Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Python library polars-bio for genomic interval operations and bioinformatics file I/O on Polars DataFrames, built on Arrow and DataFusion. Covers overlap, nearest, merge, cluster, coverage, complement, subtract, count_overlaps, per-base pileup depth, and read/scan/write of BED, VCF, BAM, CRAM, SAM, GFF/GTF, FASTA, FASTQ, plus SQL queries over those files. Use when intersecting or merging genomic intervals in Polars. Use when reading or streaming large BED, VCF, or BAM files, including from S3, GCS, or Azure. Use when computing read depth from BAM or CRAM. Use when running SQL on genomic files. Use when migrating bioframe code to a faster alternative. Not for pandas-only workflows that do not use Polars or DataFusion.
Data file fetching and caching for geoscience applications. Download sample datasets with automatic caching, checksum verification, and multiple download sources. Use when the agent needs to: (1) Download datasets from URLs or DOIs, (2) Cache files locally with automatic verification, (3) Verify file integrity with SHA256/MD5 hashes, (4) Extract compressed archives (ZIP, TAR, GZIP), (5) Create data registries for reproducible workflows, (6) Fetch from Zenodo or other repositories.
Use when writing a social post on a topic or a reply to someone's post — X/Twitter, LinkedIn, Bluesky, Threads — and the obvious take is not good enough. Triggers include "reply to this post", "write a post about", "quote this", "tweet about", "my replies all sound the same", "what's a non-obvious take on", "build in public post", a pasted post with "what would you say to this", or a post URL. Do NOT use for analytical work like debugging, code review, or implementation tasks.
Write, execute, and optimize DAX queries and measures for Power BI semantic models using pbi-cli. Invoke this skill whenever the user mentions DAX, queries data in Power BI, writes calculations, creates measures, asks about EVALUATE, SUMMARIZECOLUMNS, CALCULATE, time intelligence, or wants to analyze/aggregate data from a semantic model. Also invoke when the user asks to run a query, test a formula, or check row counts. This skill contains critical guidance on passing DAX expressions via CLI arguments -- multi-line DAX (VAR/RETURN) requires special handling.
Run PR maintenance to completion automatically after an agent creates a PR or a draft PR becomes ready for review: keep polling CI and bot review with gh, repair failures and reply in Japanese in the same worktree, escalate design loops, and squash merge when safe, without waiting for a human to restart each poll cycle. Use right after an agent-created PR exists or transitions draft-to-ready. Do NOT use for human-authored PRs, and do NOT redefine repair/merge/escalation policy here (that lives in pr-maintainer).
[Beta] Session-start scan that surfaces relevant learnings, recent errors, and eval status before work begins. Bridges the outer loop back into the inner loop by making accumulated knowledge visible at task start. Activated via SessionStart hook or manually before major tasks.
Search the PRIDE Archive v3 REST API for proteomics datasets: discover projects by keyword + faceted filters (organism, instrument, disease, software), fetch project metadata, list and download RAW/PEAK/RESULT/FASTA files (with FTP/Aspera URLs), look up which projects mention a UniProt accession, and find similar projects. PRIDE v3 no longer exposes peptide/PSM-level identification endpoints — for spectrum-level data download the project's RESULT files. Use uniprot-protein-database for protein sequences; interpro-database for domain architecture.
Step-by-step problem solving with detailed explanations. Uses structured approach (Identify, Plan, Execute, Verify) for math, physics, chemistry, and CS problems. Can provide hints before solutions. Use when solving academic problems, working through practice questions, or learning problem-solving methods. Triggers - solve problem, step by step, show work, explain solution, how to solve, problem help.
Turn a one-sentence startup idea into a structured product brief with problem, audience, value proposition, 5-7 MVP features, 90-day metrics, risks, and a go-to-market snapshot. Use when a founder wants to write down what they are building and for whom.
Use when developing astrology/numerology apps, validating chart calculations (timezone/DST, quadrant handling), or producing psychology-first interpretations. Expert advisor (30+ years) catches common bugs (D026-D028) and defines accuracy/test standards. (project)
Creates Pull Requests for Prowler following the project template and conventions. Trigger: When working on pull request requirements or creation (PR template sections, PR title Conventional Commits check, changelog gate/no-changelog label), or when inspecting PR-related GitHub workflows like conventional-commit.yml, pr-check-changelog.yml, pr-conflict-checker.yml, labeler.yml, or CODEOWNERS.
Read and export a Photoshop (.psd) layer tree as JSON, including layer metadata (name, type, visibility, bbox) and detailed text style information. Use this skill whenever the user needs to analyze PSD structure, find specific layers (such as modals or buttons), or prepare the data needed for an HTML/CSS rebuild. Even for complex nested structures or precise text reproduction (font, color, spacing), this tool provides structured support.
Use when the user has a finished blog master draft and wants to publish it to multiple content platforms (知乎/掘金/CSDN/公众号 等) via the @wechatsync/cli tool. Handles pre-flight auth checks, platform selection, dry-run preview, and the actual sync. Do NOT use for writing, rewriting, compliance rewriting, or topic selection — this skill only publishes existing drafts as-is.
Python library for healthcare ML on EHR data: process MIMIC-III/IV, eICU, OMOP-CDM; encode medical codes (ICD, ATC, NDC); build patient-level datasets; train Transformer, RETAIN, GRASP, MedBERT for mortality, drug recommendation, readmission, diagnosis prediction. Alternatives: FIDDLE (preprocessing), clinical-longformer (clinical NLP), ehr-ml (embeddings).
Builds clinical deep-learning pipelines with PyHealth using its Dataset → Task → Model → Trainer → Metrics pattern. Covers loading MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14 and EHRShot data, defining prediction tasks (mortality, readmission, length of stay, drug recommendation, sleep staging, ICD coding, EEG events), models such as Transformer, RETAIN, GAMENet, SafeDrug and StageNet, training with Trainer, and ICD/ATC/NDC/RxNorm code lookup and cross-mapping. Use when building a clinical prediction model on EHR data. Use when working with MIMIC or eICU datasets. Use when recommending drugs or staging sleep from signals. Use when mapping medical codes between ICD, ATC, NDC or RxNorm. Not for generic PyTorch on tabular data.
Hardware-agnostic Python liquid-handler library: portable scripts run on Hamilton STAR, Tecan Freedom EVO, Opentrons OT-2, or a simulator without vendor lock-in. For protocol automation, method dev, plate reformatting, serial dilutions, and Python lab workflows.
Develop and review PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Use for PyLabRobot protocols or API questions; keep physical execution behind an explicit operator safety gate.
Python framework for single- and multi-objective optimization with evolutionary algorithms. Define vectorized objectives and constraints; solve with NSGA-II, NSGA-III, MOEA/D, GAs, or differential evolution. Analyze Pareto fronts, visualize trade-offs, customize operators and callbacks. For engineering design, hyperparameter search, and conflicting objectives. Alternatives: scipy.optimize (single-objective, gradient), platypus, jMetalPy (Java).
Complete mass spectrometry analysis platform. Use for proteomics and metabolomics workflows—feature detection, peptide/protein identification, label-free and isobaric quantification, adduct/accurate-mass annotation, and complex LC-MS/MS pipelines. Supports extensive file formats and algorithms. For simple spectral comparison and small-molecule library matching use matchms.
Three.js materials in R3F, built-in materials (Standard, Physical, Basic, etc.), ShaderMaterial with custom GLSL, uniforms binding and animation, and material properties. Use when choosing materials, creating custom shaders, or binding dynamic uniforms.
Frida script generation methodology: target characteristics → template selection → rewriting → verification. Independent of execution instrumentation (re-frida). Trigger words: generate Frida script, write hook script, how to write a frida script, write a hook, script generation.
Cross-platform kernel reversing: Windows drivers (.sys/IRP/SSDT), Linux kernel modules (.ko/ET_REL/LKM/rootkit), macOS KEXT and System Extension/DriverKit, Android GKI/vendor modules, seL4 (capability system), Fuchsia/Zircon (handle model + DFv2 user-mode driver framework), FreeBSD (linker sets/SYSINIT/KLD), illumos/Solaris (DDI/DKI, dev_ops/cb_ops), OpenBSD (KARL/autoconf/pledge), NetBSD (on-demand module autoloading), Genode (component tree/session/quota), MINIX 3 (RS self-healing/grants/live update), Plan 9 (namespace/9P), HelenOS (fibril/DDF), Redox (scheme), Haiku (device_node/on-demand discovery), z/OS (TCB·SRB/cross-memory), IBM i (single-level storage), OpenVMS (AST), Unikraft·MirageOS (unikernel), HIC (same-privilege-level MMU-isolated driver model / capability / physical sandbox / self-describing modules / entry-page IPC). Triggers: kernel, driver, .sys, .ko, LKM, kext, dext, rootkit, kernel module, IRP, GKI, kernel extension, seL4, capability, CSpace, CNode, capDL, CAmkES, MCS, Fuchsia, Zircon, handle, DFv2, driver host, FIDL, FreeBSD, KLD, SYSINIT, linker set, illumos, Solaris, DDI, dev_ops, cb_ops, OpenBSD, KARL, autoconf, pledge, unveil, NetBSD, kmod, GENODE, session, quota, MINIX, RS, grant, 9P, Plan 9, namespace, HelenOS, fibril, DDF, Redox, scheme, Haiku, device_node, z/OS, TCB, SRB, cross-memory, IBM i, single-level storage, OpenVMS, AST, $QIO, unikernel, Unikraft, MirageOS. English triggers: kernel module, driver reversing, LKM, kext, rootkit, GKI, seL4, capability system, capDL, Fuchsia, Zircon, handle, driver framework, FIDL, FreeBSD, KLD, SYSINIT, linker set, illumos, Solaris, DDI, dev_ops, cb_ops, OpenBSD, KARL, autoconf, pledge, NetBSD, kmod, Genode, session, quota, MINIX, reincarnation server, grant, 9P, Plan 9, namespace, HelenOS, fibril, DDF, Redox, scheme, Haiku, device node, z/OS, TCB, SRB, cross-memory, IBM i, single-level storage, OpenVMS, AST, QIO, unikernel, Unikraft, MirageOS
Keep a repository's README for the person deciding whether and how to use it, its AGENTS.md (or a CLAUDE.md read through it) for the agent working inside it, and the manifests hosts read first (package.json, plugin and marketplace files, agents/openai.yaml) on the repository's one name: audit them with the bundled script, then move each line to the file whose reader needs it and fix each disagreeing manifest. Use when writing, rewriting or reviewing a README or an AGENTS.md, when an agent-only command shows up in a README or marketing copy in an agent guide, when deciding which file a section belongs in, or after a rename. Not for contracts, ledgers, changelogs or release notes.
Guides Redis usage including data structures (strings, hashes, lists, sets, sorted sets), caching patterns, pub/sub, persistence (RDB/AOF), clustering, and Lua scripting. Use when the user needs to implement caching, session storage, rate limiting, queues, or any Redis-based data layer.
Prevents citation hallucination in academic writing. Invoke when: finding papers to support a specific claim; verifying/checking/auditing existing citations or DOIs; confirming whether a paper actually says what the user claims it says ('is that what the paper says?', 'did they actually show X?'); adding a citation by describing a paper ('add a citation for the paper where X'); running a pre-submission reference sweep. Do NOT invoke for: formatting references in APA/IEEE style, general topic explanations, citation style questions, or prose editing. Selects Quick Screen (seconds per paper) or Full Audit (source-depth claim check) automatically.
Use when the user wants to collect research material for an article or topic by gathering YouTube videos and web articles into a NotebookLM notebook, then running analysis queries and saving results as markdown. Best for "收集素材"、"给我找这个话题的相关视频和文章"、"整理成 NotebookLM 分析" type requests. Combines yt-dlp YouTube search, NotebookLM `nlm` CLI research, and markdown report output.
Interactive research orchestrator. Scopes a high-level research goal through a short interview, presents an approvable nested plan tree of sub-questions ("unknown unknowns"), then fans out parallel subagents (with per-branch model tiering for cost) and rolls up their findings live into a written report plus executive summary. Use when the user wants to research a broad or fuzzy topic, explore unknown unknowns, run a deep multi-angle investigation, or mentions fan-out research, a research plan, or a research report
Gate on identity questions to the user. Before any "who is X?" (or role / relationship question) reaches the user, exhaust the brain's lookup chain: think → search + page read → mounted sources → timeline/graph → web. If escalation survives the chain, ask WITH a hypothesis, never a bare unknown. Also owns the no-placeholders-at-ingest rule: pages created during bulk ingestion get their relationship/role resolved immediately.
Unified multi-dimensional code review with automated fix orchestration. Routes to session-based (git changes), module-based (path patterns), or fix mode. Triggers on "workflow:review-cycle", "workflow:review-session-cycle", "workflow:review-module-cycle", "workflow:review-cycle-fix".
Review a Remotion video with AI vision. Starts with a cheap local check of rendered still frames, then has TwelveLabs watch the full render and score it against a JSON rubric (pacing, composition, text legibility, audio sync and more) with timestamped fixes, applies the fixes and re-reviews. The feedback loop that closes the production circle
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.