Finance & Business
Finance agent skills bring structure to money-related work: financial models, accounting workflows, invoices, budgeting, and market analysis. Your AI agent loads the skill when the task matches and follows its rules, in any agent that reads SKILL.md files.
-
upsolve-labs Skill Dstack InvestigateAnomaly root cause analysis. Use when a metric looks wrong or surprising. Runs a structured 4-phase investigation over a single Upsolve thread: confirm → narrow → hypothesize → validate. Findings use numbered codes (1A CONFIRMED, 1B CANDIDATE, 2A RULED_OUT). Trigger phrases: "revenue dropped", "metric is spiking", "why did X change?", "something looks wrong", "root cause", "debug this metric".
-
kijitoai Skill Kijito RecallRecall patterns that make Kijito answer hard questions well — decompose multi-part questions into per-hop sub-queries, merge under a fixed context budget, chain entities between hops, and keep abstention discipline. Use when a question needs several distinct facts from memory (a "multi-hop" question), when a single recall came back with a compromise neighborhood that misses the point, or when deciding how deeply to retrieve before answering.
-
danishi Bundle Izakaya SearchSearch and recommend izakaya (Japanese-style pubs) and restaurants based on party size, budget, area, and additional preferences. Aggregates reviews from gourmet sites (Tabelog, Hot Pepper Gourmet, Gurunavi) and Google Maps, calculates composite ratings, and provides reservation links and Google Maps directions for quick booking.
-
ariessolutionsio Bundle MarketplacerOperator-side patterns for integrating Marketplacer into a composable commerce stack — GraphQL Operator API, per-seller order splits via Invoices, caller-shaped webhooks with HMAC, MPay deposit-and-reconcile payouts, Golden Product PIM sync, wholesale orders, additional charges, and Catalog Rules. Use when implementing or maintaining a Marketplacer marketplace behind any commerce platform (commercetools, Kibo, Scayle, etc.), any search engine, any PIM, OMS, or ERP. Triggers on Marketplacer, marketplace, multi-vendor, multi-seller, Advert, Seller, Invoice, Golden Product, MPay, Airwallex, Hyperwallet, Xero, RefundRequest, RemittanceAdvice, Remittance, Taxon, Prototype, Catalog Rule, marketplace commission, marketplace fees, marketplace operator, marketplace webhooks, paymentReferences. Consult this skill before writing code that talks to a Marketplacer instance, defines a Marketplacer webhook, or maps Marketplacer data into another system.
-
hospitalityos Skill Revenue ManagementHotel revenue management and dynamic pricing analysis. Use when the user asks about 'rate optimization', 'STR benchmarking', 'RevPAR analysis', 'pickup pace', 'compression night pricing', 'channel mix', 'displacement analysis', or any room pricing and demand strategy question for a hotel property.
-
byteseek Skill Sec Filing AnalysisAnalyze SEC disclosures for lightweight fact supplements or deep filing reviews, including source gaps, accounting quality, and thesis-relevant deltas.
-
mehdimicra Bundle Renoolab Chiffrer Piloter RentabiliteÀ charger avant de répondre à toute rédaction ou relance de facture client ou d'impayé, et à toute question financière d'une entreprise artisanale : coût, temps facturable, prix, marge, rentabilité, devis émis, acompte, avenant, TVA, paiement, encaissement ou trésorerie. Déclencher même si le métier n'est pas précisé. Pour le budget d'un particulier, utiliser la planification ; pour comparer plusieurs devis reçus, utiliser la recherche d'artisans ; pour relancer un devis non signé, utiliser le développement commercial.
-
tellmefrankie Skill Context BudgetContext Budget Tracker
-
taewanu Bundle Time TrackingTrack per-session work time on freelance/personal projects with automatic timestamps, timezone, and category breakdowns. Supports multiple open sessions via switch / pause+resume / concurrent. Use whenever the user wants to start, end, pause, resume, switch, analyze, or invoice a work session, including phrases like "시작", "끝", "일시정지", "재개", "전환", "갈아타", "타임 트래킹 시작", "세션 종료", "이번 주 분석", "분석해줘", "<client> 청구서", "start tracking", "end session", "pause session", "resume", "switch to <project>", "analyze hours", "invoice for X", or simply invoking the skill via /time-tracking. Triggers on any work-session timing intent, even if the user doesn't say "track" or "skill" explicitly.
-
philipobenito Skill Design ReviewReviews a consolidated design summary for completeness, consistency, clarity, scope, and YAGNI by dispatching a fresh reviewer subagent against the summary text alone. Invoked by `design-dialogue` and `design-committee` once the design is consolidated and before final user approval; the inline design path below the design threshold deliberately does not use it. Returns an approved summary, the open decisions the design never made, or an escalation once its three-dispatch budget is spent. Not a standalone entry point; a design summary handed straight to Claude for review belongs to the design skill that owns it.
-
philipobenito Skill Debug InvestigationRuns a disciplined, evidence-driven investigation to reproduce a bug, identify its root cause, and deliver a minimal verified fix. You MUST use this before touching any code in response to a bug, an error, a crash, a failing or flaky test, a regression, or anything described as not working, including one-line fixes and changes that look like an obvious typo: the hard gate (no fix without a reproduction and an identified root cause) applies however simple the fix looks. Enforces scope discipline, the investigation budget, and the minimal fix principle, and takes its own approval for the fix approach so bugs do not go through the design step.
-
mosofin Skill Three Way MatchUse this skill whenever the user wants to perform a three-way match between purchase orders, goods receipts and vendor invoices against a connected Mosofin workspace. Triggers include: 'three-way match these documents', 'verify the invoice against the PO and receipt', 'match PO to receipt to invoice', 'PO matching', 'GRN matching', 'run the match across all open invoices', uploading a PO + receipt + invoice trio, or any AP control task involving PO-to-invoice verification. Do NOT use for invoice extraction alone — use invoice-data-extractor. Do NOT use for duplicate detection — use duplicate-invoice-detection. Where the workspace holds purchase orders and item receipts, this runs across the full population every period rather than document by document. Outputs a match result with line-by-line comparison and exception list. Proposes only — Mosofin pays nothing and releases nothing.
-
mosofin Skill Bank ReconciliationUse this skill whenever the user needs to reconcile a bank account (cash GL) to bank statements for a period, working from their Mosofin workspace. Triggers include: bank recon, reconcile bank, cash reconciliation, bank statement tie-out, unreconciled items, outstanding checks, deposits in transit, or investigating recon differences. Workspace-scoped: it confirms the workspace, discovers which company files are connected and which read-only tools are enabled, then builds the complete book side from live ledger data and prepares the bridge — while stating plainly that the bank statement is outside any accounting datasource and must be supplied before a reconciliation can actually be completed. Produces a recon output, variance explanations, a clean list of required journal entries or corrective actions, and a coverage sheet.
-
mosofin Skill Journal Entry BuilderUse this skill whenever the user wants to construct, format, or validate a journal entry against their Mosofin workspace. Triggers include: 'book a JE for...', 'create a journal entry to record...', 'how do I record this transaction', 'make me an accrual JE', 'reclass these entries', 'reverse this entry', or any request involving debits and credits to specific accounts. Also trigger for adjusting entries, correcting entries, closing entries, intercompany entries, and import-ready JE files for accounting systems. Workspace-scoped: it confirms the workspace, discovers which company files are connected and which read-only tools are enabled, then builds entries against the real chart of accounts and validates them against the books — checking that accounts exist, signs match account types, the period is open, and no prior accrual already covers the item. Mosofin never posts: every entry is a proposal for a person to post. Do NOT use for GL coding decisions only — use gl-coding-assistant. Do NOT use for full perio
-
mosofin Skill Ar Aging And CollectionsUse the confirmed Mosofin workspace and its connected accounting datasource to pull live A/R, build and reconcile an aging, prioritize collections, calculate receivables metrics, and draft review-only reminders. Trigger for 'run an AR aging,' 'who owes us money,' 'prioritize collections,' 'calculate DSO,' or 'draft overdue-invoice reminders.' Workspace-scoped: require the Mosofin workspace and an active connection, discover which read-only tools are enabled, and resolve every task against that capability map before reading data. Do not use for cash application, bad-debt write-offs, invoice creation, or sending reminders.
-
mosofin Skill Duplicate Invoice DetectionUse this skill whenever the user wants to detect duplicate or fraudulent invoices in AP from their Mosofin workspace. Triggers include: 'check for duplicate invoices', 'find duplicate payments', 'scan AP for duplicates', 'detect invoice fraud', 'have we paid this twice', uploading a payment history or AP register, or any AP control review focused on payment integrity. Workspace-scoped: it confirms the workspace, discovers which company files are connected and which read-only tools are enabled, then runs the detection rules directly against live bills, payments and the vendor master — nine of the ten rules are pure queries. The bank-account rule cannot run, because Mosofin deliberately does not expose vendor bank details. Do NOT use for general fraud detection across all transaction types — use fraud-detection-and-forensics. Outputs a duplicate-suspect list with confidence ratings, supporting evidence, and a coverage sheet.
-
olaradiallysymmetrical491 Skill Web3 Bug ClassesComplete reference for all 10 DeFi smart contract bug classes. Use this when hunting for specific vulnerability types, need attack patterns for accounting desync, access control, incomplete path, off-by-one, oracle manipulation, ERC4626 vaults, reentrancy, flash loans, signature replay, or proxy/upgrade bugs.
-
databricks-solutions Bundle Cost OptimizerRecommend Databricks cost-optimization actions for the FinOps/platform team — commitment/discount coverage, budget variance, and forecast-vs-actual DBU spend from system.billing.usage and system.billing.list_prices.
-
databricks-solutions Bundle Budget Variance AnalyzerAnalyze Financial Applications budget-vs-actual variance by cost center and account from aggregate financial ledger tables. Ask me where spend is over or under budget, variance trends, or the biggest variance drivers.
-
wlzh Bundle Wlzh Invoice Scanner扫描目录识别所有类型发票(交通、住宿、餐饮等),提取关键信息并生成分类统计报告
-
swih Skill French Invoice ReminderRédige une relance de facture B2B en français avec un ton contrôlé (poli, ferme, ou final). À utiliser quand l'utilisateur demande une relance facture, un rappel de paiement, un mail de recouvrement, ou une dunning letter en français.
-
andreworia Skill Zero Based Budget BuilderBuilds a zero-based budget for a cost center by requiring every line item to be justified from first principles rather than rolled forward from the prior year.
-
aatirs-vault Skill Voc ProfilerEnrich a raw Voice of Customer signal (a quote, complaint, request or praise from a call, chat message, meeting note, review, survey or ticket) with CRM context — ICP fit score, segment, revenue tier, lifecycle stage. Flags missing metadata explicitly so weighted decisions never run on anonymous noise. Trigger on /voc-profiler, "profile this quote", "who said this and do they matter".
-
trpc-group Skill Travel Planning AssistantAutomatically generate a comprehensive travel plan based on user's travel needs (destination, date, budget, etc.), including transportation, accommodation, attractions, food, and itinerary. Use when a user asks for a travel plan, itinerary, travel tips, or mentions a specific destination.
-
jazz1x Bundle RalphiQuality-loop discipline. Enforces a per-cycle token budget (setup → worker → verifier → commit → handoff phases) and runs a between-cycle philosophy auto-check via rg sweep over the diff. Halts on any introduced ROP / version-hardcoding violation. Etymology — "ralph" (from Ralph Wiggum, persistent retry) + "-i" (inspection). Triggers: "ralphi", "사이클 점검", "loop budget", "cycle gate", "philosophy sweep", "between-cycle check"
-
jjfroehlich Bundle Grant WritingUse when the user is planning, drafting, revising, or reviewing a grant or fellowship application, including specific aims, project summaries, significance/innovation/approach sections, funder-fit checks, budget-feasibility alignment, risk/alternative plans, resubmissions, interviews, or reviewer-facing funding narratives. Trigger only when the artifact or decision is part of a funding mechanism; for manuscript peer review, journal submission, general prose editing, or career materials without a funding context, use a different skill.
-
joshrotenberg Bundle CookingUse this skill when the user needs to prepare a meal, bake bread, build a sauce, or perform any food preparation task. Triggers include: 'what should I make for dinner', 'my roux keeps breaking', 'how do I dice an onion properly', or 'I want to make sourdough'. Do NOT use for metaphorical cooking such as 'cooking the books' — see the accounting-fraud skill.
-
aznatkoiny Skill VerifyVerify a forge-built plugin before shipping: smoke matrix, fresh pass^k trials, holdout tranche, trigger evals on default AND crowded targets, token budget check, and triage of sampled failures. Use after a forge build loop has gone green (.forge/state.json phase smoke or verify) and before /plugin-forge:ship.
-
blockchainhb Bundle Giggster SearchSearch Giggster event/venue rentals via their internal API instead of clicking through the website. Use when the user wants to find an event space, party venue, film/photo location, or asks to "check Giggster". Filters by date availability, house rules (alcohol, loud noise, smoking), capacity, budget, and overnight operating hours — then shortlists.
-
gaia-computer-technologies Skill Design BriefTurn a client conversation, loose notes, or a mood description into a structured architectural design brief — programme, site, design intent, materials, sustainability, budget, and open questions. Use when an architect needs to formalise design intent at RIBA Stage 1 / AIA Pre-Design, wants to "write a brief", "structure this client meeting", or turn a vague idea into a project north-star. Pairs with programme-schedule (area validation) and material-palette (material direction).
-
gaia-computer-technologies Skill Programme ScheduleBuild or sanity-check a schedule of accommodation — room list, per-space areas from named benchmarks, circulation and net-to-gross with an explicit efficiency factor, reconciled to a target GIA or budget. Use when an architect needs an "area schedule", "schedule of accommodation", "space programme", net/gross gross-up, or "does this fit". Shows every calculation step (free-typed arithmetic is unreliable), states benchmarks as convention to verify (never code), and flags gaps. Extends design-brief.
-
theanirudhkumar Bundle Estimate From PrecedentCorrects a time or effort estimate by checking it against how long similar work actually took last time, instead of how long this instance feels like it should take. Trigger when the user says "how long will this actually take", "estimate this", "how long should I budget for", "is this timeline realistic", "we always run over on these, why", "sanity check my estimate", "how long did this take last time", or gives a time estimate and asks whether it holds up. Also trigger when a scope-the-work note or a delegate allocation needs a time figure attached. Asks for the closest past cases, pulls their actual duration, and adjusts the estimate toward that reference class rather than the gut number, naming the gap and why. Ends on an adjusted estimate with the reference cases shown, not a bare number. Not for cost in money, and not useful without a comparable past case; without one it says so rather than inventing a reference class.
-
jegly Bundle Budget TrackerTrack daily expenses and income. Use when the user wants to log spending, record a purchase, add income, or see a budget summary.
-
vlinr Skill Fw Task Plan CheckpointLong-task step-by-step execution and checkpoint resume skill. Used for multi-step tasks such as feature implementation, refactoring, troubleshooting, and migration. Requires generating a detailed plan in a temporary run directory first, then executing step by step with continuous state write-back. Supports users referencing step IDs directly to rerun or modify a step. If context or token budget approaches its limit, automatically outputs a task handoff file recording key terms, completed items, incomplete items, and next execution instructions for seamless continuation.
-
relexlegal Skill Relex IntakeRun an end-to-end client intake in Relex — find the request, write the intake note, make an agreement from a template, get it e-signed, and invoice the client. PII-safe id-only flow (client is a server-resolved guest ref, never a name/email). Organisation-only; notarization/e-filing are Enterprise.
-
datajinipk Bundle StewardSenior HSE, ESG, and Decarbonisation Specialist for oil & gas, refining, petrochemical, polymer, upstream, and energy projects. Use whenever the user mentions HSE management system (HSE-MS), ISO 14001 environmental management, ISO 45001 occupational health & safety, OHSAS 18001, ISO 50001 energy management, IOGP standards, IPIECA reporting, GRI Standards (Global Reporting Initiative), SASB, TCFD (Task Force on Climate-related Financial Disclosures), ISSB (IFRS S1/S2), CSRD (Corporate Sustainability Reporting Directive), CDP, Science Based Targets initiative (SBTi), Scope 1/2/3 GHG accounting (GHG Protocol), CO2e, CO2 equivalent, methane intensity, OGMP 2.0 (Oil & Gas Methane Partnership), flare reduction, fugitive emissions, leak detection and repair (LDAR), OGCI (Oil & Gas Climate Initiative), Aiming for Zero methane, IMO 2020 sulphur cap (0.5%), IMO 2050 GHG strategy, IMO 2030 / 2040 / 2050 carbon-intensity targets, MARPOL Annex VI, Tier III NOx, scrubber (open-loop / closed-loop), VLSFO / ULSFO / HFO / MGO
Frequently asked questions
What are Finance & Business agent skills?
Finance agent skills bring structure to money-related work: financial models, accounting workflows, invoices, budgeting, and market analysis. Your AI agent loads the skill when the task matches and follows its rules, in any agent that reads SKILL.md files.
Which Finance & Business skills are most installed?
Popular Finance & Business skills on SkillMD right now include giggster-search, dstack-investigate, kijito-recall. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Finance & Business 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.