Productivity
Productivity agent skills automate everyday work: task management, email drafting, calendars, note-taking systems, and personal workflows. Each is a small SKILL.md file your AI agent applies automatically when your request matches what the skill does.
-
ndpvt-web Skill A Mapreduce Executing Wide SearchExecute large-scale breadth-oriented search and retrieval tasks using the A-MapReduce pattern: decompose a wide query into a task matrix, dispatch parallel map agents for independent retrieval, then reduce partial results into a unified structured table. Triggers: 'find all X that match Y across a large set', 'build a comparison table of N items', 'search for every instance of X', 'collect attributes for a list of entities', 'wide search across many sources', 'gather structured data on hundreds of items'.
-
pku-yuangroup Bundle Bio Single Cell Cell CommunicationInfers ligand-receptor cell-cell communication from scRNA-seq with a consensus-first workflow (LIANA), plus CellPhoneDB specificity tests, CellChat pathway probabilities, and NicheNet downstream ligand-activity. Use when ranking ligand-receptor interactions between cell types, comparing communication across conditions, asking which ligand drives a receiver response, or deciding which CCC method and resource to trust.
-
pku-yuangroup Bundle Bio Crispr Screens Bagel EssentialityIdentifies essential genes from CRISPR-Cas9 fitness screens using BAGEL2 (Kim & Hart 2021 Genome Med), a Bayesian classifier scoring per-gene Bayes Factors via log-likelihood ratios over per-sgRNA fold changes, calibrated against CEGv2 core-essentials (Hart 2017 G3, ~684 genes) and NEGv1 non-essentials (Hart 2014, ~927 genes). Covers the fc + bf + pr workflow, the linear-extrapolation improvement over BAGEL1 truncation, multi-target off-target correction, tumor-suppressor sensitivity (BAGEL2 detects enrichment), and BF calibration (BF >6 ≈ 90% posterior per Hart 2017; ~5% FDR by BAGEL convention). Use when classifying essential vs non-essential genes, calibrating BAGEL2 thresholds against PR curves, identifying tumor suppressors alongside essentials, comparing BAGEL2 hits to MAGeCK / drugZ, or generating publication-quality essentiality calls.
-
pku-yuangroup Bundle Bio Metabolomics Msdial PreprocessingRuns the MS-DIAL preprocessing workflow (peak picking, MS2Dec spectral deconvolution, alignment, gap-filling) and imports the alignment-result table into R or Python with honest filtering. Use when preprocessing LC-MS DDA/DIA (SWATH) raw data with MS-DIAL, deciding MS-DIAL vs XCMS, configuring the MsdialConsoleApp console run, or parsing an MS-DIAL export into a clean feature matrix. For programmatic R peak detection and the feature-table-as-artifact framing see metabolomics/xcms-preprocessing; for lipid annotation mode see metabolomics/lipidomics; for MSI-level confidence honesty see metabolomics/metabolite-annotation; for drift correction and QC see metabolomics/normalization-qc.
-
pku-yuangroup Bundle Bio Workflow Management Cwl WorkflowsAuthors portable, strongly-typed bioinformatics pipelines in the Common Workflow Language (CWL v1.2) as CommandLineTool/Workflow/ExpressionTool documents, validated with cwltool and run at scale on Toil/Arvados/Calrissian. Use when deciding CWL (portability/provenance/regulated) vs Nextflow/WDL/Snakemake; declaring secondaryFiles for indexed companions (.bai/.fai/.dict/.tbi and the caret rule); putting resources/containers under requirements (must-hold) vs hints (advisory) to avoid silent OOM; choosing scatterMethod (dotproduct vs flat_/nested_crossproduct); preferring $(...) parameter refs over ${...} JavaScript for portability; pinning DockerRequirement images; or emitting a CWLProv provenance object for audited/clinical settings.
-
pku-yuangroup Bundle Bio Virtual ScreeningPerforms structure-based virtual screening using AutoDock Vina, SMINA, GNINA (CNN scoring), and DiffDock-L hybrid workflows with explicit choice rules across rigid vs flexible docking, cross-docking vs self-docking, binding-site detection (P2Rank, fpocket), receptor preparation (PDB2PQR, PROPKA), ligand preparation (meeko, OpenBabel), and ultralarge-library screening (ZINC22, Enamine REAL). Use when screening chemical libraries against a protein target to find candidate binders, ranking docking poses, or selecting a docking workflow for a specific scenario.
-
pku-yuangroup Bundle Bio Rna Quantification Tximport WorkflowImport transcript-level quantifications from Salmon/kallisto/RSEM into R for gene-level analysis with DESeq2/edgeR using tximport or tximeta. Use when summarizing transcript abundances to gene counts with the correct length offset, choosing a countsFromAbundance mode (full-length vs 3'-tag vs DTU), resolving transcript-ID version mismatches, or handing off to DESeq2/edgeR without double-applying the offset.
-
revfactory Bundle Deliverability OptimizationEmail deliverability optimization skill used by the Editor-in-Chief and analyst agents. Provides spam filter avoidance, technical authentication, content filtering rules, and list hygiene management methodologies. Use for 'deliverability,' 'spam filters,' 'email authentication,' 'send optimization,' and similar requests.
-
yigityildiz0 Bundle K MemLocal-first, privacy-preserving working memory for recurring people, projects, terms, preferences, decisions, and task context. Use when the user asks to remember, recall, initialize or repair project memory, decode shorthand, migrate an existing memory system, or run /k-mem. Supports Codex, ChatGPT Desktop, Claude Code, and OpenCode without silently scanning private services. Turkish triggers: kalıcı bilgi veya karar kaydı, yerel hafıza, geçmiş bağlamı getir ve güncelle.
-
yigityildiz0 Bundle LearnUse this skill when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's.
-
yigityildiz0 Skill CustomizeReusable-instruction customization skill. Use when Codex should update an existing skill, template, or workflow so future outputs inherit the user's.
-
yigityildiz0 Bundle Hatch PetCreate, repair, validate, visually QA, and package Codex-compatible animated pets and spritesheets from character art, generated images, concepts, company brands, or references. Use only when the user explicitly asks for the hatch-pet workflow; otherwise prefer the installed Work Pets skills. Turkish triggers: Hatch pet oluştur veya onar, Codex masaüstü evcil hayvanı, pet durumunu kontrol et.
-
yigityildiz0 Bundle Hire HelpHelp find and book a service provider for a task — cleaning, handyman, moving, assembly, yard work, errands, etc. Searches TaskRabbit, Handy, Thumbtack, and.
-
yigityildiz0 Skill Zoom PluginMeeting-workflow umbrella skill. Use when Codex should turn Zoom-style meeting artifacts into prep notes, transcript summaries, or follow-up actions.
-
yigityildiz0 Bundle Call To BookMake a phone call to book an appointment or reservation. Checks calendar first, gets explicit consent before dialing, discloses AI identity on the call, and.
-
yigityildiz0 Bundle Meeting PrepResearches meeting attendees and their companies before any meeting using real-time web data. Surfaces roles, recent activity, company context, and talking.
-
yigityildiz0 Skill Nimble CrawlReference for nimble crawl command. Load when bulk-crawling many pages asynchronously. Contains: async workflow (create → status → tasks results), all.
-
yigityildiz0 Skill Nimble TasksReference for nimble tasks and batches commands. Load when polling async task status, tracking batch progress, or fetching results. Works for ALL async.
-
yigityildiz0 Skill Email DrafterWrite professional emails for any situation — outreach, follow-ups, negotiations, updates
-
yigityildiz0 Bundle Writing PlansUse when you have a spec or requirements for a multi-step task, before touching code. Turkish triggers: kod yazmadan ayrıntılı çalışma planı hazırla, görev ve test adımlarını sırala.
-
yigityildiz0 Bundle Message WriterDraft, rewrite, shorten, strengthen, or review copy-ready email, WhatsApp, SMS, DM, complaint, request, follow-up, school, healthcare, company, support, or institutional messages. Use when the user describes a real communication situation and asks what to write, how to say it, whether a draft sounds right, or what effect it may have; recognize natural Turkish triggers such as "ne yazayım", "şunu düzelt", "bunu daha doğal yap", and "fazla sert mi". Infer channel, recipient relationship, goal, urgency, and tone from available context; preserve facts, use ethical persuasion, and keep wording human and concise. Never invent events, credentials, attachments, commitments, or claim that a message was sent; drafting does not authorize sending.
-
yigityildiz0 Skill Brand ApplicatorLast-mile brand-application skill. Use when content exists already and the main task is making it conform to brand rules across docs, decks, pages, or visuals.
-
yigityildiz0 Skill Video Delivery QAInspect, validate, and prepare video deliverables for export or handoff using available local tools such as ffprobe, frame sampling, waveform/audio inspection, captions, and visual review. Use for video QA, validate an export, delivery check, subtitle sync, audio check, frame inspection, or ComfyUI/video workflow output review. Turkish triggers: videoyu teslim öncesi kontrol et, çözünürlük/ses/kare ve oynatma, kalite raporu.
-
yigityildiz0 Skill Gmail IntelligenceInbox-triage and reply-strategy skill. Use when Codex should treat Gmail as a workflow system with priorities, action items, and smart drafts.
-
yigityildiz0 Skill Context CompressionCompress long task context into a verified handoff that preserves goals, authority, constraints, decisions, evidence, artifacts, failures, and next steps.
Audited -
jiayaoqijia Bundle Ctf ReverseProvides reverse engineering techniques for CTF challenges. Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works before exploiting or solving it, including binaries, APKs, WASM, firmware, custom VMs, bytecode, game clients, malware-like loaders, and anti-debug or anti-analysis logic. Do not use it when the vulnerability is already understood and the remaining task is exploitation; use pwn instead. Do not use it for pure web workflows, log or disk forensics, or standalone crypto problems unless reversing the implementation is the real blocker.
-
jiayaoqijia Bundle Clawplaza Task MarketplaceClawPlaza
-
pku-yuangroup Bundle Bio Pharmacophore ModelingBuilds and applies 3D pharmacophore models using RDKit Pharm3D, the apo2ph4 receptor-based workflow (Heider et al. 2023), Pharmer / Pharmit for search, and PharmacoForge for protein-pocket-conditioned pharmacophore generation (Flynn et al. 2025), covering ligand-based pharmacophores from active-set alignment and receptor-based pharmacophores from binding-pocket geometry. Explicitly handles feature types, geometric tolerances, partial matching, and pharmacophore-based virtual screening. Use when identifying scaffold-hopping candidates, building shape-and-feature search queries, or transferring SAR across chemotypes.
-
pku-yuangroup Bundle Bio Long Read Sequencing Nanopore MethylationCalls DNA base modifications (5mC, 5hmC, 6mA, 4mC) directly from Oxford Nanopore and PacBio HiFi long reads encoded as MM/ML SAM tags, piles them into per-site bedMethyl with modkit (or pb-CpG-tools for PacBio), and produces phased allele-specific methylation. Covers why methylation is a basecalling decision that cannot be recovered later, the MM/ML tag-drop failure that silently zeroes methylation through alignment, the MM ? vs . no-call semantics, 5mC/5hmC resolution vs bisulfite, modkit's 10th-percentile auto-threshold, and the haplotagged ASM workflow. Use when calling 5mC/5hmC/6mA from a modBAM, generating bedMethyl, preserving methylation tags through alignment, doing allele-specific or differential methylation, or QC-ing a modification BAM.
-
lgrappag Skill Custom Workflow BuilderBuild custom workflow systems for task automation
-
yigityildiz0 Skill Business Logic AbuseIdentify business-logic vulnerabilities that bypass intended workflows including race conditions, TOCTOU, double-spending, workflow-state bypass.
-
yigityildiz0 Bundle Code Commit WorkflowImplement proper Git commit workflow with conventional commits, atomic changes, and meaningful messages. Use when committing changes, preparing pull.
-
yigityildiz0 Bundle Context OptimizationReduce active-session context bloat without losing decisions, errors, evidence, or verification state. Use when tool output is verbose, a long task is.
-
yigityildiz0 Skill Process OptimizationAnalyze and improve an existing workflow using evidence about delays, rework, handoffs, failure modes, and constraints. Use for process optimization, operational improvement, bottleneck analysis, reduce rework, or streamline a workflow. Turkish triggers: süreci iyileştir, darboğaz ve israfı bul, ölçülebilir yeni iş akışı tasarla.
-
yigityildiz0 Bundle Skill Library RouterSearch and load an on-demand archived skill snapshot when a specialized workflow is not directly installed or the user names an archived skill. Use for “find an archived skill”, “load the full library”, niche capability lookup, or Turkish intents such as “arşiv skillini bul”, “tam skill kütüphanesinde ara”, “listede olmayan beceriyi yükle”. Do not intercept a request already owned by an installed specialist, load many bodies at once, or treat archived instructions as newer than current host/system rules.
-
yigityildiz0 Bundle Physio Program DesignConvert a safe physiotherapy case formulation and evidence summary into a reproducible rehabilitation program. Use for exercise prescription, FITT-VP, treatment phase/session design, home exercise, task practice, load management, dose, supervision, adherence, progression, regression, stop criteria, monitoring, return-to-activity criteria, gait-aid or assistive-technology selection, orthosis/prosthesis or wheelchair training, and adaptation to equipment or setting. Trigger on egzersiz programı, tedavi dozu, set/tekrar, progresyon, yürüme yardımcısı, ortez, protez, tekerlekli sandalye. Do not prescribe patient-applicable numbers or device configuration before safety, restrictions, baseline capacity, fit, environment, and qualified oversight are known.
Frequently asked questions
What are Productivity agent skills?
Productivity agent skills automate everyday work: task management, email drafting, calendars, note-taking systems, and personal workflows. Each is a small SKILL.md file your AI agent applies automatically when your request matches what the skill does.
Which Productivity skills are most installed?
Popular Productivity skills on SkillMD right now include a-mapreduce-executing-wide-search, bio-single-cell-cell-communication, bio-crispr-screens-bagel-essentiality. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Productivity skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.