dtsong/accounting-skills · Archived

firm-config

Loads firm-specific accounting configuration including chart of accounts, materiality thresholds, close calendar, approval matrix, and standard mappings. Use at the start of any workflow that needs to apply firm-specific rules rather than generic accounting conventions.

First seen Aug 15, 2026

Installation

$ npx skills add dtsong/accounting-skills --skill firm-config

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from dtsong/accounting-skills.

npx skills add dtsong/accounting-skills

Browse all from dtsong/accounting-skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

License LICENSE
Default branch main
Open issues 0
Status Archived

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,268 B
  • docs SUMMARY.md 289 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 2 installs

SKILL.md

Firm Config

This skill exposes firm-specific configuration. The other skills in this bundle (bank-rec, flux-analysis, prepaid-schedule, pbc-package, je-review) consume it. You will customize this skill per firm. The files in references/ ship as templates with realistic placeholder data clearly marked TEMPLATE — REPLACE.

When to load

At the start of any workflow that needs:

  • Account validation (is this account in our chart?)
  • Materiality threshold application (does this variance exceed our threshold?)
  • Period/calendar awareness (is the date in an open close window?)
  • Approval routing (who signs off at this amount?)

A workflow skill loads firm-config before applying any threshold or validation. If a workflow runs without firm-config available, it must say so explicitly in Review_Notes and use the defaults stated in each reference file.

What's in references/

File Purpose Consumed by
chart-of-accounts.csv All valid GL accounts with descriptions and natural balance je-review, flux-analysis, bank-rec
materiality.md Per-workflow thresholds flux-analysis, je-review, prepaid-schedule
close-calendar.md WD1–WD10 task schedule and open/closed periods je-review, all (period awareness)
approval-matrix.md Approval routing by dollar threshold je-review (escalation), bank-rec (over-threshold reconciling items)

Customizing for your firm

Replace each file in references/:

  1. Chart of accounts — export from your GL. The CSV must keep the same column headers (accountnumber, accountname, accounttype, naturalbalance, is_active). Account numbers as strings to preserve leading zeros.
  2. Materiality — replace the thresholds in materiality.md. The threshold names are referenced by other skills, so keep the names; change the numbers.
  3. Close calendar — update WD1–WD10 task lists, posting cutoffs, and the list of currently open periods.
  4. Approval matrix — update name placeholders and dollar thresholds.

The template values are reasonable defaults for a mid-market services company at ~$50M revenue. They are not your firm's values.

Reading config in practice

Other skills reference config values by name, not by hardcoded number. Example from flux-analysis:

Apply materiality.fluxthresholdpct and materiality.fluxthresholddollar from firm-config/references/materiality.md. An account triggers commentary if it exceeds either the dollar threshold OR the percent threshold.

If you change a threshold in materiality.md, the change takes effect on the next workflow run. No skill code needs updating.

What this skill is not

This is not a config-loading library. The files in references/ are read directly by the workflow skills as part of their context. There is no Python module to import — just markdown and CSV that the skills inspect.