Skip to main content
ClaudeWave
Skill132 repo starsupdated 2d ago

requirement-forge-refiner

The requirement-forge-refiner guides teams through a structured interview to define and document how requirements should be organized and expressed for their project, producing a requirement-standards.md file that the requirement-quality atom reads to enforce consistent epic, feature, scenario, and acceptance-criteria formatting. Use this when establishing a new project's requirement structure, customizing how your team writes features and acceptance criteria, or when explicitly asked to configure requirement standards.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/techygarg/lattice /tmp/requirement-forge-refiner && cp -r /tmp/requirement-forge-refiner/skills/refiners/requirement-forge-refiner ~/.claude/skills/requirement-forge-refiner
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# 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 feat
skill-alignSkill

Audit and fix all Lattice documentation, README, docs/, GitHub issue templates, and CLAUDE.md to ensure they are fully aligned with the current skill inventory. Documentation drift is the most common source of user confusion in Lattice — a skill exists in the codebase but not in the docs, or a renamed skill leaves a stale reference in the bug report template. If you've made any change to skills/ and haven't run this, run it now. Use when the user says 'align docs', 'audit docs', 'update documentation', 'skill align', 'check docs are in sync', 'audit skill inventory', 'ensure docs are aligned', 'are the docs up to date', or 'what needs updating'. Standalone — does not call other skills.

skill-forgeSkill

Create a new Lattice skill — atom, molecule, or refiner — following all framework conventions. Writing skill files manually almost always produces convention violations: wrong section order, missing confirmation gates, defaults.md without the right structure. This skill knows all of that and guides you through it. Use whenever adding any new atom, molecule, or refiner to Lattice, or when the user says 'create a new skill', 'add an atom', 'add a molecule', 'add a refiner', 'build X for Lattice', 'new lattice skill', or 'skill forge'. Does not validate, align docs, or deploy — those are separate skills you run after.

skill-reviewSkill

Deep behavioral audit of a Lattice skill — proposes 3 review personas relevant to the skill, runs independent scenario analysis from each persona's perspective, then merges only the high-confidence, practical findings into a severity-ordered gap report with proposed fixes. Structural validation (conventions, cross-references) is skill-validate's job — this skill finds gaps that would realistically surface when someone actually uses the skill: missing scenario handling, ambiguous instructions, silent failure cases, and behavioral inconsistencies. Filters out theoretical edge cases, low-likelihood speculation, and findings owned by other skills. Use after writing or significantly changing any skill, or when the user says 'review this skill', 'deep review', 'does this skill work', 'find gaps in this skill', 'stress test this skill', 'review from different angles', or 'skill review'. Standalone — does not call other skills.

skill-validateSkill

Validate any Lattice SKILL.md against all tier conventions — atoms, molecules, and refiners. Catches structural errors, broken cross-references, and convention violations before they reach the repo. If you just wrote or modified a Lattice skill file and haven't run this yet, run it now — manual review consistently misses the same categories of errors this skill is specifically designed to catch. Use when the user says 'validate this skill', 'check this skill', 'does this follow conventions', 'review this skill file', 'check my SKILL.md', or 'skill validate'. Reports PASS/FAIL with specific file-and-section findings and actionable fixes. Standalone — does not call other skills.

architecture-compassSkill

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 shareable insights document. Scoped to one repository, module, or folder. Does not execute transformation — it orients. Use when the user says 'assess my codebase architecture', 'what direction should my codebase go', 'architecture compass', 'understand my architecture', 'audit architecture drift', 'architectural assessment', or 'help me understand what is wrong with my codebase'.

architecture-refinerSkill

Facilitate a structured conversation to define architecture principles for a repository. Supports multiple architecture styles: clean architecture (default), hexagonal / ports & adapters, modular monolith, or custom. Produces a formal architecture document that the corresponding atom will use. Use when setting up a new project, defining architecture standards, or when the user says 'setup architecture', 'define layers', 'architecture principles', 'help me define my architecture', 'hexagonal architecture', 'modular monolith', 'ports and adapters', or 'define my architecture style'.

architectureSkill

Enforce architectural rules when generating or modifying code. Defaults to clean architecture; supports any architecture style via the architecture-refiner. Validates layer responsibilities, dependency direction, and structural constraints using the loaded architecture rules. Use when generating code, reviewing architecture, creating new files, or when the user mentions 'architecture', 'layers', 'structure', 'dependency rules', 'hexagonal architecture', 'ports and adapters', 'modular monolith', or 'onion architecture'. Also use when reviewing generated code for structural compliance.

bug-fixSkill

Investigate, reproduce, and safely fix a bug with regression protection. Composes context, diagnosis, architecture, code quality, and testing guardrails into a reproduce-first repair workflow. Use when the user says 'fix this bug', 'debug this', 'investigate this failure', 'patch this regression', 'repair this issue', or 'why is this broken'.