finance-review
Review actual results against budget with variance analysis, a KPI scorecard and a reforecast of the remaining periods, plus recommended reallocations. Use when a month or quarter has closed and the u
SKILL.mdskills/finance-review/SKILL.md
GitHubReview
Review financial performance for "$ARGUMENTS". Compare actuals to budget, analyze variances, identify trends, and update the forecast based on new information.
Arguments. $ARGUMENTS may contain the project name and optional flags. Take the first token as <project> and treat --skip-checks as a flag; never include flags in file paths. All paths below use <project>. If --skip-checks is present, skip the prerequisite check and, before writing any artifact, append one line to .singularskills/log.jsonl: {"ts":"<ISO timestamp>","skill":"finance-review","workflow":"finance","phase":6,"project":"<project>","event":"skipped","artifact":"06-review.md","note":"<reason or \"none given\">"}.
Compute with code. Perform every calculation (totals, balances, ratios, variances, projections) with a script — Bash, Python or a spreadsheet formula written to a file — and include the computation alongside the result. Never do arithmetic mentally.
Prerequisites
Part of a workflow. This skill is phase 6 (Review) of the FP&A workflow (finance); cross-domain workflows run it too. First check .singularskills/log.jsonl for an open run for this project: a run-started line with "project":"<project>" and no later run-finished line for the same workflow and project. If one exists, the conductor is running you: continue here. Otherwise, if the user asked to start, run, continue or resume a process or workflow rather than this one step, do not continue here: invoke the workflow skill with the workflow the user asked for, or finance when they named none, followed by <project>; it runs this phase in order, asks before it writes and records the run. Otherwise continue here: a later phase runs on its own, behind its gate.
Run this skill's gate before writing: sh <this skill's folder>/scripts/gate.sh <project> <project root>, where <project root> is the folder that contains .singularskills/ (use . when you are already there). If it exits non-zero, stop and tell the user what it printed, unless --skip-checks was given (see Arguments). On a refusal, before you stop, append this line to .singularskills/log.jsonl (create the folder and file if missing): {"ts":"<ISO timestamp>","skill":"finance-review","workflow":"finance","phase":6,"project":"<project>","event":"refused","artifact":"06-review.md","note":"<what the gate printed>"}. Once the gate has passed, or under --skip-checks once you have appended the skipped line, append this line before you start work: {"ts":"<ISO timestamp>","skill":"finance-review","workflow":"finance","phase":6,"project":"<project>","event":"started","artifact":"06-review.md","note":""}.
Read .singularskills/finance/<project>/05-model.md. If this file does not exist, tell the user:
Phase 5 (Model) has not been completed for "<project>". Run
/finance-model <project>first, or use--skip-checksto bypass.
Process
Read context:
- Read
.singularskills/finance/<project>/02-plan.mdfor KPI targets - Read
.singularskills/finance/<project>/03-forecast.mdfor original projections - Read
.singularskills/finance/<project>/04-budget.mdfor departmental budgets - Read
.singularskills/finance/<project>/05-model.mdfor scenario benchmarks
- Read
Collect actuals:
- Ask the user for actual financial results for the review period
- Revenue actuals by stream
- Expense actuals by department and category
- Cash position and cash flow actuals
- Headcount actuals
Variance analysis:
- Calculate budget vs actual for each line item
- Classify variances: favorable/unfavorable, timing/permanent, volume/price/mix
- Identify the top 5 variances by dollar amount
- Determine root causes for significant variances
KPI scorecard:
- Update each KPI with actual values
- Show trend (improving, stable, declining)
- Flag any KPIs at risk of missing annual target
Reforecast:
- Based on actuals and trends, update the remaining forecast
- Adjust assumptions that have proven incorrect
- Recalculate runway and break-even timing
- Recommend budget reallocations if needed
Write the artifact to
.singularskills/finance/<project>/06-review.mdwith sections:- Period Summary — review period and key headlines
- Variance Analysis — budget vs actual with explanations
- KPI Scorecard — target vs actual vs trend
- Reforecast — updated projections for remaining periods
- Recommendations — actions to take based on findings
- Risks and Watch Items — emerging issues to monitor
Output
The review written to .singularskills/finance/<project>/06-review.md. Present a summary highlighting:
- Performance vs budget (on track, ahead, behind)
- Largest variances and root causes
- Updated runway and key metric trajectory
- Recommended actions
Record the run. After you have written the artifact, append this line to .singularskills/log.jsonl (the started line of Prerequisites, with "event":"finished"): {"ts":"<ISO timestamp>","skill":"finance-review","workflow":"finance","phase":6,"project":"<project>","event":"finished","artifact":"06-review.md","note":""}.
Open the artifact with this frontmatter (agent is the agent you run in, or unknown; gate is passed when the gate ran clean and skipped under --skip-checks):
---
skill: finance-review
workflow: finance
phase: 6
project: <project>
started: <ISO timestamp>
finished: <ISO timestamp>
agent: <the agent you run in, or "unknown">
gate: <passed|skipped>
---
End the artifact with ## Decisions and ## Open questions, in this shape:
## Decisions
- <what was chosen> — <why> — <what was rejected>
## Open questions
- <what the next phase or a reviewer must settle>
End the artifact with this paragraph, verbatim:
Not financial or tax advice. This artifact is generated analysis for review by a qualified accountant or financial professional before any filing, reporting or decision relies on it.