Agent skill

Tax Build

by filedcom in filedcom/opentax

Autonomous form builder. An agent skill from filedcom/opentax.

AGPL-3.0Auto-check passedFrontend & Design

Install Tax Build

skills CLI
$ npx skills add filedcom/opentax --skill tax-build -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install filedcom/opentax tax-build --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/filedcom/opentax.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/tax-build .claude/skills/tax-build && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
tax-build
GitHub stars
108
Token cost
~1.1k tokens
SKILL.md length
458 words
Files
5
Skills in repo
8
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Autonomous form builder. An agent skill from filedcom/opentax.

  • Works in 5 steps: Derive Paths + Load State → Research → Ground Truth → …
  • Tasks that involve Forms and validation
  • SKILL.md covers Overview, Phase 0 — Derive Paths + Load…, Phase 1 — Research and Phase 2 — Ground Truth, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Tax Build is an agent skill from filedcom/opentax. Autonomous form builder. Given a form number (e.g. 1120), researches IRS instructions, extracts ground truth from IRS sample returns, builds all nodes section by section, then runs a validate+fix loop until ≥95% of benchmark cases pass.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `agents/extractor.md`, `agents/node-builder.md` and `agents/researcher.md`).

It sits in Frontend & Design, covering Forms and validation. The repository describes itself as: Fully open-source US federal tax engine. Single binary cli. Runs on macOS, Linux, and Windows. Built for AI agents using AI agents. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Forms and validation

Example prompts

  • “/tax-build”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Derive Paths + Load State
  2. Research
  3. Ground Truth
  4. Build
  5. Validate + Fix Loop

What it can do on your machine

Read from SKILL.md and the folder at commit 0c6ae76. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tax Build loads about 1.1k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 458 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from filedcom/opentax at commit 0c6ae76, republished under its AGPL-3.0 licence (© filedcom). 458 words, ~1,113 tokens.

Download SKILL.mdSave it as .claude/skills/tax-build/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
tax-build
description
Autonomous form builder. Given a form number (e.g. 1120), researches IRS instructions, extracts ground truth from IRS sample returns, builds all nodes section by section, then runs a validate+fix loop until ≥95% of benchmark cases pass.

Tax Build — Autonomous Form Builder

Form: $ARGUMENTS

Overview

This skill autonomously builds a new tax form from scratch. It runs in phases, tracking progress in the harness state file so it can resume if interrupted.

Phase 0 — Derive Paths + Load State

Parse $ARGUMENTS as form number (e.g. 1120). Prepend f to get form dir prefix: f1120.

Derive all paths from convention:

  • Form dir: forms/f{ARGUMENTS}/
  • Shared nodes: forms/f{ARGUMENTS}/nodes/
  • Year dir: forms/f{ARGUMENTS}/2025/
  • Policy doc: forms/f{ARGUMENTS}/FORM.md (create if building new form)
  • Benchmark cases: benchmark/cases/f{ARGUMENTS}/2025/
  • State key: f{ARGUMENTS}:2025 in .state/bench/state.json under forms
  • Node specs: .state/bench/node-specs/{ARGUMENTS}-2025-nodes.json
  • Progress log: .state/bench/progress.md

Read CLAUDE.md and (if it exists) forms/f{ARGUMENTS}/FORM.md. Pass both as context to all spawned agents throughout this skill.

Read .state/bench/state.json. Navigate to forms.f{ARGUMENTS}:2025.build:

  • null or missing → start from Phase 1
  • "research" → skip to Phase 2
  • "ground_truth" → skip to Phase 3
  • "build" → skip to Phase 4
  • "validate" → skip to Phase 4 (re-validate)

Set status to "running" and write state.json.

Phase 1 — Research

Spawn one researcher agent (see agents/researcher.md). Pass:

  • Form number: $ARGUMENTS
  • Output path: .state/bench/node-specs/$ARGUMENTS-nodes.json

Wait for completion. Verify the file exists and is valid JSON with a nodes array.

Update state.json: phase → "research", node_specs_path set.

Append to .state/bench/progress.md:

## [Form $ARGUMENTS] Phase 1 Complete — Research
- Nodes identified: N
- Sections: [income, deductions, tax_computation, credits, payments]

Phase 2 — Ground Truth

Spawn one extractor agent (see agents/extractor.md). Pass:

  • Form number: $ARGUMENTS
  • Cases output dir: benchmark/cases/f{ARGUMENTS}/2025/

Wait for completion. Count created case directories ($ARGUMENTS-*).

Update state.json: phase → "ground_truth", benchmark_cases_created set.

Append to progress.md:

## [Form $ARGUMENTS] Phase 2 Complete — Ground Truth
- Benchmark cases created: N
- Case directories: [list]

Phase 3 — Build

Read .state/bench/node-specs/$ARGUMENTS-nodes.json. Group nodes into sections (income, deductions, tax_computation, credits, payments, other).

For each section, spawn one node-builder agent in parallel (see agents/node-builder.md). Pass:

  • The node specs for that section (JSON subset)
  • Form number and year (2025)
  • Path to the most similar existing form for reference patterns

Spawn ALL section agents in a single message (parallel). Wait for all to complete.

Update state.json: phase → "build", nodes_built array populated.

Append to progress.md:

## [Form $ARGUMENTS] Phase 3 Complete — Build
- Sections built: [list]
- Nodes implemented: N
Show full SKILL.md (157 more words)Show less

Phase 4 — Validate + Fix Loop

Repeat until ≥95% pass or 3 consecutive rounds with no improvement:

4a. Validate

Spawn validator agent (see agents/validator.md). Pass form: $ARGUMENTS.

Parse VALIDATOR_RESULT: line from output. Record in state.json benchmark_runs.

4b. Evaluate

  • If pass rate ≥ 95%: set status → "done", commit, append final summary to progress.md, stop.
  • If net-positive vs. previous round: commit, continue.
  • If no improvement for 3 rounds: set status → "stalled", stop.

4c. Fix

For each failing case, spawn one bug-fixer agent (.claude/skills/tax-fix/agents/bug-fixer.md). Pass:

  • Failing case name + input.json + correct.json content
  • Form: $ARGUMENTS
  • Root cause: "unknown — investigate from scratch"

Spawn all failing-case fix agents in parallel. Wait. Then go back to 4a.

Key Constraints

  • Always check the existing forms/f1040/ structure before building anything in forms/f$ARGUMENTS/ — follow the exact same patterns
  • Read CLAUDE.md before spawning node-builder agents — pass its contents as context
  • Never skip the research phase — node specs are the contract everything else depends on
  • Only commit after a net-positive validation round

© filedcom, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files in .claude/skills/tax-build of filedcom/opentax.

  • SKILL.md
  • agents/extractor.md
  • agents/node-builder.md
  • agents/researcher.md
  • agents/validator.md

Open the folder on GitHubat commit 0c6ae76

Compare with similar skills

Tax Build next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Tax Build compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tax Build this skillfiledcom/opentax108—~1.1kAutomated safety check: PassAGPL-3.0
MCP Developmentcoollabsio/coolify63k1 repos~949Automated safety check: PassMIT
Accessibility Fixeribelick/ui-skills9.5k4 repos~1.2kAutomated safety check: PassMIT
Formik Form PatternsChrisWiles/claude-code-showcase6.1k3 repos~2.1kAutomated safety check: PassNone
Buefy Vue UI Componentsbuefy/buefy9.5k—~8.2kAutomated safety check: PassMIT
Formkitformkit/formkit4.8k—~1.7kAutomated safety check: PassMIT

Similar skills

  • MCP Development

    coollabsio/coolify

    A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 1 repo~949 tokens
    Frontend & DesignAuto-check passed
  • Accessibility Fixer

    ibelick/ui-skills

    Audits and fixes HTML accessibility problems such as ARIA labels, keyboard navigation, focus management, contrast and form errors with minimal changes.

    9.5k GitHub starsUsed in 4 repos~1.2k tokens
    Frontend & DesignAuto-check passed
  • Formik Form Patterns

    ChrisWiles/claude-code-showcase

    Shows how to build forms with Formik and Yup validation, including conditional rules, field helpers, GraphQL submission, edit forms and multi-step flows.

    6.1k GitHub starsUsed in 3 repos~2.1k tokens
    Frontend & DesignAuto-check passed
  • Rules for writing Vue 3 templates with Buefy components on Bulma CSS: install options, prop conventions, b-field wrapping, tables, theming and dialogs.

    9.5k GitHub stars~8.2k tokensUpdated 29 days ago
    Frontend & DesignAuto-check passed
  • Formkit

    formkit/formkit

    A skill your agent uses when working with FormKit forms, validation, schema, or custom inputs in React, Vue, or Nuxt projects.

    4.8k GitHub stars~1.7k tokensUpdated 2 mo ago
    Frontend & DesignAuto-check passed
  • HTML Coder

    TokenRhythm/opensquilla

    Guides semantic, accessible HTML work: pages, forms, media and HTML5 APIs, plus how to deliver a runnable webpage project with a preview.

    7.1k GitHub stars~1.4k tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed

More from filedcom/opentax

All 8 skills in this repo
  • Audit Harness

    filedcom/opentax

    Generic audit/fix loop. An agent skill from filedcom/opentax.

    108 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed
  • Save Skill

    filedcom/opentax

    Helps users permanently set up the OpenTax skill on their AI platform so they don't have to load it every time.

    108 GitHub stars~724 tokensUpdated yesterday
    Auto-check passed
  • Tax Cases

    filedcom/opentax

    Generate realistic benchmark cases from IRS-published sources (VITA exercises, Pub 17 examples, MeF test cases).

    108 GitHub stars~923 tokensUpdated yesterday
    Auto-check passed
  • Tax Fix

    filedcom/opentax

    Autonomous bug-fix loop for any form:year. An agent skill from filedcom/opentax.

    108 GitHub stars~699 tokensUpdated yesterday
    Auto-check passed
  • Tax Preparer

    filedcom/opentax

    Tax preparer agent that uses the opentax CLI to prepare, validate, and export federal tax returns.

    108 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed
  • Tax Reviewer

    filedcom/opentax

    Tax return reviewer that audits a completed return against source documents using the opentax CLI.

    108 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed

Questions about Tax Build

What does Tax Build do?

Autonomous form builder. An agent skill from filedcom/opentax. Tax Build is an agent skill from filedcom/opentax. Autonomous form builder.

When should I use Tax Build?

Tax Build fits situations like: tasks that involve Forms and validation.

How do I install Tax Build in Claude Code?

Run `npx skills add filedcom/opentax --skill tax-build -a claude-code`. Or copy the skill folder (.claude/skills/tax-build in filedcom/opentax) into .claude/skills/tax-build in your project. Claude Code loads it when a task matches its description.

How do I install Tax Build in Codex?

Run `npx skills add filedcom/opentax --skill tax-build -a codex`. Or copy the skill folder (.claude/skills/tax-build in filedcom/opentax) into .agents/skills/tax-build in your project. Codex loads it when a task matches its description.

Can I use Tax Build in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add filedcom/opentax --skill tax-build -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tax-build, .gemini/skills/tax-build, .github/skills/tax-build and .opencode/skills/tax-build in your project.

What does Tax Build need to run?

SKILL.md names no scripts, command-line tools or credentials: Tax Build is instructions for the agent only.

Does Tax Build access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Tax Build safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Tax Build use?

Tax Build is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Tax Build use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Tax Build?

Skills that share tags, products or a category with Tax Build: MCP Development (coollabsio/coolify, 63k stars), Accessibility Fixer (ibelick/ui-skills, 9.5k stars), Formik Form Patterns (ChrisWiles/claude-code-showcase, 6.1k stars) and Buefy Vue UI Components (buefy/buefy, 9.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tax Build?

filedcom (a GitHub organization) maintains it in filedcom/opentax, which has 108 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 7, 2026.

Source: filedcom/opentax on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.