Skills
100,696 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Train custom TTS voices for Piper (ONNX format) using fine-tuning or from-scratch approaches. Use when creating new synthetic voices, fine-tuning existing Piper checkpoints, preparing audio datasets for TTS training, or deploying voice models to devices like Raspberry Pi or Home Assistant. Covers dataset preparation, Whisper-based validation, training configuration, and ONNX export.
Use when operating Ultralytics Platform from a terminal or script with the ul cloud CLI (ul cloud RESOURCE OPERATION key=value, PyPI package ultralytics-platform) — listing, creating, updating, cloning, or moving projects, datasets, and models; inspecting dataset images, statistics, metadata, duplicates, and similar images; starting and monitoring cloud training runs; per-image model validation analysis; downloading weights; exports, deployments, uploads, trash and restore, storage integrations, and account usage, storage, and billing; and building Agents (YOLO, LLM, gate, and alert workflows). For the Platform web UI or local yolo commands, see yolo; for choosing what to train and how to improve it, see yolo-training and yolo-tuning.
Docs-PM decision support for the "Write the docs" authoring process — makes audience, stage, and cross-cutting scope calls during the Frame and Shape stages (including cross-repo product lookup via universe when accessible, else the public OSS path), and helps decide when a docs question needs to self-serve vs. escalate to a docs PM. Use when framing a new docs page or launch, deciding what product stage or audience a feature targets, judging whether a docs question needs PM sign-off, or confirming which product repos a launch spans.
Use whenever adding, modifying, or reviewing any Copilot, agent, LLM, AI, tool, permission, sandbox, MCP, model, telemetry, feature-gate, setting, configuration, or enterprise control—especially anything an organization or administrator may need to manage. Start here to decide whether it belongs in runtime managed settings, a typed SDK contract, VS Code configuration policy, extension policy, or a split implementation. Run on every new Copilot/agent/LLM control and ANY change that adds a `policy:` field.
Use the configured PowerPoint MCP server to inspect or edit presentations on Windows. Covers session safety, live tool discovery, saving, and visual verification; not general presentation design. Triggers: PowerPoint MCP, presentation tools, edit a PowerPoint deck.
Pull every meal you ever logged out of MyFitnessPal — per-food CSV, agent-shaped trends, and a local SQLite store. Trigger phrases: `what did I eat this week`, `export my food diary`, `find every time I logged X`, `top foods driving my protein`, `am I hitting my calorie streak`, `use myfitnesspal`, `run myfitnesspal`.
Use when creating an approachable, self-contained HTML review aid for a pull request; explaining what changed, why it matters, how it works, and how it fits into the broader system; turning PR diffs, commits, tests, and architecture context into a local `.pr-review/` HTML page for reviewers; or helping reviewers understand complex code changes without dumping the full diff.
How to write, test, and deploy an app with Prisma Composer (`@prisma/composer`): declare services with `compute()` and typed dependencies, define RPC contracts, compose Modules, declare the service input (config and secrets as one schema, read back with `input()`), compose the ready-made cron/storage/streams Modules, provision a raw S3-compatible object-store bucket with `bucket()`, find extensions (npm packages named `prisma-composer-*`), test with `mockService`/`bootstrapService`, run the whole app locally with `prisma-composer dev` and tail its logs with `prisma-composer log`, and deploy with `prisma-composer deploy` (stages, destroy). Use when building a Prisma App, wiring a service dependency, adding a Postgres database, adding scheduled jobs / blob storage / event streams / a raw bucket, writing tests for composed services, running an app locally, reading its logs, or deploying/tearing down an environment. Triggers on "prisma composer", "@prisma/composer", "prisma app", "compute()", "service.load()", "module()", "contract()", "mockService", "bootstrapService", "prisma-composer dev", "prisma-composer log", "prisma-composer deploy", "--stage", "--fresh", "--tail", "prisma-composer destroy", "prisma-composer-", "bucket()".
Systematic problem-solving techniques for stuck-ness. Techniques: simplification cascade (complexity spirals), collision-zone thinking (innovation blocks), meta-pattern recognition (recurring issues), inversion exercise (assumption constraints), scale game (uncertainty). Actions: simplify, analyze, recognize patterns, invert assumptions, scale thinking. Keywords: problem solving, complexity spiral, innovation block, stuck, simplification, meta-pattern, assumption inversion, scale uncertainty, breakthrough thinking, root cause, systematic analysis, Microsoft Amplifier, debugging approach, creative solution. Use when: complexity spiraling, hitting innovation blocks, seeing recurring patterns, constrained by assumptions, uncertain about scale, generally stuck on problems.
Maintain `*-skills` README standards and checklist-style roadmap docs through one canonical maintenance entrypoint. Use when a repo needs profile-aware README maintenance, checklist roadmap validation or migration, or a bounded audit-first doc workflow with Markdown and JSON reporting.
Generates project context and codebase documentation for AI agents. Creates `.agents/` directory with project overview and deep codebase analysis (architecture, conventions, testing, integrations, checklist, workflows, features when vertical slicing detected, review). Use when starting work on a project, onboarding to an existing codebase, generating project documentation for agents, mapping codebase patterns, or incrementally refreshing the index from recent git changes. Triggers: "initialize .agents", "setup project index", "index project", "map codebase", "analyze codebase", "project overview", "codebase summary", "onboarding to this repo", "integrate feedback", "sync knowledge", "refresh codebase", "sync codebase", "patch index". Not for feature work, Obsidian session notes, or dev tooling setup like prettier or eslint.
Convert code projects into an Obsidian knowledge base. Activates when the user mentions obsidian, project documentation, knowledge base, analyzing a project, or converting a project. [After activation, you must]: 1. First read this SKILL.md file in full 2. Understand the AI writing rules (default to 00_Inbox/AI/, append-only, unified Schema) 3. Execute STEP 0: use AskUserQuestion to ask the user for confirmation 4. Start STEP 1 project scanning only after user confirmation 5. Strictly follow the order STEP 0 → 1 → 2 → 3 → 4 [Prohibited actions]: - Do not start analyzing a project without reading SKILL.md - Do not skip STEP 0 user confirmation - Do not create directly in 30_Resources (go to 00_Inbox/AI/ first) - Do not decide the output location on your own
Pytest testing standards emphasizing the AAA pattern, fixtures, and parametrize. Use when writing or reviewing Python tests with pytest, including Django tests. Covers fixture organization, database access patterns, API testing, and mock clients. Do NOT use for: JavaScript/TypeScript tests, unittest-style tests, or non-pytest frameworks.
Memory-safe Python script patterns for long-running processes under systemd MemoryMax constraints. Covers allocator purge (mimalloc/glibc malloc_trim), HTTP response lifecycle, DataFrame cleanup, thread-local connection reuse, and periodic GC cadence. Battle-tested through 5 OOM optimization cycles on production GPU workstations. Use this skill proactively whenever writing or reviewing Python scripts that: run under systemd with MemoryMax, process data in loops (downloads, ETL, backfill), use ThreadPoolExecutor, or make repeated HTTP requests. Also use when diagnosing OOM kills, RSS creep, or fd exhaustion in Python services. TRIGGERS - memory optimization, OOM prevention, RSS reduction, malloc_trim, systemd MemoryMax, memory leak, allocator purge, memory-safe script, RSS creep, fd exhaustion, SIGKILL status 9, MemoryHigh, glibc arena, mimalloc purge, requests memory leak, ThreadPoolExecutor cleanup.
Read a customer's live Langfuse traces, sessions, and scores via the Langfuse MCP server, pattern-match against a known-failure catalog, and write a findings report split into Ratel-flavored opportunities and stack-agnostic low-hanging fruit. Use to scan the dashboard, dig into failures, review recent sessions or the partner's traces, audit their observability, see what the agent's doing wrong, or `/ratel-langfuse-analyze`. Writes to <repo>/.ratel/ (accumulates); fails fast if MCP is down, honest-skips clean data, never edits code. Follow-up to /ratel-langfuse-integrate, reached after /ratel-observability-assessment picks Langfuse.
Reverse engineering modern consoles and retro platforms: Switch NSO/NPDM containers and encrypted partitions, PS4/PS5 ORBIS structures, SDK library fingerprints; retro ROM headers, cartridge formats, saves, and Cheat codes. Trigger terms: console reverse engineering, Switch, NSO, NPDM, PS4, PS5, ORBIS, Xbox, retro, ROM, NES, GBA, emulator, Cheat.
Crash and vulnerability sample analysis: deterministic reproduction, ASAN/UBSAN report interpretation, input minimization (afl-tmin/cmin), gdb backtrace localization, rr recording and replay, and PoC generation. Trigger terms: crash, ASAN, UBSAN, undefined behavior, UAF, heap overflow, out-of-bounds, segmentation fault, segfault, core dump, PoC, vulnerability analysis, crash analysis.
Electron desktop app reverse engineering: asar unpacking, main/renderer process JS, V8 bytecode (.jsc) boundaries, CDP dynamic debugging, and anti-debugging countermeasures. Triggers: Electron, asar, desktop app reverse engineering, .jsc, V8 snapshot, CDP, ELECTRON_RUN_AS_NODE, devtools detection.
Coverage-guided fuzzing: AFL++/libFuzzer/honggfuzz, instrumentation and corpus initialization, afl-fuzz runtime parameters, coverage (afl-cov), dictionaries/structured inputs. Trigger terms: fuzz, fuzzing, AFL, afl-fuzz, libFuzzer, honggfuzz, coverage, corpus, dictionary, vulnerability hunting.
Managed code reverse-engineering gateway. Orchestration: identify runtime → decompile → deobfuscate → route malware scenarios to [[re-malware]]. Subskills: [[re-dotnet]] [[re-java]] [[re-script-deob]] [[re-wasm]] [[re-ai-triage]] → [[re-ai-model]] [[re-blockchain]] [[re-python]]、[[re-browser-ext]]、[[re-electron]]、[[re-javacard]]. Trigger terms: .NET, dnSpy, ILSpy, Java, jar, bytecode, PowerShell obfuscation, VBA macro, JS deobfuscation, managed code.
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.