reconciliation
Skill21 starsChanged 4 months agoMITView on GitHub
Matches two datasets — bank vs ledger, subledger vs GL — via exact matching, fuzzy matching (amount tolerance, date window, reference similarity), and split detection; buckets exceptions (timing, missing, duplicate, amount mismatch), ages unmatched items, proposes adjusting entries, and proves the bridge between the two balances. Use when the user says 'reconcile the bank statement', 'these two reports don't agree', or 'the AR subledger is off from the GL'.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- microsoft/MicroHacktheir own version, first seen Nov 8, 2026
- microsoft/cat-agent-skillstheir own version, first seen Nov 8, 2026
- nisarth/claude-skills-storetheir own version, first seen Nov 8, 2026
- insight68/Skillstheir own version, first seen Nov 8, 2026
- anthropics/knowledge-work-pluginstheir own version, first seen Oct 13, 2026
- IngAs8/ClaudeSkilltheir own version, first seen Sep 28, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- anthropics/knowledge-work-plugins★ 35ksame name
- microsoft/MicroHack★ 220same name
- microsoft/cat-agent-skills★ 101same name
- google-gemini/gemini-managed-agents-templates★ 99same name
- insight68/Skills★ 5same name
- 1398281322-a11y/java-backend-guardrails★ 2same name
- miptah21/skills★ 2same name
- nisarth/claude-skills-store★ 1same name
- awesomeclaude666/ClaudeCodeProject★ 0same name
- IngAs8/ClaudeSkill★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository63 other files it gives its agents.
- account-intelligenceSkill
- account-researchSkill
- ad-creativeSkill
- agent-evaluationSkill
- agent-reliabilitySkill
- ai-adoption-leadSkill
- ai-data-stewardSkill
- ai-seoSkill
- ai-workflow-architectSkill
- appsec-reviewSkill
- audit-supportSkill
- brand-guidelinesSkill
- call-prepSkill
- cash-flow-snapshotSkill
- chief-of-staffSkill
- claude-memSkill
- close-managementSkill
- compliance-checkSkill
- context7Skill
- copywritingSkill
- croSkill
- cto-advisorSkill
- customer-researchSkill
- draft-outreachSkill
- financial-statementsSkill
- frontend-designSkill
- growth-engineeringSkill
- growth-experimentsSkill
- growth-strategySkill
- hook-generatorSkill
- invoice-chaseSkill
- journal-entrySkill
- lead-magnetsSkill
- legal-risk-assessmentSkill
- lifecycle-growthSkill
- margin-analyzerSkill
- mcp-builderSkill
- objection-handlerSkill
- pipeline-reviewSkill
- plan-payrollSkill
- post-writerSkill
- profile-optimizerSkill
- proposal-builderSkill
- reels-scriptingSkill
- revenue-operationsSkill
- review-contractSkill
- run-campaignSkill
- signature-requestSkill
- skill-creatorSkill
- skill-vettingSkill
- superpowersSkill
- tasteSkill
- tax-prepSkill
- token-accountantSkill
- transitionsSkill
- triage-ndaSkill
- ui-ux-pro-maxSkill
- variance-analysisSkill
- vendor-checkSkill
- voice-builderSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
Propose adjusting entries: only for genuine book errors (unbooked bank fee, duplicate posting) — full balanced journals in the …
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Reconciliation — Reconciler
"Reconcile the books."
When to use
- Bank vs ledger — "reconcile June's bank statement against GL cash".
- Subledger vs GL — "the AR subledger says 412k, the GL says 405k — why?".
- Processor vs books — "match Stripe payouts to booked revenue".
- Intercompany — "our payable to the sub doesn't equal their receivable from us".
- Any two lists that should agree and don't.
Workflow
- Load both sides with code (pasted data or CSV/XLSX — never eyeball long columns). Standardize columns (date, amount, reference, description), normalize signs and currency, drop exact re-export duplicates. Record each side's row count and total — these anchor the bridge.
- Exact pass. Match on amount + date (+ reference when present); remove matched pairs from the pool.
- Fuzzy pass, rules tightening in order: amount within tolerance (default ±0.01 — widen only with user sign-off), date within window (default ±3 business days), reference/description similarity. Log every fuzzy match with the rule that made it.
- One-to-many pass. Detect splits and batches (one bank deposit = several ledger receipts) via combination sums inside the date window.
- Bucket every leftover: timing (legit, will clear — deposits in transit, outstanding checks), missing (no counterpart expected — unbooked fees, unrecorded receipts), duplicate (same item twice on one side), amount mismatch (paired but different — show the delta).
- Age the unmatched by days outstanding: 0–7, 8–30, 31–60, 60+. Anything over 30 days gets a priority flag.
- Propose adjusting entries only for genuine book errors (unbooked bank fee, duplicate posting) — full balanced journals in the
journal-entryskill's format. Timing items never get forced adjustments. - Prove the bridge: side A balance ± each exception bucket = side B balance, computed in code, residual shown. Target 0.00; anything else is stated, never hidden.
Output format
# Reconciliation — <A> vs <B> — <period>
## Bridge
<A> balance <amount>
+ timing: <description> <amount>
− missing on <side>: <desc> <amount>
± mismatches (net) <amount>
= <B> balance <amount>
Residual: 0.00 ✓ (or: <amount> — UNRESOLVED, see exceptions)
## Match summary
Exact: <n> | Fuzzy: <n> (rules logged) | One-to-many: <n> | Unmatched: <n>
## Exceptions
| # | Side | Date | Amount | Ref | Bucket | Age (days) | Action |
|---|------|------|-------:|-----|--------|-----------:|--------|
| 1 | Bank | <date> | <amt> | <ref> | missing | <n> | book JE-R1 |
## Proposed adjusting entries
JE-R1 — <memo> — Dr <account> <amt> / Cr <account> <amt> (support: <ref>)
## Aging of unmatched
0–7: <n> / <amt> | 8–30: <n> / <amt> | 31–60: <n> / <amt> | 60+: <n> / <amt>Quality bar
- Bridge computed in code and proves out; any residual stated explicitly, never hidden.
- Matched + exceptions = input totals on both sides — nothing silently dropped.
- Every fuzzy match shows the rule (tolerance / window / similarity) that made it.
- Every unmatched item bucketed and aged — no "miscellaneous" pile.
- Adjusting entries proposed only for real book errors, each as a balanced JE.
- Tolerances and windows stated up front as assumptions.
Example
Invocation: "Reconcile bank-jun.csv against gl-cash-jun.xlsx."
Produced: 214 of 220 rows matched exact, 3 fuzzy (±2-day window, logged), 1 split deposit resolved; exceptions: two deposits in transit $5,110.00 (timing) and one $45.00 unbooked bank fee (missing → JE-R1); bridge: bank $88,214.16 + 5,110.00 = $93,324.16 = GL $93,369.16 − 45.00, residual 0.00.
Decision support, not accounting advice — material figures belong with your accountant/auditor.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

