Skip to content

JPeetz/agent-skills / skills/finance-ops/month-end-close

month-end-close

Verified

Use this skill when managing month-end financial close, running account reconciliations, preparing close checklists, or analyzing close efficiency. Activates on "month-end close", "close the books", "reconciliation", "bank reconciliation", "accrual", "prepaid", "deferred revenue", "close checklist", "trial balance", "variance analysis", "flux analysis", "journal entry", "close calendar", or "financial close". Covers close calendars and checklists, bank and balance-sheet reconciliations, accrual and prepaid schedules, deferred revenue roll-forward, journal entry drafting, trial balance and flux review, and close-cycle time reduction.

FileKindSize
CHANGELOG.mdmarkdown2.6 KB
LICENSEother1.0 KB
SKILL.mdskill md29.3 KB
evals/evals.jsonconfig9.7 KB
references/close-framework.mdmarkdown11.9 KB
scripts/close_checklist.pyscript34.2 KB

CHANGELOG.md

View on GitHub
# Changelog

All notable changes to this skill are documented here. Format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), versioning follows [SemVer](https://semver.org/).

## [1.0.0] — 2026-11-16

### Added
- Initial release.
- `SKILL.md` — the month-end close workflow: three-phase calendar model
  (pre-close D-5→D-1, core close D+1→D+5, review D+6→D+8), day-by-day checklist
  with owners and evidence artifacts, bank reconciliation procedure with tiered
  matching rules and tolerances, accrual schedules with reversal and true-up
  discipline, prepaid amortization and deferred revenue roll-forward, trial
  balance review (out-of-balance detection, unusual movements, flux vs prior
  period), budget-vs-actual variance analysis, journal entry anatomy and approval
  matrix, close efficiency metrics, workflow optimization levers, and a
  14-row anti-patterns table.
- `scripts/close_checklist.py` — stdlib-only checklist generator. Scopes the
  task library to the entity's active modules, computes status against the
  current close day (overdue / due today / upcoming / done), totals estimated
  hours by owner, warns on uncovered modules and unassigned roles, and emits
  markdown or JSON. Validates entity, period format, module ids, materiality,
  team values and day tokens; exits non-zero on bad input. 34 built-in
  self-test checks via `--self-test`.
- `references/close-framework.md` — the phase model with exit criteria per
  phase, the full task inventory, role and segregation-of-duties matrix, the
  close-calendar contract and its failure modes, acceleration strategies in
  return-on-effort order, soft-close vs hard-close guidance, and interactions
  with adjacent processes.
- `evals/evals.json` — four positive and two negative evaluation cases covering
  scoped checklist generation, a bank rec with an unexplained residual, accrual
  and reversal discipline, close-efficiency diagnosis, and two near-miss
  routing cases (revenue-recognition policy, vendor payment dispute).
- `LICENSE` (MIT), `CHANGELOG.md`.

### Notes
- Extends the `finance-ops` category alongside `saas-metrics-coach`; the two are
  complementary (recognised revenue and reported metrics vs. the close
  procedure that produces them).
- Materiality, tolerances and day offsets are parameters, not defaults to be
  silently assumed — the script warns when materiality is unset.
- The skill states accounting procedure, not accounting policy. Policy decisions
  (revenue recognition treatment, capitalisation thresholds, restatement calls)
  route to technical accounting review.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall