Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Qdrant vector database integration patterns with LangChain4j. Store embeddings, similarity search, and vector management for Java applications. Use when implementing vector-based retrieval for RAG systems, semantic search, or recommendation engines.
Discover, configure, and manage Qodo Review Standards using managed tools through MCP or the CLI. Use to set up a skills/plugin repository for reviews, map review skills to target repositories, change skill scope or rules/steering mode, capture a convention as a rule, edit or deactivate rules, or triage suggestions. For reading and applying rules use qodo-get-rules; installing local coding-agent skills uses qodo-setup.
Android cryptography system audit (crypto audit): analyze AndroidKeyStore keys (aliases/algorithms/uses/hardware backing), audit Cipher/KeyInfo, and hook cryptographic call sites (intercept key aliases and uses with Frida). Trigger terms: Keystore, AndroidKeyStore, Cipher, KeyInfo, StrongBox, cryptography audit, crypto hook, key alias
Virtualization reverse engineering: VT-x/SVM, hypervisor detection, VMCS/EPT analysis, and partitioning and vdev semantics in Xen / QNX Hypervisor / Jailhouse / ACRN / Bao / Hyper-V·VMBus / XtratuM / LynxSecure / Quest-V. Trigger terms: hypervisor, VT-x, SVM, virtualization detection, EPT, Xen, grant table, event channel, Jailhouse, cell, ACRN, ivshmem, Bao, shmem_id, vdev, GPA/HPA, Hyper-V, VMBus, VSC, VSP, GPADL, SR-IOV, XtratuM, XM_CF, LynxSecure, Quest-V, sandbox kernel
Use when building charts, data visualisations, or dashboards with Recharts. Also use when integrating Recharts with HeroUI, reviewing chart components, or creating responsive chart containers. Generates Recharts charts styled with HeroUI v3 design tokens and Tailwind CSS v4.
Use when a recursive-mode requirement involves debugging a bug, test failure, or unexpected behavior. Insert Phase 1.5 between Phase 1 and Phase 2 to perform systematic root cause analysis before attempting any fixes. Trigger phrases: "debug", "investigate", "failing tests", "crash", "root cause".
Use when implementing any code in recursive-mode Phase 3. Enforces strict RED-GREEN-REFACTOR discipline with The Iron Law - no production code without a failing test first. Trigger phrases: "implement this", "add feature", "fix bug", "write a failing test", "TDD".
Reduce an unoptimized-query-oracle test failure log to the simplest possible reproduction case. Use when you have unoptimized-query-oracle*.log files from a failed roachtest and need to find the minimal SQL to reproduce the bug.
Put the real values back into an analysis that was produced from GREEN (placeholder) text — LOCALLY, using the user's own reversible map. Completes the confide round-trip (redact -> cloud-analyze the green -> rehydrate locally). Use when the user says "rehydrate", "restore real names", "unmask the analysis", "put the names back", "de-redact this output", "reverse the placeholders", or hands you an analysis full of [CONFIDE_PERSON_0001]/[CONFIDE_DATE_0002] plus a *.map.json. Runs only on the user's own map; the map never leaves the machine; nothing fetched or transmitted. Prints counts only — never echoes restored PII. Warns on placeholders not in the map (possible LLM hallucination).
Resolve evidence-backed `docs/follow-ups/*.md` through a bounded manual, Codex Scheduled task, or Claude Routine sweep. Use when project follow-ups should be reproduced before editing, handled by one isolated worker and branch per item, and published as independent ready-for-review pull requests without automatic merge. Do not use to invent intended behavior or merely record a newly discovered follow-up.
Use when diagnosing why a published video underperformed — reading a YouTube retention graph, comparing a weak video against a winner, or mapping audience drop-off points to script beats. For writing the next script, use storytelling-hooks or long-form-youtube.
Identifies root causes behind declining user retention with likely causes, supporting evidence, and fix experiments. Use when you observe a retention drop and need to systematically diagnose why users are leaving.
Use when reverse-engineering a binary or firmware — static triage + decompilation (Ghidra/IDA/Binary Ninja), dynamic instrumentation (GDB/Frida 17/angr), anti-reversing & packer bypass, OLLVM/VM deobfuscation, UEFI/BIOS RE & Secure Boot research, patch-diffing for n-days
How to author custom PostHog Review skills: the review perspectives, blind-spot checks, validation criteria, and resolution criteria that drive PostHog Review's automated PR reviews. Use when a user wants a new review perspective (a specialist lens on their PRs), a custom blind-spot sweep, their own validation bar for which findings get published, or their own bar for which review comments get implemented. Trigger on "create a PostHog Review perspective", "custom review perspective", "my own blind-spot check", "custom validation criteria", "custom resolution criteria", "tune what PostHog Review publishes", "tune what PostHog Review implements".
Review code for performance: complexity, database/query efficiency, I/O and network cost, memory and allocation behavior, concurrency contention, caching, and latency/throughput regressions. Cognitive-only atomic skill; output is a findings list.
Manuscript review and reader-retention diagnosis for Chinese web fiction. Use when the user wants a manuscript reviewed, plot holes checked, foreshadowing payoffs verified, character consistency audited, or satisfaction-beat density assessed, or wants to know "why reader retention drops / why this chapter loses readers". Produces a data-driven diagnostic report and actionable revision suggestions.
Author Roblox character animations (R15 or R6) headlessly in Blender from a JSON pose spec, verify them by rendering contact sheets and GIFs and match a reference pose. Use this whenever the user wants to make, generate, or automate a Roblox animation — a punch, swing, emote, idle, walk, death, tool action — or wants an animation built to match a reference pose, or asks to animate a .blend rig without opening Blender's UI. Also trigger when a Roblox animation "comes apart", limbs detach, a rig poses correctly in script but renders wrong, limbs pop or flip between frames, or a pose looks nothing like the reference.
Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user asks to improve an existing skill from recent runs, recurring failures, outdated sources, excessive bloat, changed platform behavior, or validated workflow feedback. Do not use to create a brand-new skill or to execute the business workflow itself.
Builds and manage membership sites and online courses — course structure, content delivery, pricing models, retention, community, and platform selection. Use when members keep canceling, course completion rates are low, unsure how to price a membership, drip content isn't engaging subscribers, need to pick a course platform, or struggling to structure a membership site. Do NOT use for webinar-based selling (use /sales-webinar), checkout and payment setup (use /sales-checkout), email marketing to members (use /sales-email-marketing), or SendPulse-specific help (use /sales-sendpulse). For Groove-specific help, use /sales-groove.
Smartlead platform help — campaigns, SmartSenders, SmartInfra, SmartAgents, SmartDialer, SmartProspect, SmartDelivery, warmup, API, integrations, agency/white-label. Use when Smartlead emails are landing in spam, campaigns have low reply rates, SmartSenders mailboxes keep getting flagged, warmup scores aren't improving, SmartAgents aren't personalizing well, SmartDialer connect rates are low, SmartDelivery tests show poor inbox placement, agency workspaces need restructuring, or the Smartlead API isn't syncing. Do NOT use for building prospect lists (use /sales-prospect-list), designing cadence strategy (use /sales-cadence), cross-platform deliverability (use /sales-deliverability), or multi-client agency architecture (use /sales-agency-outbound).
Detect Server-Side Template Injection (SSTI) vulnerabilities in a codebase using a three-phase approach: recon (find template rendering sites that use dynamic strings), batched verify (trace user input to those sites in parallel subagents, 3 candidates each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/ssti-results.md. Use when asked to find SSTI or template injection bugs.
Deep multi-reviewer code review for bugs, regressions, tests, standards, and whether the change meets its ticket. Dispatches specialist reviewer subagents in parallel, merges their findings into one report, checks the diff against the ticket's acceptance criteria, then performs the authorized follow-up or asks whether to report only, fix and push, or leave inline PR comments. Use before opening a PR, when asked for a thorough review, to scan a branch, or to review a PR.
Generate comprehensive scientific research-style documentation for completed coding projects. Use when the user requests project documentation, a technical breakdown, a study paper, a lecture document, or wants to understand everything about a project they just built. Triggers include phrases like "document this project," "create a study paper," "explain everything we did," "write up the full breakdown," "scientific documentation," or "I want to learn from this project." Produces formal Word documents (.docx) with academic structure, beginner-friendly explanations, and exhaustive code analysis.
Create web scraper scripts using Playwright. Use when the user wants to scrape a website, extract data from web pages, build a scraping pipeline, initialize a scraping project, or automate data collection from websites. Supports Python and Node.js ecosystems. Handles proxy configuration, stealth mode with patchright, and data export to CSV, JSON, or database.
【Internal suite skill · Users usually don’t need to call it directly in the full workflow; simply tell the orchestrator short-drama-director what you need, and it will route to this skill automatically】【漫剧老李 V7.5.0-SLIM suite · Subskill】Specialized engine for dramatic and everyday-scene storyboards (short-drama visual style): short-drama camera system + shot economy + restrained performance + five dimensions of within-segment continuity and five camera movement modes, converting original novels/scripts into concise storyboard scripts; **also produces storyboard images (★standard image asset): one multi-panel image per segment, split by seven action phases (wind-up/process/contact/apex/result/reaction/exit), with panel count determined by action complexity rather than mechanically using a nine-grid; exit frame = next segment’s entry frame; CLEAN_GRID clean version for image generation + optional technical annotation version**. **★ Must detect the I style lock image basis (live action/2D/3D/ink wash) and adapt face close-up angles accordingly—3D/photorealistic forbids the “close-up × straight-on eye-level” combination; use an angled side view instead (live action adheres to a 1/3 quota, 2D uses the same shot no more than twice consecutively)**. Trigger words: storyboard, text storyboard, film storyboard, generate storyboard, help me storyboard, director’s storyboard, shot script, storyboard, shot continuity, camera movement continuity, story board, storyboard image, panel chain, four-panel storyboard, four-grid storyboard, six-grid storyboard, nine-grid storyboard, 2×2 storyboard. This skill is part of a suite; the complete workflow starts with the orchestrator short-drama-director.
Build, adapt, and document apps that run inside Sealos Desktop using the Sealos app SDK. Use when creating a new Sealos app, integrating an existing web app into Sealos Desktop, wiring Sealos session data into business features, preparing local iframe-based debugging, or producing beginner-friendly Sealos app tutorials and starter implementations. Also triggers on “/sealos-app-builder”.
Deploy any GitHub project to Sealos Cloud in one command. Assesses readiness, generates Dockerfile, builds image, creates Sealos template, and deploys — fully automated. Use when user says "deploy to sealos", "deploy this project", "deploy to cloud", "deploy this repo", mentions Sealos deployment, wants to deploy a GitHub URL or local project to a cloud platform, or asks about one-click deployment. Also triggers on "/sealos-deploy".
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.