Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Browser automation guidance and patterns. Trigger this skill BEFORE starting any browser interaction (navigating pages, logging in, scraping, filling forms, testing UI) to learn the correct workflow and avoid common pitfalls. Also trigger when browser MCP tools misbehave: element not found, click does nothing, page crashes, timeout, "target closed", snapshot returns empty, or any unexpected browser behavior. This skill teaches you HOW to use the browser MCP tools effectively — without it you will hit avoidable failures like stale UIDs, heavy-page crashes, and silent navigation failures.
Build NestJS the way THIS project's module architecture already does it, not by framework defaults — a reference carrying the real module boundaries and dependency-injection discipline behind thin controllers, class-validator DTOs, TypeORM/Prisma data access, guards, interceptors, pipes, exception filters, BullMQ queues, WebSockets, microservices, OpenAPI, and testing, so a change lands idiomatic and review-ready instead of bypassing the framework. Use when a task touches this project's NestJS modules and should follow its DI-driven architecture rather than framework defaults.
Routing front door for obsidian-second-brain — a self-rewriting Obsidian vault that evolves Karpathy's LLM-Wiki pattern. Every source REWRITES existing pages instead of appending: people updated, claims revised, contradictions reconciled, patterns synthesized automatically. 45 commands across 4 layers, background + 4 scheduled agents, 4 role presets, AI-first write validator. Cross-CLI: Claude Code, Codex CLI, Gemini CLI, OpenCode.
Produce and understand audio with OpenAI request-based audio APIs and audio-capable chat models, including text-to-speech, transcription, translation, multimodal audio input/output, model routing, prompt and performance direction, artifact custody, approval gates, and safety/rights review. Use for non-realtime OpenAI audio production; route continuous live voice agents to the separate realtime voice skill.
Caching strategies in front of AWS OpenSearch (Elasticsearch) or AWS Personalize — search, recommenders, multi-recommender pages, anon vs logged-in traffic. Covers ROI decision (TPS/minProvisionedTPS, Zipf, amplification), key design (canonicalisation, cohort vs user, solution-version pinning, bucketing), personalisation boundary (anon/logged split, fan-out coalescing), strategies (cache-aside, refresh-ahead, write-through, batch precompute, L1+L2), TTL (volatility, soft/hard, jitter, event-driven invalidation), stampede protection (single-flight, XFetch, stale-while-revalidate, circuit breaker), observability (hit-rate, cost-per-1k, cardinality drift, log-replay), defensive caching (negative, Bloom filter), and tier composition (LRU, ElastiCache Redis, CloudFront, OpenSearch request/filter cache). Triggers on cache hit rate, Personalize throttling, stampede, single-flight, L1/L2, ElastiCache sizing. Complements opensearch-function-scoring-algorithms.
Sets up and configures Hookdeck Outpost for outbound event delivery to customer endpoints. Use when sending webhooks to customers, building webhook delivery infrastructure, managing tenants and destinations with supported types (webhooks, Hookdeck Event Gateway, AWS SQS/Kinesis/S3, Azure Service Bus, GCP Pub/Sub, RabbitMQ, Kafka), or aligning topics and publishes. EventBridge support is tracked in GitHub issues.
PostgreSQL 17/18+ performance tuning and optimization. Covers async I/O configuration, query plan forensics, index strategies, autovacuum tuning, vector search optimization, connection pooling, declarative partitioning, and practical query patterns. Use when diagnosing slow queries, configuring async I/O, tuning autovacuum, optimizing vector indexes, analyzing execution plans with EXPLAIN BUFFERS, configuring PgBouncer or connection pooling, setting up table partitioning, implementing cursor pagination, or optimizing queue processing.
Comprehensive guide for PostgreSQL psql - the interactive terminal client for PostgreSQL. Use when connecting to PostgreSQL databases, executing queries, managing databases/tables, configuring connection options, formatting output, writing scripts, managing transactions, and using advanced psql features for database administration and development.
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Interview the operator and write the strategic layer of a product — vision, problem, users, scope, competitors, opportunities, open questions, glossary — into the `context/` of its node in the brain, never into the body repo. Manually triggered, last link of the discovery pipeline and the gate before specs.
Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, produces a content-addressed plan and materialises canonical Atlas Kanban cards by default (explicit taskmaster-file compatibility remains available). Use when user says "PRD", "product requirements", "I want to build", invokes /atlas, or wants task-driven development.
Prepare a Honcho change for a pull request to plastic-labs/honcho. Invoke before opening a PR, when drafting a PR body, when asked if a branch is PR-ready, or when filling the pull request template. Checks required tests and docs, then writes Description / Proofs / Fixes.
Discover external customer problems and product requirements from human stakeholders. Assess customer evidence before investing, or map who to talk to, ask questions that surface hidden assumptions, detect gaps in real time, resolve conflicts, and translate conversations into structured SDD specs. Phase 0 upstream of Spec-Driven Development. Also grill a PRD, interrogate a proposal, poke holes in a spec, or interview its author about an existing draft, one consequential question at a time. Do not use for personal-life discovery (daily-life-discovery), general research without product requirements (research-methodology), or implementation planning.
Drafting Python Enhancement Proposals (PEPs) — proposing a Python language feature, a standard library change, an interoperability standard, or an informational/process document for the Python community. Covers all three PEP types (Standards Track, Informational, Process): choosing the right type, scaffolding a valid reStructuredText pep-NNNN file, filling each required section to the acceptance bar, linting the headers, and navigating the sponsor / submission / Steering Council review process. Trigger on "write a PEP", "draft a PEP", "propose a Python feature", "create a Python Enhancement Proposal", "PEP template", or when someone is preparing a proposal for the Python Discourse or python-dev. Use it even if the user only says "PEP" or doesn't mention reStructuredText — the headers, sections, and process are exactly what trips PEP authors up.
Provides one-command project creation for React Native including project initialization, configuration, and template generation. Use when the user asks about creating React Native projects, needs to initialize a new React Native project, or generate React Native project structure.
Creates programmatic video with React via Remotion — compositions, sequences, and motion graphics animated with useCurrentFrame() and rendered to MP4. USE WHEN video, animation, motion graphics, video rendering, React video, render video, animate content, make a short, create animations, video overlay, explainer video, animated explainer, content to video, programmatic video. NOT FOR static images, diagrams, or illustrations (use Art), tight-cut filler removal from raw talking-head recordings (that is video editing, not motion graphics), or audio-only podcast cleaning (use AudioEditor).
Core mechanics of the Rerun Chunk Processing API (rerun.chunk) — LazyChunkStream pipelines, Chunk, lenses (MutateLens/DeriveLens/Selector), RrdReader, and writing optimized RRDs. Read BEFORE writing any ingestion/conversion/preprocessing code (convert an MCAP, build a recording from a dataset, preprocess an .rrd, port an old converter): it mandates reader+lens pipelines and steers away from hand-built chunks — no Chunk.from_columns for data a reader/lens can produce, no per-message rr.log, no manual pa.array assembly. Source-specific knowledge lives in the importer skills (rerun-mcap, rerun-urdf, rerun-parquet, rerun-mp4, rerun-lerobot); read rerun-data-model first to decide what the data should become
Run supervised multi-agent reviews with the revmux CLI, report or act on findings, and re-review fixes. Supports branches, commits, paths, fetched pull requests, visible overlay runs, review-fix loops, and issue or discussion triage with grounding, thesis, antithesis, and cost panels. Also analyzes archived rounds in self mode to tune local prompts and answers questions about profiles, lenses, task directories, output, exit codes, and archives. Use when the user says revmux, supervised review, multi-agent review, review with revmux, revmux a branch/commit/PR, show the review, triage an issue, is this worth doing, revmux self, tune revmux, or asks about revmux behavior.
Build, refine or reskin a short SaaS product film in Remotion, cut to the beat of its soundtrack, from the product's real screens, brand and copy. Use when the user wants a product demo, launch video, explainer or social reel of their software made in code; wants an existing product film changed, reskinned or critiqued; or has a product with no interface to record and needs schematic UI. Covers 16:9 and 9:16, b-roll under motion graphics, sound effects and checked renders. Not a live-action editor and not a screencast tool.
Design multi-touch outbound email sequences with personalized messaging, timing cadences, and conversion-aware copy for prospecting or re-engagement. Use when the user needs a coordinated sales campaign across several touches; use email-drafting for a single message or reply.
Use when a user wants to make their own comic, manga, BD, graphic novel or illustrated book with Scenario: a short personalized story from a photo or an idea, a branded or training comic, an album, or a book of hundreds of pages adapted from a text. Keywords: comic book, manga, webtoon, graphic novel, personalized comic, book adaptation, comic pages, speech balloons.
Generate a requirements-quality checklist for an OpenSpec change and run it against the proposal/design/tasks/delta — validating completeness, clarity, consistency, and testability BEFORE you approve the spec. Modeled on GitHub Spec-Kit's /checklist. Use when reviewing a spec at the human approval gate, or before launching implementation, to catch under-specified requirements early.
Surface-aware end-to-end verification of a change — determine whether it touches a FRONTEND surface (rendered UI) or an API/backend surface, then validate the right way. Frontend → chrome-devtools MCP (open the affected page, screenshot, confirm it renders, check console/network/accessibility). API → a Playwright request script that hits the affected endpoints and asserts status + response shape. Use after implementing a change, or in the harness Validate step, to confirm it actually works in the running app — not just that unit tests pass. Requires the chrome-devtools-mcp plugin (frontend) and/or Playwright (API); both are wired up by the kit installer.
Search and read the decompiled C# code of Space Engineers 1 to learn how the game works inside and to get exact signatures, method bodies, IL and content files. If the se-dev-game-book handbook is installed, read it first for how a system works overall and come here for the exact code.
Diagnose broken Splunk searches, reports, alerts, and dashboards from supplied evidence. Use when an existing search or saved object is empty, missing, wrong, inconsistent, invisible, not dispatching, not triggering, or not rendering and the user needs the first unsupported functional stage, the smallest next evidence, aligned read-only validation, and an exact authoring, governance, field, workflow, or performance handoff. Do not use for SPL, object authoring, implementation, optimization, configuration, mutation, or remediation.
Teaches agents to recognize and avoid security threats during normal activity. Covers phishing detection, credential protection, domain verification, and social engineering defense. Use when building or operating agents that access email, credential vaults, web browsers, or sensitive data.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
