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.
-
xjli360 Bundle Sealeap Baize Amazon Budget Placement ControlControl Amazon ad budget and placement as separate levers, diagnosing when click acceleration dilutes conversion and when additional budget can extend profitable traffic. Use for 加预算后转化下降、点击太快、怎么调顶部和商品页、预算不足还是竞价过高.
-
xjli360 Bundle Sealeap Baize Amazon Conversion First ScalingScale Amazon ad traffic only after conversion quality, click velocity, budget continuity, inventory, and contribution economics show that broader reach can be absorbed. Use for 点击突然变多转化下降、要不要加预算、自然排名与广告扩量、维护新品转化.
-
xjli360 Bundle Sealeap Baihu Amazon Multimarket Peak KeywordsBuild localized, evidence-backed Amazon keyword plans for seasonal peaks across multiple marketplaces. Use when preparing listings and ads for an event while preventing literal translation, shared-budget assumptions, and cross-market data leakage.
-
xjli360 Bundle Sealeap Amazon Scalable Seller Operating SystemDesign a scalable Amazon seller operating system using category specialization, portfolio capacity, operator skill tiers, SOP floors, experiment governance, incentives, and resource allocation. Use when the user asks how a small team can manage more products, improve operator productivity, allocate launches, or balance expert autonomy with standardized processes. Do not repeat anecdotal revenue claims as benchmarks.
-
xjli360 Bundle Sealeap Tengshe Amazon Portfolio Budget TriageTriage a large Amazon ASIN portfolio into protect, prove, repair, harvest, or exit cohorts using contribution, evidence, maturity, inventory, and strategic value. Use when ad budget is scarce and many products cannot learn effectively.
-
xjli360 Bundle Sealeap Xiezhi Amazon Small Budget Fba ValidationPlan a small-budget, part-time Amazon FBA validation with explicit cost, timeline, product count, and stop-loss assumptions. Use when a beginner wants to test the full operating loop without a large upfront commitment.
-
swan-gtm Bundle Qbr Ebr BuilderDesign and build customer business reviews that buyers actually attend: QBR (operational cadence) and EBR (executive cadence), with the value recap in the customer's own numbers as the load-bearing artifact. Triggers on 'QBR,' 'EBR,' 'business review,' 'executive business review,' 'quarterly review deck,' 'prove value to the customer,' 'renewal conversation prep,' 'customer stopped attending reviews,' 'our QBRs are a feature parade,' 'success plan review,' or any situation where post-sale value needs to be demonstrated to the people who pay, not just the people who use. BOUNDARY: account-health scanners produce the internal diagnostic BEFORE the review; this skill builds the customer-facing instrument itself and starts from their output. renewal-save-motion owns the intervention when a review surfaces risk; expansion-revenue-architect owns the motion when it surfaces headroom; this skill hands off to both and runs neither. revenue-operating-cadence owns INTERNAL meeting architecture; a business review is a cu
-
swan-gtm Skill Message ValidationUse this skill when validating which ad messages actually drive revenue — connecting ads to downstream lead quality and scaling only validated messages.
-
swan-gtm Skill Ads Scaling QuadrantUse this skill when deciding how to scale paid spend — the budget-by-creative quadrant and which lever to pull based on current performance.
-
swan-gtm Skill Ads Budget AllocationUse this skill when allocating paid budget by stage — testing vs scaling vs retargeting, and how the split shifts as spend grows.
-
swan-gtm Skill Ads Channel SelectionUse this skill when choosing paid channels — where Meta, LinkedIn, and search each win for B2B, and how to sequence them by budget and motion.
-
swan-gtm Skill Google Ads Ppc MathUse this skill when someone asks for a budget projection, a ROAS or CPA target, an impression-share opportunity estimate, or any paid-search math from numbers they already have — no live account access needed. Produces a shown-work table with a sensitivity check, not just a final number. Triggers: budget projection, ROAS calculation, CPA target, conversion forecast, impression share opportunity, break-even ROAS, "what would happen if."
-
swan-gtm Bundle Founder Post Triggers 24Use this skill when a founder has no results to point at and needs something to publish — "I have nothing to post about", "what do I write when we haven't launched", "who would even listen to me", "should I build a personal brand", "our CAC is climbing and we have no budget". Twenty-four things that already happened this week and are publishable, in five categories, plus the play selector, copy-paste opening lines, and the pre-publish check.
-
swan-gtm Skill Meta Ads Operating SystemUse this skill for any operational decision on a Meta account — pause, scale, graduate, budget, creative count. The decision framework with the formulas, thresholds, and actions.
-
bromso Skill Trial BalanceVerify that total debits equal total credits across all ledger accounts
-
bromso Skill ReconciliationReconcile balances between related accounts or external statements
-
bromso Skill Adjusted BalanceVerify updated account balances after posting adjusting entries
-
bromso Skill Capacity PlanningPlan team capacity across sprints accounting for holidays and availability
-
antins-labs Bundle Openbudget Lacity OrgLA City Open Budget Access Skill
-
robsonkades Bundle Timeouts And DeadlinesBounding how long a call may take and propagating that bound: per-hop timeouts versus an absolute deadline, deadline propagation over HTTP and gRPC, remaining-budget arithmetic and refusing work that cannot finish, cooperative cancellation of abandoned callee work, and keeping connect, read, total and retry timeouts consistent. Use when a client sets a connect timeout but no request timeout, when Future.get() or join() is called with no bound, when a timeout is a round number repeated across services, when three hops each wait five seconds, when a retry policy total exceeds the caller timeout, when a JDBC call has no setQueryTimeout, when a Kafka consumer rebalances during slow processing, or when a timed-out request leaves work running downstream. Does not cover what to do after the timeout fires (retries-and-backoff), percentiles (latency-statistics), tail decomposition (tail-latency-analysis), tripping on repeated timeouts (circuit-breakers), or pool sizing (connection-pool-sizing).
-
robsonkades Bundle Incident Evidence CapturePreserving decision-grade JVM incident evidence before remediation destroys it: setting an explicit recovery/evidence budget, selecting representative and control instances, copying existing telemetry first, capturing repeated low-risk state, escalating to JFR, heap, or core evidence only by symptom and approval, surviving containers/restarts, and recording integrity, clocks, provenance, privacy, and capture failures. Use during live degradation, impending restart/OOM, an unresponsive JVM, or runbook design. Owns ordering and safety; artifact-specific analysis belongs to heap-dump-analysis, concurrency-diagnostics, jfr-and-async-profiler, gc-log-analysis, and jhsdb-and-core-dumps.
-
robsonkades Bundle Distributed Systems TestingTesting the failure behaviour a distributed system claims: injecting latency, errors, partitions and process death; verifying that timeouts, retries, breakers and fallbacks do what their configuration says; proving idempotency against duplicate delivery; and running a controlled experiment in production rather than a chaos tool. Use when resilience configuration exists but has never been exercised, when a timeout or retry budget is being chosen, when an incident was caused by a dependency being slow rather than down, when a consumer is assumed idempotent, when a rollout is protected by a probe nobody has failed on purpose, or when chaos engineering is proposed without a hypothesis. Does not cover the in-process test pyramid and architecture rules (architecture-testing), thread-level race testing (concurrency-testing), throughput and saturation measurement (load-testing), or the remedies themselves (retries-and-backoff, circuit-breakers, timeouts-and-deadlines).
-
robsonkades Bundle Object Layout And FootprintSizing a data structure in bytes before it exists. Use when a shape is chosen for millions of instances — record, class, primitive array, parallel arrays or boxed collection; when an array is proposed to save the header; when HashMap<Integer,Integer> or List<Long> is on a bulk path; when -XX:+UseCompactObjectHeaders is evaluated for footprint; or when smaller objects are expected to buy shorter GC pauses without a collector-specific measurement. Answers in bytes per element; one record-versus-array example reverses under the JDK 27 default (JEP 534, not yet GA). Sizing a replacement belongs here; measuring what exists is heap-dump-analysis. Not flag lifecycle (jvm-performance-review), @Contended padding (false-sharing-and-contended), cache hierarchy (cpu-cache-and-numa), allocation rate (allocation-profiling), container budget (jvm-memory-regions), compressed class space (metaspace-internals), off-heap memory (off-heap-memory), or sharing duplicates (gof-flyweight).
-
robsonkades Bundle Epsilon And Shenandoah InternalsEpsilon as a measurement instrument (isolating allocation cost, failing fast against an allocation budget, sizing from time-to-OOM) and Shenandoah internals (the load reference barrier, the concurrent phase sequence, generational mode and its card-table remembered set, the heuristics and their thresholds, pacing, and the degenerated-versus-full fallbacks). Use when a hot path is claimed to be allocation-free, when benchmark numbers are polluted by collection, when an Epsilon catch block never runs, when "Degenerated GC" appears in a Shenandoah log, when Shenandoah latency rises with no pause in the log, when a Shenandoah comparison does not state its ShenandoahGCMode, when the LRB is called a read barrier or charged 8 bytes per object, or when an Epsilon example omits -XX:+UnlockExperimentalVMOptions. Does not cover choosing between or operating the concurrent collectors (zgc-and-shenandoah), finding which code allocates (allocation-profiling), or establishing whether GC is the bottleneck (jvm-gc-tuning).
-
robsonkades Bundle Grpc Http2 Service Mesh PerformanceDiagnosing and designing the performance of gRPC and HTTP/2 communication paths, including channel, connection and stream topology, flow control, serialization, Netty event loops, TLS connection churn and service-mesh proxy cost. Use when multiplexed traffic is skewed or stalls, a channel pool or HTTP/2 setting is proposed, mesh overhead consumes a material latency or CPU budget, or retries exist in both client and proxy. API semantics belong to rpc-and-api-contracts; TCP behavior to tcp-tuning; routing ownership to load-balancing-and-routing.
-
bromso Skill BudgetAllocate expenses by department and set spending guardrails
-
bromso Skill ReviewMonitor performance against budget, analyze variances, and reforecast
-
bromso Skill CloseClose temporary accounts and transfer balances to retained earnings
-
bromso Skill ForecastProject revenue, expenses, and cash flow over the planning horizon
-
bromso Skill AdjustRecord accruals, deferrals, depreciation, and other period-end adjustments
-
bromso Skill LedgerPost journal entries to the general ledger and compute running balances
-
bromso Skill AnalyzeIdentify and review financial transactions from source documents
-
bromso Skill JournalRecord journal entries with debits and credits for each transaction
-
bromso Skill ControlsDesign internal controls to prevent errors and fraud
-
bromso Skill VarianceCompare actual financial results against budget or forecast
-
bromso Skill StatementsPrepare income statement, balance sheet, and cash flow statement
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 sealeap-baize-amazon-budget-placement-control, sealeap-baize-amazon-conversion-first-scaling, sealeap-baihu-amazon-multimarket-peak-keywords. 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.