Agent skill

Requirement Forge Refiner

by techygarg in techygarg/lattice

Facilitate a structured conversation to define requirement standards for a project — epic and feature definitions, scenario structure, AC format, priority notation, status workflow, and naming…

MITAuto-check passedDevelopment

Install Requirement Forge Refiner

skills CLI
$ npx skills add techygarg/lattice --skill requirement-forge-refiner -a claude-code

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

GitHub CLI
$ gh skill install techygarg/lattice requirement-forge-refiner --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/techygarg/lattice.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/requirement-forge-refiner .claude/skills/requirement-forge-refiner && 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
requirement-forge-refiner
GitHub stars
199
Token cost
~2.9k tokens
SKILL.md length
1,520 words
Files
2 (incl. assets)
Skills in repo
33
Repo updated
First seen
Licence
MIT

At a glance

Facilitate a structured conversation to define requirement standards for a project — epic and feature definitions, scenario structure, AC format, priority notation, status workflow, and naming…

  • Works in 3 steps: Read .lattice/config.yaml — check… → If the path exists, read that file. Ask… → If no config or no existing document,…
  • Setting up a new project
  • SKILL.md covers What This Produces, Scope Clarification, Before You Begin and Choosing the Mode, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Requirement Forge Refiner is an agent skill from techygarg/lattice. Facilitate a structured conversation to define requirement standards for a project — epic and feature definitions, scenario structure, AC format, priority notation, status workflow, and naming conventions. Produces a formal requirement-standards.md that the requirement-quality atom reads via config resolution, customising its embedded defaults for the team's product process. Use when setting up a new project, defining product standards, or when the user says 'set up requirement standards', 'define feature…

Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including assets (for example `assets/template.md`).

It sits in Development. The repository describes itself as: Install engineering discipline into any AI coding assistant. Composable skills for design, implementation, review, and team standards. Better process, not just better prompts. The licence is MIT.

When your agent uses it

  • Setting up a new project
  • Defining product standards
  • The user says set up requirement standards
  • Define feature standards

Example prompts

  • “set up requirement standards”
  • “define feature standards”
  • “configure requirement forge”
  • “/requirement-forge-refiner”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Read .lattice/config.yaml — check paths.requirement_standards.
  2. If the path exists, read that file. Ask the user
  3. If no config or no existing document, proceed with the full interview.

What it can do on your machine

Read from SKILL.md and the folder at commit 4d6c35f. 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 (its code samples are yaml).

    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

Requirement Forge Refiner loads about 2.9k tokens when it runs. Until then it costs about 164 tokens; SKILL.md has 1,520 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~164
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

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 techygarg/lattice at commit 4d6c35f, republished under its MIT licence (© techygarg). 1,520 words, ~2,936 tokens.

Download SKILL.mdSave it as .claude/skills/requirement-forge-refiner/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
requirement-forge-refiner
description
Facilitate a structured conversation to define requirement standards for a project — epic and feature definitions, scenario structure, AC format, priority notation, status workflow, and naming conventions. Produces a formal requirement-standards.md that the requirement-quality atom reads via config resolution, customising its embedded defaults for the team's product process. Use when setting up a new project, defining product standards, or when the user says 'set up requirement standards', 'define feature standards', 'configure requirement forge', 'define how features should be structured', or 'requirement forge refiner'.

Requirement Forge Refiner

What This Produces

  • Output: .lattice/standards/requirement-standards.md (or custom path from .lattice/config.yaml → paths.requirement_standards)
  • Two modes:
    • Overlay (mode: overlay): A slim document containing only sections that differ from the built-in defaults. The requirement-quality atom reads its embedded defaults.md first, then applies this document's sections on top. This is the expected common case.
    • Override (mode: override): A comprehensive standalone document that fully replaces the atom's embedded defaults. For teams whose product process differs fundamentally from the defaults.
  • Default mode: Overlay — produces only what the team wants to change
  • Config key: paths.requirement_standards in .lattice/config.yaml
  • Consumed by: requirement-quality atom (via config resolution) → requirement-forge molecule (composes the atom)
  • Template: Read ./assets/template.md for the full document structure, default content, and interview guidance comments

Scope Clarification

This refiner defines how requirements are structured and expressed for this project. It does not define:

  • What to build (that is the requirement-forge molecule's job)
  • Architecture or technical design (that is the architecture-refiner's job)
  • Domain modeling patterns (that is the ddd-refiner's job)

The standards produced here answer: what is an epic, what is a feature, what is a scenario, how are ACs written, how are features named and prioritized. These are the rules the requirement-quality atom enforces — the molecule composes the atom and inherits those rules automatically.

Before You Begin

Check for an existing standards document
  1. Read .lattice/config.yaml — check paths.requirement_standards.
  2. If the path exists, read that file. Ask the user:
    • "You already have a requirement standards document. Would you like to revise it (update specific sections), start fresh (new interview), or add to it (add new sections)?"
    • Revise: load the existing document, walk through only the sections the user wants to change, update in place.
    • Start fresh: proceed with the full interview flow below.
    • Add to it: skip to the "New Sections" part of the interview.
  3. If no config or no existing document, proceed with the full interview.
Ask two orienting questions first

Before the formal interview, ask:

  1. "Does your team already have a way of writing requirements — any existing PRDs, Confluence templates, or Jira conventions I should be aware of?"
  2. "Is there a specific product domain or terminology I should know before we define the standards?"

These two questions are the only free-form listening before the structured interview begins. Synthesize what you hear and carry it forward — do not ask follow-up questions at this stage.

Choosing the Mode

Present the three options:

"How would you like to define your requirement standards?

  1. Customize specific sections (overlay) — Keep the built-in defaults and change only what differs for your project. This produces a slim document. Most teams choose this.
  2. Define everything from scratch (override) — Walk through all sections and produce a comprehensive standalone document.
  3. Add project-specific sections only (overlay with additions) — Keep all defaults as-is and add new sections, such as domain terminology or custom status workflows.

The built-in defaults cover standard product spec practices well. Option 1 is recommended unless your team's conventions are fundamentally different."

Map the choice:

  • Options 1 and 3 → mode: overlay
  • Option 2 → mode: override

Facilitation Approach

Conversation style
  • One section at a time. Do not present all questions at once. Walk through the template sequentially.
  • Defaults-first. For each section, briefly summarize the default, then ask if it matches. Do not read defaults verbatim — summarize key points and ask.
  • Propose, don't just ask. When the user's answer is ambiguous, propose the most reasonable interpretation and ask them to confirm or correct. "It sounds like you want MoSCoW priorities — so 'Must', 'Should', 'Could', 'Won't'. Is that right?"
  • Record decisions, not discussion. The output document reads as a specification. "We discussed X and decided Y" is wrong. "Y" is right.
  • Challenge weak definitions. If the user defines a "feature" so broadly it would encompass an entire epic, push back: "That scope sounds like an epic — a feature should be independently designable in one design-blueprint session. Can we tighten the definition?"
For overlay mode

This should be fast. Many sections will be "keep as-is."

  1. Present each section's default in 2–3 sentences.
  2. Ask: "Does this match your project, or would you like to change it?"
  3. If matches → skip it (section will NOT appear in the output).
  4. If changes wanted → discuss specifics, record the changes.
  5. After all sections, ask: "Anything to add that isn't covered — domain-specific terminology, custom fields, team conventions?"
  6. Only changed or added sections appear in the output document.
For override mode

Every section gets attention and appears in the output.

  1. Walk through every section in full detail.
  2. User confirms, modifies, or replaces each section.
  3. All sections appear in the output.
Common scenarios
  • "I agree with everything" → No custom document needed. "The embedded defaults are already active. No custom document is needed — requirement-forge will use the defaults automatically."
  • "We use MoSCoW priorities" → Overlay §6 only.
  • "We call them 'use cases' not 'scenarios'" → Overlay §4 (rename + update any description that references "scenario").
  • "We have a longer status workflow" → Overlay §7.
  • "We have domain-specific terms that should be consistent" → Overlay with additions — add §10 Domain Terminology.
  • "Our features tend to be larger" → Overlay §2 and §4 — adjust the size signals and max scenario count.

Section-by-Section Interview Guide

Read ./assets/template.md and follow the <!-- INTERVIEW GUIDANCE: --> comments for each section. Those comments contain specific questions, probing questions, and what is customizable vs. fixed.

Show full SKILL.md (646 more words)Show less
Cross-section dependency table
Decision inAffectsHow
§2 — Feature size definition§4 scenario countLarger features tolerate more scenarios; tighter features need a lower cap
§4 — Scenario nomenclature§8 naming conventionsIf "scenario" is renamed, naming conventions must use the new term
§4 — Max scenarios per feature§2 feature definitionThese two must be consistent — the split signal in §2 should align with the cap in §4
§5 — AC format§4 scenario structureAC format determines what each scenario's criteria look like
§6 — Priority notationfeature file frontmatterPriority field format used in every generated feature file
§7 — Status workflowfeature file frontmatterStatus field used in every generated feature file
§8 — Naming conventionsall file generationFeature file names and display names generated by the molecule

When a dependency is triggered, inform the user: "Since you changed [X], we should also review [Y] — it's affected by that decision."

Overlay-specific section flow

For each of the 9 default sections:

  1. Summarize the section's key points in 2–3 sentences.
  2. Ask: "Does this match your project?"
  3. Yes → Move to the next section. This section will not appear in the output.
  4. No → Dive into the details using the template guidance. Produce the user's version.
  5. After all 9 sections, ask about additions.
Override-specific section flow

For each of the 9 default sections:

  1. Present the section's full content.
  2. Ask: "Does this work as-is, or would you like to modify it?"
  3. As-is → Include the default content unchanged.
  4. Modify → Discuss changes, produce the modified version.
  5. All sections go in the output.

Output Assembly

For overlay mode
  1. YAML frontmatter: mode: overlay
  2. Overlay preamble (from template)
  3. Table of contents listing only included sections
  4. Only the sections the user changed or added — each must be self-contained and complete
  5. Section headings must match template.md exactly (the molecule matches sections by heading)
  6. New sections (§10+) included after the default sections
  7. Footer with project name, date, mode
For override mode
  1. YAML frontmatter: mode: override
  2. Override preamble (from template)
  3. Full table of contents (all 9+ sections)
  4. All sections: defaults for unchanged, user's version for changed, new sections at end
  5. Footer with project name, date, mode
For both modes

Strip all <!-- INTERVIEW GUIDANCE: --> comments from the output. The final document is a clean specification.

Determine output path:

  1. If .lattice/config.yaml exists and has paths.requirement_standards, use that path.
  2. Otherwise, default to .lattice/standards/requirement-standards.md.

Write the document:

  1. Create .lattice/standards/ directory (and .lattice/ parent) if it does not exist.
  2. Write the document to the determined path.

Update config:

  1. If .lattice/config.yaml does not exist, create it with:
    yaml
    paths:
      requirement_standards: .lattice/standards/requirement-standards.md
  2. If .lattice/config.yaml exists but has no paths.requirement_standards, add the key. Preserve all existing content.
  3. If the key already exists, no config change needed.

Confirm to user: "Your requirement standards have been written to [PATH] in [overlay|override] mode. The requirement-forge molecule will now use these standards and will not re-ask structural questions covered here."

Document Quality Checks

Before writing the final document, verify:

Overlay mode checks
  • Each included section is self-contained and complete (not a diff or partial section)
  • Section headings match template.md exactly
  • No <!-- INTERVIEW GUIDANCE: --> comments remain
  • Frontmatter has mode: overlay
  • Only changed or added sections are included
Override mode checks
  • All 9 default sections are present (plus any additions)
  • §2 feature size signal is consistent with §4 max scenario count
  • §4 scenario nomenclature is consistent with §8 naming conventions
  • §5 AC format is consistent with how §4 describes scenario criteria
  • §6 priority values and §7 status values match the frontmatter field descriptions in §8
  • No <!-- INTERVIEW GUIDANCE: --> comments remain
  • Frontmatter has mode: override
  • Document is readable as a standalone specification
Both modes
  • Frontmatter is valid YAML with correct mode value
  • Document is well-formatted markdown
  • Config file (.lattice/config.yaml) is correctly updated
  • Output path exists and is writable

© techygarg, MIT. 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 1 other file (assets) in skills/requirement-forge-refiner of techygarg/lattice.

  • SKILL.md
  • assets/template.md

Open the folder on GitHubat commit 4d6c35f

Compare with similar skills

Requirement Forge Refiner 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.

Requirement Forge Refiner compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Requirement Forge Refiner this skilltechygarg/lattice199—~2.9kAutomated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from techygarg/lattice

All 33 skills in this repo
  • Architecture Compass

    techygarg/lattice

    Architectural thinking partner for an existing repository — scans the codebase, conducts a structured interview, agrees on current architectural state and recommended direction, and produces a…

    199 GitHub stars~4.4k tokensUpdated 3 days ago
    Auto-check passed
  • Lattice Init

    techygarg/lattice

    Guided setup and upgrade-check experience for Lattice projects -- scans the repository, detects existing configuration and outdated conventions, suggests refiners and available upgrades in priority…

    199 GitHub stars~3.3k tokensUpdated 3 days ago
    Auto-check passed
  • Skill Align

    techygarg/lattice

    Audit and fix all Lattice documentation, README, docs/, PROJECT.md, GitHub issue templates, and CLAUDE.md to ensure they are fully aligned with the current skill inventory.

    199 GitHub stars~2k tokensUpdated 3 days ago
    Auto-check passed
  • Skill Validate

    techygarg/lattice

    Validate any Lattice SKILL.md against all tier conventions — atoms, molecules, and refiners.

    199 GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed
  • Architecture Refiner

    techygarg/lattice

    Facilitate a structured conversation to define architecture principles for a repository.

    199 GitHub stars~3.7k tokensUpdated 3 days ago
    Auto-check passed
  • Clean Code Refiner

    techygarg/lattice

    Facilitate a structured conversation to define clean code principles for a repository.

    199 GitHub stars~3k tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Requirement Forge Refiner

What does Requirement Forge Refiner do?

Facilitate a structured conversation to define requirement standards for a project — epic and feature definitions, scenario structure, AC format, priority notation, status workflow, and naming…. Requirement Forge Refiner is an agent skill from techygarg/lattice. Facilitate a structured conversation to define requirement standards for a project — epic and feature definitions, scenario structure, AC format, priority notation, status workflow, and naming conventions.

When should I use Requirement Forge Refiner?

Requirement Forge Refiner fits situations like: setting up a new project; defining product standards; the user says set up requirement standards; define feature standards.

How do I install Requirement Forge Refiner in Claude Code?

Run `npx skills add techygarg/lattice --skill requirement-forge-refiner -a claude-code`. Or copy the skill folder (skills/requirement-forge-refiner in techygarg/lattice) into .claude/skills/requirement-forge-refiner in your project. Claude Code loads it when a task matches its description.

How do I install Requirement Forge Refiner in Codex?

Run `npx skills add techygarg/lattice --skill requirement-forge-refiner -a codex`. Or copy the skill folder (skills/requirement-forge-refiner in techygarg/lattice) into .agents/skills/requirement-forge-refiner in your project. Codex loads it when a task matches its description.

Can I use Requirement Forge Refiner 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 techygarg/lattice --skill requirement-forge-refiner -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/requirement-forge-refiner, .gemini/skills/requirement-forge-refiner, .github/skills/requirement-forge-refiner and .opencode/skills/requirement-forge-refiner in your project.

What does Requirement Forge Refiner need to run?

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

Does Requirement Forge Refiner 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 Requirement Forge Refiner 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 Requirement Forge Refiner use?

Requirement Forge Refiner is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Requirement Forge Refiner use?

About 2.9k tokens (SKILL.md is roughly 12k 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 Requirement Forge Refiner?

Skills that share tags, products or a category with Requirement Forge Refiner: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Requirement Forge Refiner?

techygarg (a GitHub user) maintains it in techygarg/lattice, which has 199 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 6, 2026.

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