agentleFS
grechjgrechj/Australian-Builders-Brain/skills/estimating/SKILL.md

estimating

Skill0 starsChanged 22 days agoMITView on GitHub

Estimate and quote building jobs for Australian builders and trades. Builds the Trade Based Estimate Workbook, prices it with contingency and markup, compares subcontractor quotes, tests margin sensitivity, logs pre-contract clarifications, and produces the Quote Acceptance Form. Use when someone wants to price a job, do an estimate or take-off, put a quote together, compare subbie or supplier quotes, work out markup or margin, check if a job is worth taking, or get a client to accept a quote.

  • Installs packages

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run commands from the user's own project folder (the current working directory), so my_project.yaml and out/ are theirs.

    line 20
  2. Distinctive:

    Before anything else, know who you're helping and where:

    line 37
  3. Very specific:

    Ask for the trade and state if the project file doesn't have them (python3 $ABB/tools/profile.py trades lists every trade.

    line 43
  4. Distinctive:

    Put a validity period on it, and list inclusions, exclusions and allowances.

    line 99
  5. Very specific:

    Write it from the Structure section of brain/documents/<name>.md, which lists every section, field, table and prompt in order.

    line 137
  6. Very specific:

    If they have their own branded Word template, tools/fill_template.py fills any .docx that uses the same [PLACEHOLDERS].

    line 138

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Estimating

You help a builder price a job properly, quote it clearly, and win it without leaving money or risk on the table.

Where things are

The brain (this repository) is at ${CLAUDE_PLUGIN_ROOT}. If that shows literally as ${CLAUDE_PLUGIN_ROOT}, you are working in a clone instead: the brain is the repository root, two levels up from this skill's folder. $ABB below means the brain's folder: write it out as the real path in every command. Paths starting brain/, templates/, tools/ and examples/ are inside it.

Run commands from the user's own project folder (the current working directory), so my_project.yaml and out/ are theirs. Never write into the brain's folder: an installed plugin's folder is replaced on every update.

  • Knowledge: brain/contracts/estimating_and_quoting.md (read it first), brain/contracts/variations.md (PC and provisional sums), brain/states/overview.md
  • Maths: brain/computations/estimate_price.md, margin.md, gst.md
  • Templates: templates/excel/Trade_Based_Estimate_Workbook.xlsx, Estimate_to_Quote_Converter_TEMPLATE.xlsx, Quote_Comparison_TEMPLATE.xlsx, Margin_Sensitivity_Calculator_TEMPLATE.xlsx, Pre_Contract_Clarifications_TEMPLATE.xlsx; templates/word/Quote_Acceptance_Form_TEMPLATE.docx, Trade_Quote_TEMPLATE.docx
  • Examples: examples/estimate_spec.yaml, examples/quote_acceptance_spec.yaml

For python3, use ${CLAUDE_PLUGIN_DATA}/venv/bin/python if it exists (the plugin's setup hook creates it). Otherwise, if python3 -c "import docx, openpyxl, yaml" fails, run python3 -m pip install -r $ABB/requirements.txt first.

Profile: trade and location

Before anything else, know who you're helping and where:

python3 $ABB/tools/profile.py show --project my_project.yaml      # or: --trade <trade> --state <STATE>

Ask for the trade and state if the project file doesn't have them (python3 $ABB/tools/profile.py trades lists every trade; builder sees everything). Stay within the profile: use the NCC pages, skills, materials and suppliers it lists, apply only that state's NCC variations and rules, and read the state page for local differences.

Steps

1. Scope first

Get the drawings or a clear description, the site address, the state, and whether it is residential work for an owner. Residential work changes the contract and deposit rules. List what is unclear as clarifications (RFI-001 ...) in the Pre-Contract Clarifications register, rather than guessing.

2. Build the estimate

Work trade by trade into the Trade Based Estimate Workbook, using cell entries as in examples/estimate_spec.yaml:

  • Labour, rows 9 to 28: trade, description, qty, unit, rate. Column E defaults to the Setup rate and can be overridden.
  • Materials, rows 33 to 57: item, description, qty, unit, unit cost
  • Subcontractors, rows 62 to 76: trade, subcontractor, quote ref, quote date, amount
  • Setup: default markup (B16) and contingency (B17) as fractions (0.2 and 0.05), or leave the defaults

For the materials lines, the materials skill can take off quantities and price them (Bunnings as a retail guide); replace those with trade prices before quoting. Prompt for the commonly missed items listed in the brain page. Never invent quantities or prices. Mark anything the user hasn't given as an allowance and say so.

3. Compare subbie quotes

For each trade with several quotes, fill the Quote Comparison. Check each quote's licence and insurance are current, and that its inclusions match the scope. The cheapest quote with exclusions is often not the cheapest job.

4. Price it, then check the price

python3 $ABB/tools/compute.py estimate_price --param labour=<labour subtotal> --param materials=<materials subtotal> \
    --param subcontract=<subcontract subtotal> --param contingency_pct=5 --param markup_pct=20 \
    > out/estimate_receipt.json
python3 $ABB/brain/references/attesters/check_receipt.py out/estimate_receipt.json

The workbook's totals must match the receipt. Tell the user both the markup and margin_on_price_pct ("20% markup, which is a 16.7% margin"). If the user has a target margin, compare them. For risky jobs, fill the Margin Sensitivity Calculator (Setup: estimated cost, target markup) and show what a 5% or 10% overrun does to profit.

5. The quote

  • The workbook's Quote Output sheet is the client-facing summary, with markup built into each line.
  • Its standard terms say any deposit stays within the state's legal limit. Set the actual deposit in the contract, within the cap for the state (brain/states/overview.md).
  • Put a validity period on it, and list inclusions, exclusions and allowances.

5a. A trade's own quote

A trade quoting a client or a builder for one trade package doesn't need the workbook. Use the Trade Quote (examples/trade_quote_spec.yaml): the scope, inclusions and exclusions as cells, price lines with fill_table "Item", totals from compute.py gst, the valid-until date and the payment and start terms (replace the two [SELECT: ...] prompts). The trade's typical materials and exclusions are on its trade page (brain/trades/). Remind the user that some states require a written contract for residential work above a value: check the state page before work starts.

6. Acceptance

Fill the Quote Acceptance Form as in examples/quote_acceptance_spec.yaml: quote number and dates (row for the quote date and valid-until), amounts from the receipt, a scope summary (cell), the deposit (within the state cap) and the payment method (replace "[ ] EFT" with "☒ EFT").

python3 $ABB/tools/fill_template.py $ABB/templates/word/Quote_Acceptance_Form_TEMPLATE.docx \
    --project my_project.yaml --spec out/quote_acceptance_spec.yaml --out out/Q-00N_Acceptance.docx

The fill must come back with nothing left over except [LOGO].

For residential work, remind the user that acceptance is not the contract. They need the state-compliant written contract and, above the threshold, home warranty insurance before taking the deposit. The contracts skill covers that.

Your own format

The templates are references, not a straitjacket. If the user wants the document on their own letterhead, as an email, as a PDF, or can't run Python (for example in Claude.ai):

  • Write it from the Structure section of brain/documents/<name>.md, which lists every section, field, table and prompt in order. Keep every section, and keep the money exactly as the computation receipt gives it.
  • If they have their own branded Word template, tools/fill_template.py fills any .docx that uses the same [PLACEHOLDERS].

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.