@anthropics

hook-development covers event-driven automation in claude code via pre/post tool hooks, stop validation, and session lifecycle management. supports both prompt-based (flexible) and command-based (deterministic) hook types with comprehensive configuration examples.

anthropics-rule-identifier teaches users to write hookify rules for claude, which are yaml-frontmatter markdown files that match patterns across bash, file, stop, and prompt events to trigger warnings or blocks with custom messages.

agent-development provides structured guidance for building autonomous agents in claude code plugins, covering frontmatter validation, system prompt design, triggering mechanics, and a templated creation workflow with clear examples.

build-zoom-video-sdk-app provides routing guardrails and web quick-start patterns for custom video sessions using zoom's video sdk, emphasizing strict lifecycle ordering and event-driven rendering to avoid silent failures.

agent-development covers building autonomous subprocesses in claude code plugins using yaml frontmatter, system prompts, and triggering conditions. it specifies required fields, design patterns for system prompts, and validation rules to create multi-step independent agents.

anthropics-sql-queries provides dialect-specific syntax reference and common analytical patterns (window functions, ctEs, funnels) across snowflake, bigquery, databricks, postgres and redshift, with performance tuning guidance per platform.

access manages discord channel allowlists, dm policies, and pairing approvals via json state mutations. enforces terminal-only mutations to prevent prompt injection through channel notifications.

view-pdf opens pdfs in an interactive viewer for collaborative markup, form filling, and visual annotation. designed for real-time document workflows where users need to highlight, stamp, sign, or fill fields while seeing changes live.

zoom-mcp covers MCP-based access to Zoom meetings, recordings, and assets via hosted connectors. requires user oauth, mcp-specific scopes, and ai companion features for semantic search. routes meeting crud to rest api.

slack-gif-creator provides slack-optimized gif constraints, pil-based drawing utilities, animation patterns (bounce, spin, fade, particle effects), and validation tools. emphasizes polished graphics over templates and supports both generated and user-uploaded imagery.

anthropics-xlsx handles creation, editing, and analysis of spreadsheet files with explicit workflows for formula construction, financial model standards, and error prevention. includes mandatory recalculation via libreoffice and comprehensive output requirements.

scvi-tools covers deep learning workflows for single-cell genomics including batch correction, multi-modal integration, reference mapping, and spatial analysis. provides model selection guidance, modular scripts, and decision trees for workflow routing.

slack-gif-creator provides PIL-based utilities and animation concepts for building optimized GIFs within Slack's dimension and color constraints. covers frame assembly, easing, validators, and common motion patterns like bounce and fade.

anthropics-listener-creator generates typescript email event handlers that monitor for conditions and execute custom actions. emphasizes ai-powered classification over brittle keyword matching and provides concrete templates for common automation patterns.

email-sequence guides users through designing multi-email campaigns with templated flows, branching logic, and performance benchmarks across onboarding, nurture, re-engagement, and launch use cases.

triage-nda classifies incoming NDAs into three routing buckets (standard approval, counsel review, full legal review) using a systematic 10-point screening checklist. supports multiple input formats and applies either organization-specific playbook rules or market-standard defaults.

configure sets up discord bot token storage, reads channel access policy from disk, and guides users toward allowlist-based lockdown instead of pairing mode. proactively pushes security posture by asking if the current allowlist matches intended reach.

stripe-best-practices provides authoritative guidance on modern stripe payment integration, covering checkout sessions, webhooks, subscriptions, and connect platforms while explicitly steering away from deprecated apis and legacy endpoints.

command-name documents standardized claude code plugin directory layout, manifest configuration, component organization (commands/agents/skills/hooks), auto-discovery mechanisms, and portable path references using ${CLAUDE_PLUGIN_ROOT}, covering both minimal and full-featured plugin patterns.

playground builder generates self-contained html explorers with live preview, interactive controls, and copyable prompt output. covers design, data, learning, and code review use cases via templates.

validate-data provides a systematic checklist for qa-ing analyses before stakeholder handoff, covering methodology review, calculation verification, common pitfalls, and confidence assessment. practical but generic in trigger language.

create-viz generates publication-quality charts from data using matplotlib/seaborn or plotly. covers chart type selection via decision table, python code templates with design best practices, and output as PNG files.

build-zoom-team-chat-app documents the distinction between team chat (user-scoped) and chatbot (bot-scoped) apis for zoom messaging integrations, with working code examples for both oauth flows and rich card composition.

anthropics-claude-opus-4-5-migration handles model string updates and beta header removal across four platforms, with conditional prompt adjustments for known behavioral differences. limited to sonnet/opus migrations, excludes haiku.

contact-research retrieves enriched contact profiles from common room via email, social handle, or name-company lookup, returning activity history, engagement scores, and crm fields.

skill-creator guides users through iterative skill development with quantitative benchmarking, interactive review tooling, and trigger-phrase optimization via extended thinking.

draft-content generates marketing material across multiple formats (blog, social, email, landing page, press release, case study) with configurable brand voice and seo guidance for web-facing content.

feature-spec provides a templated framework for writing product requirements documents with structured sections, user story formats, and success metric guidance. covers prd structure, prioritization methods, and scope management but lacks procedural depth and failure mode discussion.

web-artifacts-builder provides a scripted workflow for bundling react typescript projects with tailwind and shadcn/ui into self-contained html artifacts, with opinionated tooling and design guardrails to avoid common ai-generated output patterns.

call-prep assembles sales call context from web research and optional tool connectors, producing a structured brief with attendee backgrounds, suggested agenda, and discovery questions. works offline with user input or enhanced with crm, email, chat, transcript, and calendar connections.

pipeline-review scores deal health across activity, stage progression, and contact coverage, then ranks deals by closability and impact. accepts csv upload, manual paste, or cxm integration. outputs weekly action plan with risk flags and hygiene audit.

earnings-preview-single generates a dense 4-5 page equity research report on a single company using only kensho and s&p global data sources. emphasizes strict data sourcing constraints and intermediate file persistence to prevent hallucination.

guides migration from claude sonnet 4.0, 4.5, or opus 4.1 to opus 4.5 via model string replacement and optional prompt adjustments based on reported behavioral drift.

user-research-synthesis provides thematic analysis, affinity mapping, and persona development methods for extracting patterns from interviews, surveys, and behavioral data. covers initial coding through opportunity sizing to prioritize findings.

knowledge-management covers creation and maintenance of searchable support kb articles across four types: how-to guides, troubleshooting, faqs, and known issues. emphasis on customer language, structured templates, and maintenance cadences to reduce ticket volume.

digest aggregates recent activity across connected data sources (chat, email, cloud storage, project trackers, crm, knowledge bases) into a structured report organized by topic, with action items prioritized and cross-source deduplication applied.

accessibility-review audits designs and pages against wcag 2.1 aa using manual and automated approaches. outputs structured findings across perceivable, operable, understandable, and robust categories with severity levels and remediation guidance.

vendor-check consolidates agreement status across clm, crm, email, and document storage systems, mapping vendor relationships and identifying legal coverage gaps with gap analysis and upcoming renewal tracking.

metrics-review guides structured analysis of product metrics across acquisition through satisfaction, organizing data into a north star hierarchy, surfacing trends and anomalies, and recommending investigations or experiments. comprehensive but generic in activation.

frontend-design guides creation of production-grade interfaces with intentional aesthetic direction, rejecting generic patterns. it frames design thinking (purpose, tone, differentiation) before code generation in html/css/js or component frameworks.

account-research gathers company and person intelligence via web search, enrichment apis, and crm lookups to surface hiring signals, leadership info, and relationship context for pre-outreach qualification.

setup-zoom-oauth guides selection of app type, oauth grant flow, and scope planning before token exchange and refresh implementation, catching common mistakes in actor modeling and credential lifecycle.

ux-copy provides structured templates and principles for writing interface microcopy across common patterns (buttons, errors, empty states, tooltips). it emphasizes clarity and user context but lacks procedural depth and failure mode guidance.

plan-zoom-integration structures zoom integration work into phases with architecture decisions, auth requirements, and risk callouts, but lacks concrete procedural detail and specific trigger patterns.

audit-xls checks spreadsheet formulas and data integrity across user-selected scopes (range, sheet, or full model). targets financial audits with tiered depth.

anthropics-daily-briefing aggregates calendar, crm, and email data into a prioritized sales action plan. works standalone with user input or enhanced with connected integrations. outputs a 2-minute scannable briefing with meetings, pipeline alerts, and top actions.

draft-outreach researches prospects via web search and optional enrichment connectors, then generates personalized cold or warm email templates with subject line alternatives and linkedin fallbacks. no automated sending.

data-context-extractor is a meta-skill for bootstrapping and iterating on company-specific data analysis skills by capturing analyst knowledge through structured interviews and schema discovery. generates templated reference documentation for entities, metrics, and tables.

debug-zoom-integration provides a triage framework for isolating failures across zoom auth, webhooks, sdk joins, and media workflows by collecting evidence and routing to specific reference layers.

architecture guides creation and evaluation of decision records for technology choices and system design, with a structured adr template and trade-off framework but limited procedural depth and no failure recovery guidance.

interactive-dashboard-builder provides templated patterns for self-contained html dashboards with chart.js, filter controls, and responsive styling. it covers kpi cards, multiple chart types, and data tables, all in a single file without server dependencies.

campaign-plan scaffolds marketing campaign generation by collecting goal, audience, and timeline inputs, then outputs a brief with objectives, messaging, channels, calendar, and metrics. execution details remain underspecified.

slack-messaging covers mrkdwn syntax rules, formatting tables, common mistakes, and message structure guidance for composing readable slack communications.

plan-zoom-product guides selection among zoom's integration surfaces (rest api, webhooks, websockets, sdks, phone, contact center, mcp) by classifying use cases and explaining tradeoffs, but lacks concrete decision criteria and failure mode coverage.

debug-zoom isolates zoom integration failures across auth, api, webhooks, sdk, and mcp layers by collecting minimal evidence and ranking plausible causes with targeted references.

constructs standardized financial data packs from disparate sources (cims, sec filings, web, mcp servers) into excel workbooks. enforces formula-based accuracy, source traceability, and internal consistency checks for investment committee consumption.

option-vol-analysis interprets volatility surfaces, Greeks, and realized volatility to assess option pricing. tool outputs flow into implied-vs-realized comparisons and surface shape interpretation. positions assessment as analytical rather than decisional.

fixed-income-portfolio aggregates bond pricing, reference data, cashflow projections, and scenario analysis into portfolio-level risk metrics. focuses on weighted averages and benchmark relative analysis but lacks concrete implementation detail.

cowork-plugin-customizer handles setup and modification of claude code plugins for organizational contexts by locating source files, detecting placeholder patterns, and routing users through generic setup, scoped edits, or broad customization flows.

dcf-model builds discounted cash flow valuations for equity analysis. covers institutional standards, excel output with sensitivity tables, and dual execution paths (office js vs python/openpyxl) depending on deployment context.

slack-search catalogs available search tools (public channels, all channels, channel discovery, user lookup) but lacks concrete guidance on constructing queries or handling real search scenarios.

build-zoom-meeting-app guides selection between zoom meeting and video sdks, covers join/auth flows and platform routing, but lacks concrete implementation steps and failure mode handling.

reference material for zoom rivet sdk covering node.js server scaffolding, oauth token handling, webhook receivers, and typed api wrappers. routing guidance provided for auth model selection and module composition.

command-development covers creating reusable slash commands for claude via markdown files with yaml frontmatter, dynamic argument substitution, and bash context gathering. suitable for power users building custom workflows.

weekly-prep-brief assembles a 7-day call docket from calendar or manual input, then enriches each meeting with company and contact research via common room api.

anthropics-pdf covers common pdf operations (merge, split, extract text/tables, create, rotate, watermark, encrypt) via python libraries and cli tools. lacks explicit error handling, recovery paths, and validation logic.

anthropics-competitive-intelligence generates interactive html battlecards comparing your company against named competitors using web research and optional crm/docs/chat connectors. outputs a self-contained tabbed artifact with comparison matrix, per-competitor deep-dives, talk tracks, and objection handling.

process-doc generates structured SOPs with RACI matrices and flowcharts by conversational input. covers purpose, scope, detailed steps, and exceptions, but lacks concrete procedural specificity and edge case depth.

design-mcp-workflow guides selection between mcp and rest api for zoom integrations, identifying agentic vs deterministic needs and routing to appropriate connectors including whiteboard-specific paths.

journal-entry-prep documents standard accrual types, depreciation methods, revenue recognition frameworks, and approval workflows for financial close activities. covers supporting documentation requirements and common error patterns but lacks procedural automation hooks.

competitive-brief outlines a research framework and output structure for analyzing competitor positioning, messaging, and content strategy, but lacks actionable step-by-step procedures and does not address execution challenges or data quality issues.

task-management tracks work via a shared markdown file with optional html dashboard, supporting task extraction, checkbox marking, and categorical grouping into active, waiting, someday, and done buckets.

performance-report scaffolds marketing analysis across campaigns, channels, and content by routing to appropriate report type, but lacks concrete procedure steps, data source specification, and failure handling.

skill-development outlines how to construct modular skill packages for Claude Code plugins, covering directory structure, frontmatter conventions, and progressive context loading patterns. prescriptive rather than procedural.

brand-review evaluates marketing content against brand guidelines and style rules, with optional fallback to generic clarity and consistency checks. the skill provides structured frameworks for defining brand voice but the execution pathway is underspecified.

scvi-tools covers deep learning for single-cell analysis including data integration, batch correction, and probabilistic modeling. documentation lacks specific procedures and executable workflows.

ib-check-deck extracts presentation text across slides and cross-checks numeric consistency, but the workflow is incomplete and execution steps remain vague. incomplete spec, unfinished implementation.

contract-review performs clause-by-clause analysis against organizational playbooks, assigns severity flags (green/yellow/red), and suggests redlines. requires configured playbook; falls back to commercial baselines if none exists.

audit-support provides framework reference material for sox 404 testing phases including scoping, risk assessment, control identification, and deficiency classification. lacks actionable procedures and specific workflow triggers.

risk-assessment provides a framework for cataloging operational, financial, compliance, strategic, reputational, and security risks via a standard register format. lacks concrete procedural steps for facilitating assessment or surfacing hidden risks.

capacity-plan guides teams through resource allocation by collecting headcount, workload, and constraints, then generates utilization tables and bottleneck analysis with hiring or reprioritization recommendations.

equity-research synthesizes consensus estimates, fundamentals, pricing, and macro data into investment narratives. weakly structured procedures and missing recovery paths limit reliable execution.

probe-sdk covers client-side preflight diagnostics for zoom meetings, routing users through device capability checks and network readiness scoring before session join flows.

customer-escalation packages support issues into structured briefs for engineering or leadership, gathering context and assessing business impact from issue description and account details.

lbo-model covers leveraged buyout template population in excel, with conditional workflows for user-provided vs standard templates and emphasis on template reuse over custom builds.

policy-lookup retrieves and explains company policies in plain language via knowledge base search or handbook text. covers pto, benefits, compensation, remote work, travel, conduct, and growth. requires manual source citation and defers edge cases to hr.

design-system provides templates for auditing naming/token consistency, documenting component variants and states, and proposing new patterns. execution relies on manual inspection and table-filling without procedural guidance.

bond-futures-basis skill guides analysis of futures-cash basis trades through multi-tool orchestration: pricing futures, identifying cheapest-to-deliver, comparing yield curves, and assessing delivery option value. implementation incomplete.

comp-analysis benchmarks compensation against market data and analyzes internal bands for hiring and retention. covers base, equity, bonus, and benefits across role, level, location, and company stage. outputs percentile tables and placement recommendations.

swap-curve-strategy covers multi-tenor swap pricing and curve decomposition using external tools, overlaying government and inflation data to compute spreads and identify trade opportunities. lacks concrete execution steps and edge case handling.

reference material for zoom phone integration across api, webhook, smart embed, and uri-launch patterns. includes routing guardrails for embedded softphone, rest api workflows, click-to-dial, and crm chaining scenarios.

setup-zoom-websockets provides background comparison between zoom websocket and webhook connection models, but lacks actionable setup procedures, concrete trigger conditions, or failure recovery patterns needed for production deployment.

setup-zoom-mcp frames decisions between mcp and rest for zoom workflows, but lacks concrete step sequence, failure handling, and specific trigger conditions.

sox-testing provides command templates for generating sox 404 workpapers and control assessments but lacks documented procedures, decision logic, and failure handling needed for production compliance workflows.

zoom-oauth documents zoom api authentication patterns including oauth flows, token lifecycle management, and error codes, but lacks concrete procedural steps and actionable decision trees for implementation.

canvas-design generates visual art by articulating aesthetic philosophies and expressing them through pdf or png compositions. output is markdown-documented design philosophy paired with gallery-ready artwork emphasizing form, space, and color over text.

build-zoom-virtual-agent is a reference guide for implementing zoom virtual agent across web embeds and mobile wrappers, with routing logic to related skills and a documented lifecycle pattern.

internal-comms provides templated guidance for writing status reports, newsletters, and incident communications, but lacks concrete procedures, actual template content, and failure mode handling.

write-spec scaffolds feature specifications and PRDs from problem statements. the workflow begins with understanding the feature, but the implementation details trail off incompletely, leaving execution mechanics unclear.

cookbook-audit evaluates anthropic cookbook notebooks against a style rubric, checking for learning objectives, prerequisites, core content structure, and conclusion alignment. delegates actual audit criteria to an external style_guide.md file.

kb-article converts resolved support tickets and common questions into searchable knowledge base content, with examples covering sso configuration, data export limits, webhook setup, and known browser issues.

roadmap-update handles creation and reprioritization of product roadmaps via argument-driven workflow, though execution steps remain incomplete and lack specific platform integration details.

math-olympiad covers imo/putnam/usamo/aime problem solving via parallel solver agents with adversarial verification, but reads as internal documentation rather than executable skill specification.

zoom-apps-sdk is a reference skill documenting the official sdk for building web apps embedded in zoom clients, with links to docs, npm, and minimal procedural guidance.

macro-rates-monitor provides role assignment and tool inventory for macro analysis workflows, but lacks runnable procedure, decision logic, and output schema definition.

enrich-lead accepts a name, email, linkedin url, or job title and claims to return contact details. the implementation cuts off mid-procedure and lacks completion criteria.

brief generates legal team summaries in three modes (daily, topic, incident) but lacks procedural detail, input specifications, and failure handling. abstract rather than actionable.

draft-response generates customer-facing communication templates using context about customer queries, issues, or requests. lacks specifics on tone control, personalization depth, or handling sensitive situations.

build-zoom-contact-center-app collects zoom contact center integration reference material across app, web, and native surfaces but lacks procedural substance and actionable implementation detail.

skills-algorithmic-art provides verbose philosophical framing for generative p5.js art with seeded randomness, but lacks actionable implementation steps, concrete decision logic, and failure handling. the skill reads as aspirational guidance rather than executable procedure.

scribe is a reference document listing zoom's transcription endpoints and auth mechanisms without implementing a coherent workflow, intent mapping, or decision logic needed for the skill graph.

algorithmic-art provides a verbose framework for creating generative art in p5.js using seeded randomness and parametric controls. the document emphasizes philosophical articulation and craftsmanship rhetoric but lacks concrete procedural guidance for actual implementation.

call-summary accepts a transcript or notes block and extracts action items, drafts follow-up comms, and updates records, but the actual implementation logic is not described.

fhir-developer-skill documents http status codes for fhir api interactions but lacks procedural guidance, trigger conditions, or actionable workflows.

anthropics-cookbook-audit provides a framework and checklist for reviewing anthropic cookbook notebooks against style guidelines, but lacks concrete trigger phrases and does not itself execute audits - it reads as a meta-skill defining audit processes rather than performing them.

draft-offer assembles offer letters but lacks procedural specificity, defined inputs, decision logic, or failure mode handling. the skill description is aspirational rather than operational.

fsi-strip-profile describes a workflow for gathering company research inputs and planning presentation slides, but lacks execution detail, output contracts, and actual skill logic.

template placeholder with no actual skill content, intent, procedure, trigger phrases, or documented behavior.

Review a contract against your organization's negotiation playbook — flag deviations, generate redlines, provide business impact analysis. Use when reviewing…

Sync tasks and refresh memory from your current activity. Use when pulling new assignments from your project tracker into TASKS.md, triaging stale or overdue…

Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing…

Profile and explore a dataset to understand its shape, quality, and patterns. Use when encountering a new table or file, checking null rates and column…

This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin…

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent…

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and…

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files,…

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with…

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an…

Pre-call brief for an upcoming meeting - attendees, account history, prior call context from transcripts, open opportunity status, and suggested discovery questions. Use when the user asks "prep me for [meeting/company]", "call prep [company]", "I'm meeting with [company], prep me", "get me ready for [meeting]", or "what do I need to know before my [time] call".

Best practices for building Stripe integrations. Use when implementing payment processing, checkout flows, subscriptions, webhooks, Connect platforms, or any Stripe API integration.

Screen incoming NDAs and classify them as GREEN (standard), YELLOW (needs review), or RED (significant issues). Use when a new NDA comes in from sales or business development, when assessing NDA risk level, or when deciding whether an NDA needs full counsel review.

Manages connected MCP sources for enterprise search. Detects available sources, guides users to connect new ones, handles source priority ordering, and manages rate limiting awareness.

Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.

Assess and classify legal risks using a severity-by-likelihood framework with escalation criteria. Use when evaluating contract risk, assessing deal exposure, classifying issues by severity, or determining whether a matter needs senior counsel or outside legal review.

Plan and prioritize product roadmaps using frameworks like RICE, MoSCoW, and ICE. Use when creating a roadmap, reprioritizing features, mapping dependencies, choosing between Now/Next/Later or quarterly formats, or presenting roadmap tradeoffs to stakeholders.

Performs quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scverse best practices with MAD-based filtering and comprehensive visualizations. Use when users request QC analysis, filtering low-quality cells, assessing data quality, or following scverse/scanpy best practices for single-cell analysis.

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.

Draft marketing content across channels — blog posts, social media, email newsletters, landing pages, press releases, and case studies. Use when writing any marketing content, when you need channel-specific formatting, SEO-optimized copy, headline options, or calls to action.

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

This skill applies consistent corporate branding and styling to all generated documents including colors, fonts, layouts, and messaging

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions

Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

>

>

Run nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data. Use when analyzing RNA-seq, WGS/WES, or ATAC-seq data—either local FASTQs or public datasets from GEO/SRA. Triggers on nf-core, Nextflow, FASTQ analysis, variant calling, gene expression, differential expression, GEO reanalysis, GSE/GSM/SRR accessions, or samplesheet creation.

Generate a response to a common legal inquiry using configured templates, with built-in escalation checks for situations that shouldn't use a templated reply.…

>

Structure a performance review with self-assessment, manager template, and calibration prep. Use when review season kicks off and you need a self-assessment…

Run a compliance check on a proposed action, product feature, or business initiative, surfacing applicable regulations, required approvals, and risk areas. Use…

Start your day with a prioritized sales briefing. Works standalone when you tell me your meetings and priorities, supercharged when you connect your calendar,…

Analyze and improve business processes. Trigger with "this process is slow", "how can we improve", "streamline this workflow", "too many steps", "bottleneck",…

This skill generates, creates, or builds brand voice guidelines from source materials. It should be used when the user asks to "generate brand guidelines",…

Track compliance requirements and audit readiness. Trigger with "compliance", "audit prep", "SOC 2", "ISO 27001", "GDPR", "regulatory requirement", or when the…

Create or update an operational runbook for a recurring task or procedure. Use when documenting a task that on-call or ops needs to run repeatably, turning…

Multi-source research on a customer question or topic with source attribution. Use when a customer asks something you need to look up, investigating whether a…

Headcount planning, org design, and team structure optimization. Trigger with "org planning", "headcount plan", "team structure", "reorg", "who should we hire…

Full ICP-to-leads pipeline. Describe your ideal customer in plain English and get a ranked table of enriched decision-maker leads with emails and phone numbers.

Prepare journal entries with proper debits, credits, and supporting detail. Use when booking month-end accruals (AP, payroll, prepaid), recording depreciation…

Find leads matching criteria and bulk-add them to an Apollo outreach sequence. Handles enrichment, contact creation, deduplication, and enrollment in one flow.

Generate an onboarding checklist and first-week plan for a new hire. Use when someone has a start date coming up, building the pre-start task list (accounts,…

Evaluate a vendor — cost analysis, risk assessment, and recommendation. Use when reviewing a new vendor proposal, deciding whether to renew or replace a…

Create a change management request with impact analysis and rollback plan. Use when proposing a system or process change that needs approval, preparing a…

Generate a stakeholder update tailored to audience and cadence. Use when writing a weekly or monthly status for leadership, announcing a launch, escalating a…

Generate headcount, attrition, diversity, or org health reports. Use when pulling a headcount snapshot for leadership, analyzing turnover trends by team,…

nextflow-development — an installable skill for AI agents, published by anthropics/knowledge-work-plugins.

scientific-problem-selection — an installable skill for AI agents, published by anthropics/knowledge-work-plugins.

signature-request — an installable skill for AI agents, published by anthropics/knowledge-work-plugins.

earnings-analysis — an installable skill for AI agents, published by anthropics/financial-services-plugins.

Create institutional-quality equity research initiation reports through a 5-task workflow. Tasks must be executed individually with verified prerequisites -…

Clean up messy spreadsheet data — trim whitespace, fix inconsistent casing, convert numbers-stored-as-text, standardize dates, remove duplicates, and flag…

Generate a polished one-page PowerPoint slide summarizing key takeaways from recent funding rounds and notable capital markets activity across a user's watched…

Build a Zoom meeting bot, recorder, or real-time media workflow. Use when joining meetings programmatically, processing live media or transcripts, or combining…

Reference skill for Zoom webhooks. Use after routing to an event-driven workflow when implementing subscriptions, signature verification, delivery handling,…

Populates investment banking pitch deck templates with data from source files. Use when: user provides a PowerPoint template to fill in, user has source data…

Define, track, and analyze product metrics with frameworks for goal setting and dashboard design. Use when setting up OKRs, building metrics dashboards,…

Cross-product Zoom reference skill. Use after the workflow is clear when you need shared platform guidance, app-model comparisons, authentication context,…

Plan and prioritize product roadmaps using frameworks like RICE, MoSCoW, and ICE. Use when creating a roadmap, reprioritizing features, mapping dependencies,…

Apply and enforce brand voice, style guide, and messaging pillars across content. Use when reviewing content for brand consistency, documenting a brand voice,…

Research competitors and compare positioning, messaging, content strategy, and market presence. Use when analyzing a competitor, building battlecards,…

Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.

Updates a presentation with new numbers — quarterly refreshes, earnings updates, comp rolls, rebased market data. Use whenever the user asks to "update the…

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…

Reference skill for Zoom RTMS. Use after routing to a live-media workflow when processing real-time audio, video, chat, transcripts, screen share, or…

Reference skill for Zoom Cobrowse SDK. Use after routing to a collaborative-support workflow when implementing browser co-browsing, annotation tools, privacy…

Reference skill for Zoom Meeting SDK. Use after routing to a meeting-embed workflow when implementing real Zoom meeting joins, platform-specific SDK behavior,…

Choose the right Zoom architecture for a use case. Use when deciding between REST API, Webhooks, WebSockets, Meeting SDK, Video SDK, Zoom Apps SDK, Zoom MCP,…

Generate professional company tear sheets using S&P Capital IQ data via the Kensho LLM-ready API MCP server. Use this skill whenever the user asks for a tear…

build-zoom-rest-api-app — an installable skill for AI agents, published by anthropics/knowledge-work-plugins.

Evaluate FX carry trade opportunities by combining spot rates, forward points, interest rate differentials, volatility surface analysis, and historical price…

Perform relative value analysis on bonds by combining pricing, yield curve context, credit spreads, and scenario stress testing. Use when analyzing bond…

Complete, populate and fill out 3-statement financial model templates (Income Statement, Balance Sheet, Cash Flow Statement) . Use when asked to fill out model…

comps-analysis — an installable skill for AI agents, published by anthropics/financial-services-plugins.

Creates self-contained PPT template SKILLS (not presentations) from user-provided PowerPoint templates. Use ONLY when a user wants to create a reusable skill…

Performs quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scverse best practices with MAD-based filtering and comprehensive…

Framework for building competitive landscape decks — market positioning, competitor deep-dives, comparative analysis, strategic synthesis. Use when the user…

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when…