Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Get PostHog data into a canvas correctly: the host-injected `ph` SDK (loadInsight, query, capture, state, connectors, openExternal, navigate), the data hierarchy (saved insights first, typed query nodes second, inline HogQL last), verifiability (insight-backed metrics link their saved insight in PostHog; ad-hoc queries expose the exact query that ran), per-insight-type result shapes, progressive per-query loading, date-range wiring, live third-party data through the viewer's own connections (ph.connectors), and event capture from a canvas. Use whenever a canvas shows metrics, charts, tables, any PostHog data, or data from GitHub or an MCP server, or needs to send analytics events.
BufferGeometry creation, built-in geometries, custom geometry with buffer attributes, instanced meshes for rendering thousands of objects, and geometry manipulation. Use when creating custom shapes, optimizing with instancing, or working with vertex data directly.
Guides use of RDKit (Python) for reading and writing SMILES, MOL/SDF, and InChI, computing descriptors (MW, LogP, TPSA), generating Morgan/MACCS/atom-pair fingerprints, running SMARTS substructure searches, applying reaction SMARTS, and building 2D/3D coordinates with ETKDG. Use when parsing or sanitizing molecules that fail default sanitization, calculating Tanimoto similarity or clustering compounds, filtering libraries by substructure, embedding and optimizing conformers, or computing Murcko scaffolds and molecule hashes. Use when fine-grained control over sanitization or algorithms is needed. For simpler standard workflows, use datamol instead, which wraps RDKit.
Automotive reverse engineering: CAN buses, ECU firmware, AUTOSAR Classic (RTE/runnable/BSW) and Adaptive (Execution Management/manifest). Trigger terms: automotive, CAN, ECU, in-vehicle, OBD, UDS, AUTOSAR, RTE, runnable, SWC, BSW, E_OS_ACCESS, Adaptive, ARA, Execution Management, Function Group, Machine State, Execution Manifest
Use when recursive-mode work may benefit from delegated audit, review, or bounded implementation support. This skill prioritizes analyst, planner, code-reviewer, memory-auditor, tester, and implementer roles, with mandatory self-audit fallback when subagents are unavailable.
Residual re-identification RISK CHECK on text you have ALREADY redacted (defensive, dual-use). Use when the user asks to "check residual re-id risk", "red-team my redaction", "what can an attacker still infer", "is this safe to share", or assess "re-identification risk" after anonymizing. Re-runs the CONFIDE detectors on the redacted output to surface surviving identifiers (singling-out), checks multiple files for linkability, and optionally probes a local model for still-inferable attribute CATEGORIES (inference) — mapped to GDPR Art-29. Reports risk categories/counts only, never a re-identification recipe. Pairs with confide:anon (run AFTER redacting).
Redis database expert for caching, data structures, Pub/Sub, Streams, Lua scripting, and performance optimization using Bun.redis native client. Use when working with Redis, caching strategies, key-value stores, real-time data, vector search, or document databases. Works alongside bun-expert skill.
Cut a software release and maintain a tiered compatibility policy. Use when the user wants to release, ship a version, bump the version, tag a release, write a changelog, or update COMPATIBILITY. Config-driven via release.config.json; bumps version files, runs a readiness gate, updates COMPATIBILITY.md tiers and deprecations, tags (→ release workflow), and reports closed issues. Teaches the underlying standards as it runs.
Mechanism-level read path for a remindb MCP server — MemoryTree (orient), MemorySearch/MemoryFetch/MemoryFetchBatch (look up), MemoryDelta/MemoryDiff (resync), MemoryRelated (traverse), MemoryStats/MemoryHistory (inspect), passive remindb:// resources. Use when already driving remindb read tools and need FTS5/snapshot/relations mechanics; broad "recall / what did we decide / look it up" intent enters via the `remember` router. Pair with `memorize` for writes.
Create evidence-backed repository intent docs for AI coding agents, including certainty levels, evidence anchors, open questions, and review workflow. Trigger on document repo intent, REPO_INTENT.md, or what this repo is for. Do NOT use for ordinary README polishing.
Audit whether a result can actually be reproduced from the available code, data, configs, and documentation. Use before trusting a benchmark claim or releasing your own work. Use for replication, code release checks, paper artifact sanity checks, lab handoffs, catching missing seeds/configs/data before results are cited, or whenever "works on my machine" is a risk. If the user wants to plan what to include in a public artifact package, use artifact-release-packager instead; this skill's job is to test whether reproduction is possible and where it breaks.
Retire a machine the user no longer uses, such as an old VPS: take stock of what is still on it and what still points to it, save what the user wants to keep, disconnect it from the user's accounts and other machines, provide the provider's deletion step, and record the retirement where the user keeps notes on the machine. Use when the user wants to shut down, delete, clean up, or replace a server or another machine set up with /set-up-machine.
Thoroughly improve code quality by requesting a review from a sub-agent after completing tasks requiring code editing, before returning the conversation turn to the user. Use for any task that edits code or configuration. Read this skill before starting edits, and after completing the requested changes run an isolated sub-agent review loop before returning the final response.
Only use when the user explicitly invokes /review-plan (or $review-plan in Codex). Never auto-invoke. Rigorously review a pre-implementation or work plan from multiple independent review perspectives (review subagents if a delegation mechanism is available), running at least 3 cycles of review → validity check → adoption decision → proposal to reflect adopted findings in the plan document. Do not directly edit the plan document itself or implement source code; present revision proposals in chat.
Review user experience and interface design using Nielsen's heuristics, WCAG 2.1 accessibility guidelines, keyboard and screen reader audit, user flow analysis, cognitive load assessment, and form usability evaluation. Use when conducting a usability review before release, assessing WCAG 2.1 accessibility compliance, evaluating user flows for efficiency, reviewing form design, or performing a heuristic evaluation of an existing interface.
Verify assumptions before implementing large or risky changes to APIs, provider data, billing, pricing, quotas, or defaults. Use when a mistake could affect customers or the user asks if a change is safe to ship. Checks real-world impact beyond passing tests.
Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and tautomer ensembles, docking and analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflows, and related small-molecule or protein modeling tasks. Ideal for programmatic batch screening, multi-step chemistry pipelines, and workflows that would otherwise require maintaining local HPC/GPU infrastructure.
Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan. Use when the user asks to make a new skill from real run history, extract a reusable workflow from conversation/logs/files, summarize lessons into a new skill, or produce a plan before writing files. Do not use to upgrade an existing skill or to execute the business workflow itself.
Make or audit a SaaS subscription pricing and packaging decision: buyer, value metric, tiers, limits, trials, seats or usage, enterprise path, unit economics, trust constraints, and validation. Use when the primary artifact is what to charge and package. Do not use for billing implementation, entitlement state, listing/interface copy, broad market research, or an already-approved price migration.
Manages outbound sequences in Apollo.io — create, configure, optimize deliverability, and analyze performance. Use when Apollo emails are going to spam, sequence open rates are low, A/B tests aren't producing clear winners, mailboxes keep getting throttled, sequence stats don't look right, or emails just aren't sending. Do NOT use for designing cadence strategy and content (use /sales-cadence), general Apollo platform help (use /sales-apollo), or non-Apollo sequence tools (use /email-sequence).
Chatbot marketing and conversational automation — building chatbot flows, multichannel messaging (WhatsApp, Telegram, Facebook, Instagram, Viber, live chat), lead qualification bots, FAQ bots, and handoff to human agents. Use when website visitors leaving without engaging, WhatsApp or Telegram leads not getting qualified, bot flow feels broken or confusing, leads dropping off before reaching a human agent, or not sure how to automate conversations for sales. Do NOT use for live chat widget setup without bots (use /sales-live-chat), email sequences (use /sales-cadence), or SMS campaigns without conversational flow (use /sales-sms-marketing). For SendPulse-specific help, use /sales-sendpulse. For SWAI-specific help, use /sales-swai.
Email marketing for opt-in subscribers — broadcasts, nurture sequences, automation, segmentation, and list management. Use when open or click rates are underperforming, subscribers aren't engaging after signup, you need a welcome sequence but don't know where to start, your list isn't segmented and everything goes to everyone, or you're unsure which email marketing platform to pick. Do NOT use for cold outbound email (use /sales-cadence), email deliverability/SPF/DKIM (use /sales-deliverability), transactional email (use /sales-transactional-email), connecting tools to CRM (use /sales-integration), or platform-specific config — use the dedicated platform skill instead (e.g., /sales-mailchimp, /sales-klaviyo, /sales-activecampaign, /sales-omnisend, /sales-brevo, /sales-kit, /sales-swai, etc.).
Use when the user is working a B2B SaaS deal from qualified opportunity to closed-won — preparing discovery calls, structuring demos or POCs, handling a specific objection, qualifying with MEDDIC/MEDDPICC/SPICED, building mutual action plans, navigating negotiation or procurement, or reviewing pipeline health, forecast accuracy, and deal velocity. Not for finding or prospecting new leads (use prospecting) or upstream positioning (use product-position).
Use when the user asks to create, scaffold, bootstrap, or add a new NestJS application or service — standalone or as a new app inside an Nx monorepo — including requests phrased as "make/create a new Nest app/service". Applies whenever the new app needs pino logging, a global exception filter + unified API response interceptor, this author's ESLint/Vitest/pre-commit/pre-push conventions, and baseline Dockerfile/docker-compose/Makefile/.env.example deployment files wired up.
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.