功能描述

AR Collections & Aging Analysis pipeline for QBO clients. Produces a 7-tab Excel workbook with AR aging buckets (Current/1-30/31-60/61-90/90+), DSO, collecti...

使用说明 (SKILL.md)

AR Collections & Aging Analysis Skill

Name: AR Collections
Author: samledger67-dotcom

What This Does

Runs the AR Collections & Aging Analysis pipeline (scripts/pipelines/ar-collections.py) to produce a controller-level accounts receivable workbook from QBO data.

Produces:

AR aging bucketed into Current | 1-30 | 31-60 | 61-90 | 90+ days
Aging metrics: total AR, weighted average days outstanding, concentration risk
Collection priority scoring per customer (HIGH / MEDIUM / LOW / MONITOR)
Recommended collection actions per customer
Bad debt reserve (percentage-of-aging method)
Payment pattern analysis from GL history
DSO: current period and rolling 3-month
CDC: which customers improved or deteriorated since last run
Excel workbook (7 tabs)

When to Use

Use when:

Client asks for AR aging report, collections status, or DSO
Monthly close includes AR review
Need to know who owes money and what to do about it
Bad debt reserve needs to be calculated for month-end
Auditors or investors request AR aging schedule

Do NOT use when:

Client SOP says AR is not applicable (pipeline exits gracefully — no report needed)
Client collects at point of sale (e.g., SB Paulson / Willo Salons)
Running for a non-QBO client (no data source)
User wants a P&L or balance sheet (use pl-deep-analysis or client-dashboard)

SOP Gate

The pipeline automatically checks the client SOP before pulling any data:

sb-paulson → exits gracefully with explanation (POS collection, no AR)
Unknown slugs → checks SOP markdown for AR-disabled signals, defaults to AR-applicable

To add a new client's AR status, update CLIENT_AR_CONFIG in the pipeline, OR add these markers to their clients/{slug}/sop.md:

**AR Aging:** ❌ Not applicable (POS collection)

Usage

# Standard run — as of end of month
python3 scripts/pipelines/ar-collections.py --slug \x3Cclient-slug> --as-of 2026-03-31

# With custom output directory
python3 scripts/pipelines/ar-collections.py --slug \x3Cclient-slug> --as-of 2026-03-31 --out ~/Desktop/reports

# Skip GL pull (faster, no payment pattern analysis)
python3 scripts/pipelines/ar-collections.py --slug \x3Cclient-slug> --as-of 2026-03-31 --skip-gl

# QBO sandbox
python3 scripts/pipelines/ar-collections.py --slug \x3Cclient-slug> --as-of 2026-03-31 --sandbox

# Client with no AR — exits gracefully
python3 scripts/pipelines/ar-collections.py --slug sb-paulson --as-of 2026-03-31

Output

Default location: reports/ar-collections/ar-collections_{slug}_{as-of}.xlsx

Tabs:

Tab	Contents
AR Summary	Aging snapshot by bucket, key metrics, concentration risk
Aging Detail	Invoice-level list: customer, date, due date, balance, bucket
Collection Priority	Sorted action list: HIGH/MEDIUM/LOW/MONITOR with recommended actions
Payment Patterns	Avg days to pay per customer, vs. terms, reliability rating
Bad Debt Reserve	Percentage-of-aging reserve calc + suggested journal entry
DSO Analysis	Current and rolling 3-month DSO, monthly revenue detail
CDC Log	Changes since last run: improved / deteriorated / new / cleared

Collection Priority Logic

Priority	Criteria	Recommended Action
HIGH	90+ days past due OR balance > $5K	Escalate / demand letter / write-off review
MEDIUM	61-90 days OR balance > $2.5K	Follow-up call
LOW	31-60 days	Send email reminder
MONITOR	Current or 1-30 days	Standard review next cycle

Bad Debt Reserve Rates (Percentage-of-Aging)

Bucket	Rate
Current	1%
1-30	3%
31-60	10%
61-90	25%
90+	50%

DSO Formula

Current DSO = (AR Balance ÷ Current Period Revenue) × Days in Period
Rolling DSO = AR Balance ÷ (3-Month Revenue ÷ 90 days)

CDC Cache

Cached at: .cache/ar-collections/{slug}.json

Each run saves customer balances and worst buckets. Next run computes:

Improved — balance decreased or bucket moved earlier
Deteriorated — balance increased or bucket moved later
New — first appearance in AR
Cleared — balance went to zero (collected)

Requirements

pip install openpyxl
# Node.js QBO client must be auth'd
node bin/qbo info {slug}  # from your QBO integration directory

Related Pipelines

pl-deep-analysis.py — GL drill-down, P&L variance, accrual proposals
client-dashboard.py — KPI dashboard (includes DSO as a KPI)
bank-reconciliation.py — Bank rec (not AR-specific)
budget-vs-actual.py — BvA (revenue-side context for AR)

Clients

Configure AR applicability per client in CLIENT_AR_CONFIG or via clients/{slug}/sop.md.

安全使用建议

Before installing or invoking this skill, verify these points: (1) The skill assumes you have an existing repository with scripts/pipelines/ar-collections.py and a Node.js QBO client — the skill bundle does not include these files. Do not run it unless those scripts and the QBO client exist and are reviewed. (2) QBO access requires credentials (API keys or OAuth tokens); the skill does not declare or explain required env vars. Ensure you only provide least-privilege credentials scoped to read AR data and audit/rotate them. (3) The pipeline will read clients/{slug}/sop.md and may update CLIENT_AR_CONFIG and write .cache/ar-collections/{slug}.json and reports/ files — confirm you’re comfortable with those repository writes and with any PII in the outputs. (4) Run first in a sandboxed environment or QBO sandbox to confirm behavior and outputs. (5) If you intend to let an autonomous agent invoke this skill, restrict its permissions and network access and require an explicit review step before it runs against production credentials. If the author can provide the missing script files or document exactly what credentials/config are needed, re-evaluate; as-is the omission of declared credentials and the assumption of local scripts makes the skill's runtime requirements unclear.

功能分析

Type: OpenClaw Skill Name: ar-collections Version: 1.0.2 The skill bundle contains metadata and documentation for an Accounts Receivable (AR) aging and collections analysis tool. The SKILL.md file outlines legitimate financial reporting logic, including DSO formulas, bad debt reserve calculations, and integration with QuickBooks Online (QBO) via a local Python script (scripts/pipelines/ar-collections.py). There are no indicators of malicious intent, prompt injection, or unauthorized data exfiltration.

能力评估

ℹ Purpose & Capability

The name, description, and runtime instructions consistently describe an AR Collections & Aging pipeline that pulls QBO data, computes metrics, and writes an Excel workbook and a local CDC cache. That purpose aligns with the commands shown (python script, node QBO client). However, the skill metadata declares no required credentials, binaries, or config paths even though the instructions explicitly require a Node.js QBO client to be authenticated and a local repository layout (scripts/pipelines/ar-collections.py, clients/{slug}/sop.md). This mismatch (expected QBO credentials and local scripts vs. declared 'none') is an incoherence.

⚠ Instruction Scope

SKILL.md instructs the agent/operator to run a local Python script (scripts/pipelines/ar-collections.py), call a Node.js QBO client (node bin/qbo info {slug}), read clients/{slug}/sop.md and write outputs to reports/... and .cache/ar-collections/{slug}.json. Those actions are within the stated purpose, but the skill gives the agent broad discretion to read and write repository files and caches and to contact QBO via the node client — none of which are declared in the skill metadata. Also, the actual script files are not included in the skill bundle; the instructions assume they exist in the runtime environment. This could cause failures or unexpected behavior if the runtime environment differs, and it hides required credentials and file access from the metadata.

ℹ Install Mechanism

Instruction-only skill (no install spec, no code files) — lower install risk because nothing is written by the skill bundle itself. The README suggests pip installing openpyxl and requires an authenticated Node.js QBO client; those are normal for this pipeline but are not enforced or declared in metadata. Because the skill will rely on external, out-of-band tooling and repo files, the installation/operational burden is on the host environment rather than the skill — this is expected but should be explicit.

⚠ Credentials

The pipeline needs authenticated access to QBO via a Node.js client, which implies API keys/tokens or OAuth credentials, but the skill declares no required environment variables or primary credential. That omission is disproportionate: a QBO-integrating pipeline should declare the type of credential it uses (and any config paths) so operators can review before enabling. The instructions also allow writing to .cache/ and reports/ without declaring or gating file paths.

✓ Persistence & Privilege

always is false and there is no install-time modification of other skills or global agent settings. The pipeline writes to its own .cache and reports directories and suggests updating CLIENT_AR_CONFIG or clients/{slug}/sop.md, which is normal for a repo pipeline but does mean it will modify repository files if run with write permissions. That behavior is scoped to the project; it does not request elevated platform privileges in the metadata.

版本历史

v1.0.2

Updated SKILL.md

v1.0.1

Security cleanup: removed internal references, genericized examples

v1.0.0

Initial release: AR aging pipeline with DSO, bad debt reserve, collection priority scoring

元数据

Slug ar-collections

版本 1.0.2

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 3

常见问题

AR Collections 是什么？

AR Collections & Aging Analysis pipeline for QBO clients. Produces a 7-tab Excel workbook with AR aging buckets (Current/1-30/31-60/61-90/90+), DSO, collecti... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 245 次。

如何安装 AR Collections？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install ar-collections」即可一键安装，无需额外配置。

AR Collections 是免费的吗？

是的，AR Collections 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

AR Collections 支持哪些平台？

AR Collections 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 AR Collections？

由 samledger67-dotcom（@samledger67-dotcom）开发并维护，当前版本 v1.0.2。

AR Collections