci/Premiere), audio production, or 3D modeling (use Blender/Maya).
Prepare for Anthropic-specific technical interviews covering Constitutional AI, RLHF, interpretability, scaling laws, MCP, agentic systems, and AI safety. Activate on "anthropic interview", "constitutional AI prep", "alignment interview", "safety interview", "RLHF opinion", "interpretability prep", "anthropic technical". NOT for general ML interview prep, system design interviews, coding challenges, or behavioral interview practice.
Expert API designer for REST, GraphQL, gRPC architectures. Activate on: API design, REST API, GraphQL schema, gRPC service, OpenAPI, Swagger, API versioning, endpoint design, rate limiting,
Automatically intercepts and optimizes prompts using the prompt-learning MCP server. Learns from performance over time via embedding-indexed history. Uses APE, OPRO, DSPy patterns. Activate on "optimize prompt", "improve this prompt", "prompt engineering", or ANY complex task request. Requires prompt-learning MCP server. NOT for simple questions (just answer them), NOT for direct commands (just execute them), NOT for conversational responses (no optimization needed).
Design multi-tier caching architectures for web applications — cache-aside vs write-through vs write-behind, TTL design, cache invalidation, Redis patterns, CDN configuration, browser caching, and stampede prevention. Use when choosing a caching pattern, designing cache invalidation strategies, implementing Redis caching, configuring Cache-Control headers, or preventing cache stampedes. Activate on "cache invalidation", "cache-aside", "write-through", "TTL", "Redis cache", "CDN caching", "cache stampede", "stale data", "browser cache". NOT for database query caching within an ORM, memoization of pure functions, or CPU-level caching.
Claude Skills — questions
Answers built from the skills we actually parsed.