budget-planning
Create and manage budgets with variance analysis and departmental allocation. Use when the user requests budget planning or provides relevant inputs for this workflow.
git clone --depth 1 https://github.com/seb1n/awesome-ai-agent-skills /tmp/budget-planning && cp -r /tmp/budget-planning/finance-and-accounting/budget-planning ~/.claude/skills/budget-planningSKILL.md
# Budget Planning Create structured budgets by department, track actual spending against targets, and produce variance analyses that explain deviations. This skill supports top-down and bottom-up budgeting approaches, handles multi-department allocation, and generates actionable reports that highlight where spending is on track and where corrective action is needed. ## Workflow 1. **Gather Historical Data** Collect 6-12 months of actual spending data broken down by department and cost category. Identify trends, seasonal patterns, and one-time expenses that should be excluded from baseline calculations. Compute trailing averages and growth rates for each line item to establish a data-driven starting point. 2. **Set Budget Targets by Department** Define top-level budget envelopes for each department based on company revenue targets, strategic priorities, and historical run rates. Apply growth adjustments — departments investing in new initiatives may get 15-25% increases while mature cost centers target flat or declining budgets. Ensure the sum of department budgets aligns with the company-wide operating expense target. 3. **Allocate Line Items** Break each department budget into specific line items: personnel (salaries, benefits, contractors), software and tools, travel, marketing spend, office and facilities, professional services, and discretionary. Assign monthly phasing — some costs are evenly distributed while others are front-loaded (annual software renewals) or seasonal (Q4 marketing pushes). 4. **Track Actuals vs. Budget** As actual spending data comes in, map each transaction to the corresponding budget line item and period. Calculate period-to-date (MTD, QTD, YTD) actuals and compare against the phased budget. Compute both absolute dollar variance and percentage variance for each line item. 5. **Generate Variance Reports** Produce variance analysis showing over- and under-budget categories with explanations. Classify variances as timing (spending shifted between months but will normalize), volume (more/less activity than planned), rate (unit costs differ from plan), or permanent (structural change requiring budget revision). Project year-end estimates based on current run rates. 6. **Recommend Adjustments** Based on variance trends, recommend specific budget reallocations: pull forward unused budget from under-spending departments to cover overages elsewhere, or flag line items where a formal budget revision is warranted. Provide a revised forecast alongside the original budget for comparison. ## Usage Provide historical spending data, department structure, and any top-level targets or constraints. Specify the budget period (monthly, quarterly, annual) and any known upcoming expenses. **Example prompt:** > Create a Q1 2025 budget for our Engineering, Marketing, and G&A departments. Engineering had $180K/month average spend last quarter, Marketing $95K, G&A $45K. We're targeting 10% overall expense reduction. Show the budget with monthly phasing and major line items. ## Examples ### Example 1: Quarterly Department Budget **Input:** 3 departments, Q1 2025, 10% reduction target from Q4 2024 baseline of $320K/month. **Output — Q1 2025 Budget:** | Line Item | Department | January | February | March | Q1 Total | |----------------------------|-------------|-----------|-----------|-----------|------------| | Salaries & Benefits | Engineering | $112,000 | $112,000 | $112,000 | $336,000 | | Contractors | Engineering | $25,000 | $25,000 | $20,000 | $70,000 | | Cloud Infrastructure | Engineering | $18,500 | $19,000 | $19,500 | $57,000 | | Software & Tools | Engineering | $8,200 | $6,200 | $6,200 | $20,600 | | **Engineering Subtotal** | | **$163,700** | **$162,200** | **$157,700** | **$483,600** | | Salaries & Benefits | Marketing | $42,000 | $42,000 | $42,000 | $126,000 | | Advertising & Paid Media | Marketing | $22,000 | $25,000 | $28,000 | $75,000 | | Events & Sponsorships | Marketing | $5,000 | $2,000 | $12,000 | $19,000 | | Content & Creative | Marketing | $8,000 | $8,000 | $8,000 | $24,000 | | **Marketing Subtotal** | | **$77,000** | **$77,000** | **$90,000** | **$244,000** | | Salaries & Benefits | G&A | $22,000 | $22,000 | $22,000 | $66,000 | | Rent & Facilities | G&A | $12,000 | $12,000 | $12,000 | $36,000 | | Insurance & Legal | G&A | $4,500 | $4,500 | $4,500 | $13,500 | | Office & Miscellaneous | G&A | $2,500 | $2,500 | $2,500 | $7,500 | | **G&A Subtotal** | | **$41,000** | **$41,000** | **$41,000** | **$123,000** | | **Company Total** | | **$281,700** | **$280,200** | **$288,700** | **$850,600** | **vs. Baseline:** Q4 2024 run rate was $320K/month ($960K/quarter). Q1 budget of $850.6K represents an 11.4% reduction, exceeding the 10% target by $9.4K. ### Example 2: Variance Analysis Report **Input:** February actuals received, compare against Q1 budget from Example 1. **Output — February Variance Report:** | Line Item | Budget | Actual | Variance $ | Variance % | Classification | |--------------------------|-----------|-----------|------------|------------|----------------| | Engineering — Salaries | $112,000 | $112,000 | $0 | 0.0% | On track | | Engineering — Contractors| $25,000 | $31,200 | +$6,200 | +24.8% | Volume | | Engineering — Cloud | $19,000 | $22,400 | +$3,400 | +17.9% | Volume | | Engineering — Software | $6,200 | $6,200 | $0 | 0.0% | On track | | Marketing — Salaries | $42,000 | $42,000 | $0 | 0.0% | On track | | Marketing — Advertising | $25,000
Design reproducible evaluations for AI agents with representative task sets, explicit rubrics, appropriate graders, baselines, regression gates, and failure analysis. Use when defining agent quality, comparing prompts or models, validating a release, measuring tool-use reliability, investigating regressions, or deciding whether an agent is ready for production.
Design privacy-aware observability for AI agents using traces, spans, structured events, metrics, cost attribution, dashboards, alerts, and investigation workflows. Use when instrumenting an agent, debugging intermittent tool or model failures, defining service-level objectives, analyzing latency or spend, auditing agent decisions, or preparing production monitoring.
Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows. Use when deciding which agent actions require review, adding approve/reject or dual-control flows, preventing unauthorized autonomous effects, creating decision records, reducing rubber-stamping, or recovering safely from rejected, expired, or failed actions.
Design, implement, harden, and verify Model Context Protocol (MCP) servers with precise tool contracts, least-privilege authorization, safe transports, structured errors, and interoperability tests. Use when creating a new MCP server, exposing an API or data source through MCP, reviewing an MCP server design, adding or revising MCP tools, or preparing an MCP server for production.
Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis. Use when a task contains genuinely independent workstreams, specialized roles, parallel research or implementation, reviewer-worker loops, or coordination problems that one agent should not execute sequentially.
Design and validate model-facing tool definitions with clear names, action-oriented descriptions, bounded JSON Schema parameters, explicit side effects, safe defaults, idempotency, errors, and realistic tests. Use when creating function-calling tools, MCP tools, agent actions, structured tool inputs, or when a model selects the wrong tool, invents arguments, or causes unsafe side effects.
Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved environment.
Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.