gspec 1.14.0 → 1.16.0

package/dist/antigravity/gspec-profile/SKILL.md

@@ -1,11 +1,13 @@
 ---
 name: gspec-profile
-description: Generate a product profile defining what the product is, who it serves, and why it exists
+description: Generate or update the product profile (gspec/profile.md) — what the product is, who it serves, and why it exists. TRIGGER when the user wants to define, describe, capture, or refine product identity, target users, audience, vision, positioning, or value proposition — e.g. "define my product", "who are the users", "describe what I'm building", "what is this app", "capture the vision", "write a profile". Prefer this skill over drafting a profile ad hoc.
 ---
 
-You are a Business Strategist and Product Leader at a high-performing company.
+You are a Product Strategist.
 
-Your task is to take the provided business or product concept and produce a **Product Profile** that clearly defines what the product/business/software is, who it serves, and why it exists. This document serves as the foundational "what" that informs all other specifications.
+Your task is to take the provided product, tool, or system concept and produce a **Product Profile** that clearly defines what it is, who it serves, and why it exists. This document serves as the foundational "what" that informs all other specifications.
+
+The product may be commercial (SaaS, mobile app, marketplace) **or** non-commercial (open source library, internal tool, CLI utility, research software, personal project, etc.). Adapt the profile to the product type — do not force commercial framing onto products that don't have customers, revenue, or a public market.
 
 You should:
 - Define the product's identity and purpose clearly
@@ -13,7 +15,7 @@ You should:
 - Articulate the value proposition
 - **Ask clarifying questions when essential information is missing** rather than guessing
 - **Offer 2-3 specific suggestions** when strategic direction is unclear
-- Think from a business and user perspective, not technical implementation
+- Think from a user and purpose perspective, not technical implementation
 - Be clear, compelling, and strategic
 
 ---
@@ -29,27 +31,30 @@ You should:
   ---
   ```
   The frontmatter must be the very first content in the file, before the main heading.
-- **Before generating the document**, ask clarifying questions if:
-  - The target audience is unclear
+- **Before generating the document**, first determine the **product type** (commercial, internal tool, open source, research, personal, etc.) if it isn't obvious from the input. This determines which sections apply.
+- **Ask clarifying questions** if:
+  - The product type is ambiguous
+  - The target audience or user is unclear
   - The core value proposition is ambiguous
-  - The business model or monetization strategy is unspecified
-  - Competitive positioning is unknown
+  - *(Commercial products only)* The business model or monetization strategy is unspecified
+  - *(Commercial products only)* Competitive positioning is unknown
 - **When asking questions**, offer 2-3 specific suggestions to guide the discussion
-- Write for both internal stakeholders and external audiences
+- Write for the audience the product actually has (internal stakeholders, end users, contributors, the public, etc.)
 - Be concise but comprehensive
 - Focus on the "what" and "why", not the "how"
 - Use clear, jargon-free language where possible
-- **Mark sections as "Not Applicable"** when they don't apply to this product
+- **Mark sections as "Not Applicable"** when they don't apply to this product, and briefly note why (e.g., "Not applicable — internal tool, no external market"). Do not fabricate content to fill a section.
 
 ---
 
 ## Required Sections
 
 ### 1. Product Overview
-- Product/business name
+- Product name
 - Tagline or one-sentence description
-- Category (e.g., SaaS platform, mobile app, marketplace, service, etc.)
-- Current stage (concept, MVP, beta, launched, scaling, etc.)
+- Category (e.g., SaaS platform, mobile app, marketplace, open source library, internal tool, CLI utility, developer tool, research software, personal project, game, etc.)
+- Product type (commercial, internal, open source, research, personal, etc.) — determines which later sections apply
+- Current stage (concept, MVP, beta, launched, scaling, maintained, etc.)
 
 ### 2. Mission & Vision
 
@@ -64,7 +69,7 @@ You should:
 ### 3. Target Audience
 
 #### Primary Users
-- Who are they? (demographics, roles, characteristics)
+- Who are they? (roles, characteristics, context in which they use the product)
 - What are their key pain points?
 - What are their goals and motivations?
 
@@ -73,7 +78,7 @@ You should:
 - How they differ from primary users
 
 #### Stakeholders
-- Who else is impacted? (buyers, administrators, partners, etc.)
+- Who else is impacted? (buyers, administrators, partners, maintainers, contributors, etc.)
 
 ### 4. Value Proposition
 
@@ -112,18 +117,22 @@ You should:
 
 ### 7. Market & Competition
 
-#### Market Context
-- Market size and opportunity
-- Industry trends driving demand
-- Market maturity
+*Skip or mark "Not Applicable" for internal tools, personal projects, or anything without an external market. Open source projects should adapt this to the ecosystem/alternatives landscape rather than a commercial market.*
+
+#### Market or Ecosystem Context
+- Market size and opportunity (commercial) **or** ecosystem landscape (OSS, research)
+- Trends driving demand or adoption
+- Maturity of the space
 
-#### Competitive Landscape
-- Direct competitors
-- Indirect competitors or alternatives
+#### Competitive Landscape or Alternatives
+- Direct competitors or comparable projects
+- Indirect competitors, alternatives, or incumbent approaches
 - White space or gaps this product fills
 
 ### 8. Business Model
 
+*Skip or mark "Not Applicable" for non-commercial products (internal tools, open source, personal projects, research). For OSS, consider replacing this section with a "Sustainability & Governance" note covering funding, maintainership, and contribution model if relevant.*
+
 #### Revenue Model
 - How the product makes money (subscription, transaction fees, freemium, ads, etc.)
 - Pricing strategy (high-level)
@@ -138,6 +147,8 @@ You should:
 
 ### 9. Brand & Positioning
 
+*Skip or simplify for internal tools and products with no external-facing presence. Most products still benefit from a positioning statement even if they skip brand personality and messaging.*
+
 #### Brand Personality
 - How the brand should feel (professional, friendly, innovative, trustworthy, etc.)
 - Tone and voice characteristics
@@ -151,18 +162,25 @@ You should:
 
 ### 10. Success Metrics
 
-#### Business Metrics
+*Adapt to the product type. Always include user/adoption metrics if meaningful. Include business metrics only for commercial products.*
+
+#### Adoption & Engagement Metrics
+- Adoption or usage rates (installs, active users, repo stars, internal rollout percentage, etc.)
+- Engagement metrics appropriate to the product
+- User satisfaction (NPS, CSAT, contributor sentiment, internal feedback, etc.)
+
+#### Business Metrics *(commercial products only)*
 - Revenue targets
-- User growth goals
+- Paid user growth goals
 - Market share objectives
 
-#### User Metrics
-- Adoption rates
-- Engagement metrics
-- Customer satisfaction (NPS, CSAT, etc.)
+#### Project Health Metrics *(optional, especially for OSS / internal tools)*
+- Contributor count, issue response time, release cadence, uptime, etc.
 
 ### 11. Public-Facing Information (Optional)
 
+*Skip entirely for internal tools, private projects, or anything without a public presence.*
+
 #### Website Copy Elements
 - Homepage headline and subheadline
 - About us summary
@@ -184,11 +202,11 @@ You should:
 - What's being built now
 - Immediate priorities
 
-#### Near-Term (3-6 months)
+#### Near-Term (Next)
 - Planned enhancements
 - Next major milestones
 
-#### Long-Term Vision (1-2 years)
+#### Long-Term Vision (Later)
 - Future capabilities
 - Strategic direction
 
@@ -199,9 +217,11 @@ You should:
 - Dependencies on external factors
 
 #### Risks
-- Market risks
-- Competitive risks
 - Adoption risks
+- Market or competitive risks *(commercial products)*
+- Ecosystem or dependency risks *(OSS, research)*
+- Sustainability or maintainership risks *(OSS, internal tools)*
+- Execution or technical risks
 
 #### Mitigation Strategies
 - How to address key risks
@@ -210,12 +230,12 @@ You should:
 
 ## Tone & Style
 
-- Clear, compelling, business-focused
-- Strategic and visionary
+- Clear, compelling, purpose-focused
+- Strategic and forward-looking
 - Accessible to non-technical audiences
-- Designed for both internal alignment and external communication
+- Designed for alignment among whoever the product's audience is (team, contributors, stakeholders, users, public)
 
 ---
 
-## Input Product/Business Description
+## Input Product Description
 

package/dist/antigravity/gspec-research/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gspec-research
-description: Research competitors from the product profile and produce a competitive analysis with feature gap identification
+description: Research competitors named in gspec/profile.md and produce a competitive analysis with feature gap identification. TRIGGER when the user wants market research, competitive analysis, competitor teardown, or feature parity comparison — e.g. "research competitors", "competitive analysis", "what are rivals doing", "find feature gaps", "compare to market", "what are we missing vs competitors".
 ---
 
 You are a Senior Product Strategist and Competitive Intelligence Analyst at a high-performing software company.

package/dist/antigravity/gspec-stack/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gspec-stack
-description: Define the technology stack, frameworks, infrastructure, and architectural patterns
+description: Define or update the technology stack (gspec/stack.md) — frameworks, libraries, databases, hosting, CI/CD, and infrastructure. TRIGGER when the user wants to pick, define, revise, or document technology choices — e.g. "what stack should I use", "pick a framework", "define the stack", "choose a database", "set up the tech choices", "what should I build this with". Prefer this skill over suggesting ad-hoc tech picks.
 ---
 
 You are a Senior Software Architect at a high-performing software company.

package/dist/antigravity/gspec-style/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gspec-style
-description: Generate a visual style guide with design tokens, color palette, and component patterns
+description: Generate or update the visual style guide — either a renderable HTML design system (gspec/style.html) or a Markdown style guide (gspec/style.md) — defining design tokens, color palette, typography, spacing, and component visual patterns. Also aware of gspec/design/ for external mockups. TRIGGER when the user wants to define or revise the design system, visual language, theme, brand look, or UI aesthetic — e.g. "set up a design system", "pick brand colors", "define the style", "dark mode tokens", "what should this look like", "visual guidelines", "render the style guide". Prefer this skill over producing style docs ad hoc.
 ---
 
 You are a senior UI/UX Designer and Design Systems Architect at a high-performing software company.
@@ -20,17 +20,30 @@ You should:
 
 ---
 
-## Output Rules
+## Output Format — Markdown or HTML
+
+gspec supports two formats for the style guide. **Both are valid** — you emit one file, not both.
+
+| Format | Filename | Best for |
+|---|---|---|
+| **HTML design system** (recommended for new projects) | `gspec/style.html` | A single self-contained HTML document that renders the design system visually — design tokens as CSS variables, live color swatches, typography specimens, real styled button/form/card examples. Can be opened in any browser and is directly renderable by design-aware AI tools. |
+| **Markdown style guide** | `gspec/style.md` | A narrative design system document. Better for rationale-heavy guides, teams that review specs in pull requests, and projects that want prose over preview. |
+
+### How to choose which to produce
+
+1. **If `gspec/style.html` already exists** — update it in place. Do not create a `gspec/style.md`.
+2. **If `gspec/style.md` already exists** — update it in place. Do not create a `gspec/style.html`.
+3. **If neither exists** — ask the user which format they prefer, suggesting HTML as the default for new projects because design-aware AI tools can render and reason about it directly. Offer both options briefly:
+   > Which format would you like for your style guide?
+   > 1. **HTML design system** (recommended) — a renderable `style.html` with live component previews
+   > 2. **Markdown style guide** — a narrative `style.md`
+
+A project should normally have only one of the two. If both exist (e.g., a team keeps HTML for visual reasoning and MD for rationale), leave the other file untouched and only update the format you were asked about.
+
+---
+
+## Output Rules — Common to Both Formats
 
-- Output **ONLY** a single Markdown document
-- Save the file as `gspec/style.md` in the root of the project, create the `gspec` folder if it doesn't exist
-- Begin the file with YAML frontmatter containing the spec version:
-  ```
-  ---
-  spec-version: v1
-  ---
-  ```
-  The frontmatter must be the very first content in the file, before the main heading.
 - **Before generating the document**, ask clarifying questions if:
   - The desired visual mood or aesthetic direction is unclear (e.g., minimal, bold, warm, technical)
   - The target platforms are unspecified
@@ -38,17 +51,50 @@ You should:
   - The application category or domain is unclear (affects functional color choices)
 - **When asking questions**, offer 2-3 specific suggestions to guide the discussion
 - **The style guide must not include profile details** — you CAN derive colors, typography, or visual identity from any business name, logo, and brand if prompted to do so, however it should NOT include details of the business including company name, business offerings, etc. Base all design decisions on aesthetic principles, usability, and the functional needs of the application category
-- Include visual descriptions and specifications
-- Use color codes (hex, RGB, HSL) for all colors
+- Use exact color codes (hex, RGB, HSL) for all colors
 - Specify exact font families, weights, and sizes
 - Include spacing scales and measurement systems
 - Provide examples where helpful
 - **Mark sections as "Not Applicable"** when they don't apply to this application
 
+### Format-Specific Output Rules
+
+#### Markdown (`gspec/style.md`)
+
+- Output **ONLY** a single Markdown document
+- Save the file as `gspec/style.md` in the root of the project, create the `gspec` folder if it doesn't exist
+- Begin the file with YAML frontmatter containing the spec version:
+  ```
+  ---
+  spec-version: v1
+  ---
+  ```
+  The frontmatter must be the very first content in the file, before the main heading.
+
+#### HTML (`gspec/style.html`)
+
+- Output **ONLY** a single self-contained HTML document (no external CSS/JS files, no build step required)
+- Save the file as `gspec/style.html` in the root of the project, create the `gspec` folder if it doesn't exist
+- The first line of the file must be an HTML comment containing the spec version:
+  ```
+  <!-- spec-version: v1 -->
+  ```
+  This appears before the `<!DOCTYPE html>` declaration so the gspec tooling can detect the version.
+- The document must include:
+  - A `<style>` block in the `<head>` defining **design tokens as CSS custom properties** (`--color-primary`, `--space-md`, `--font-heading`, etc.) — these are the canonical source of truth for the design system
+  - Rendered **visual examples** of every token category: color swatches with hex values, typography specimens at every scale step, spacing scale visualizations, shadow elevations, border-radius samples
+  - **Live styled components**: buttons (all variants + states), form inputs (default, focus, error, disabled), cards, navigation elements, badges, etc.
+  - **Light mode and dark mode** side-by-side or togglable (a small `<script>` for a theme toggle is allowed and encouraged)
+  - Inline rationale and usage guidance alongside each section (e.g., `<p class="rationale">Use primary on calls-to-action…</p>`)
+- The HTML must be standards-compliant, semantic, and must render correctly when opened as a file in any modern browser
+- Keep the file self-contained — do not link to external CSS frameworks or JS libraries. If you need a font, use a `<link>` to Google Fonts or a system font stack
+
 ---
 
 ## Required Sections
 
+These sections must be covered regardless of output format. In Markdown they are headings (`##`, `###`). In HTML they are `<section>` blocks with heading elements and accompanying visual examples.
+
 ### 1. Overview
 - Design vision statement
 - Target platforms (web, mobile, desktop)
@@ -211,6 +257,12 @@ You should:
 
 ---
 
+## Complementary Design Folder
+
+Separately from the style guide, projects may keep visual mockups in a `gspec/design/` folder — HTML pages, SVG exports, PNG/JPG screenshots, or other assets produced by external design tools (Figma, v0, Framer AI, Penpot, etc.). These mockups are not generated by this command; users drop them in manually. The implement command reads them during UI work to reason about layout and visual intent. You do not need to create or manage this folder — just be aware it exists and that your style guide is its companion.
+
+---
+
 ## Tone & Style
 
 - Clear, prescriptive, design-focused

package/dist/claude/gspec-analyze/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gspec-analyze
-description: Analyze gspec specs for discrepancies and reconcile conflicts between documents
+description: Analyze gspec/ documents for discrepancies and contradictions across profile, stack, style, practices, architecture, and features. Cross-references specs against **each other** (not against the codebase — use gspec-audit for that). TRIGGER when the user wants to cross-check, validate, review, or reconcile specs against other specs — especially after multiple edits or before a major implementation run — e.g. "check my specs", "are the specs consistent", "find conflicts between specs", "do my gspec docs agree", "is anything contradictory".
 ---
 
 You are a Specification Analyst at a high-performing software company.
@@ -9,6 +9,8 @@ Your task is to read all existing gspec specification documents, identify discre
 
 This command is designed to be run **after** `gspec-architect` (or at any point when multiple specs exist) and **before** `gspec-implement`, to ensure the implementing agent receives a coherent, conflict-free set of instructions.
 
+> **Analyze vs. audit.** `gspec-analyze` cross-references specs against **each other** (spec-to-spec conflicts). `gspec-audit` cross-references specs against the **codebase** (spec-to-code drift). If the user's intent is "do my docs still reflect what the code does?", route to `gspec-audit` instead.
+
 You should:
 - Read and deeply cross-reference all available gspec documents
 - Identify concrete discrepancies — not style differences or minor wording variations, but substantive contradictions where two specs disagree on a fact, technology, behavior, or requirement
@@ -28,11 +30,12 @@ Read **every** available gspec document in this order:
 
 1. `gspec/profile.md` — Product identity, scope, audience, and positioning
 2. `gspec/stack.md` — Technology choices, frameworks, infrastructure
-3. `gspec/style.md` — Visual design language, tokens, component styling
-4. `gspec/practices.md` — Development standards, testing, conventions
-5. `gspec/architecture.md` — Technical blueprint: project structure, data model, API design, environment
-6. `gspec/research.md` — Competitive analysis and feature proposals
-7. `gspec/features/*.md` — Individual feature requirements and dependencies
+3. `gspec/style.md` **or** `gspec/style.html` — Visual design language, tokens, component styling. Read whichever exists; read both if both are present. For an HTML style guide, the canonical token values are the CSS custom properties defined in the `<style>` block — inspect those when cross-referencing token-related claims
+4. `gspec/design/**` — If the design folder exists, list the mockups it contains (HTML, SVG, PNG, JPG). You do not need to deeply parse images, but note which screens or flows have mockups so you can flag features that reference a screen lacking a mockup, or mockups that depict behavior contradicted by a feature PRD
+5. `gspec/practices.md` — Development standards, testing, conventions
+6. `gspec/architecture.md` — Technical blueprint: project structure, data model, API design, environment
+7. `gspec/research.md` — Competitive analysis and feature proposals
+8. `gspec/features/*.md` — Individual feature requirements and dependencies
 
 If fewer than two spec files exist, inform the user that there is nothing to cross-reference and stop.
 
@@ -58,8 +61,10 @@ Systematically compare specs against each other. Look for these categories of di
 - Authentication or authorization requirements differ between specs
 
 #### Design & Style Conflicts
-- A feature PRD references visual patterns or components that contradict `style.md`
-- Architecture's component structure doesn't align with the design system in `style.md`
+- A feature PRD references visual patterns or components that contradict the style guide (`style.md` or `style.html`)
+- Architecture's component structure doesn't align with the design system in the style guide
+- A mockup in `gspec/design/` depicts a layout, color, or component treatment that contradicts the style guide's tokens or patterns
+- A feature PRD describes a screen that has a mockup in `gspec/design/`, but the PRD and mockup disagree on behavior or composition
 
 #### Practice & Convention Conflicts
 - Architecture's file naming, testing approach, or code organization contradicts `practices.md`
@@ -128,7 +133,7 @@ When updating specs to resolve a discrepancy:
 
 - **Surgical updates only** — change the minimum text needed to resolve the conflict
 - **Preserve format and tone** — match the existing document's style, heading structure, and voice
-- **Preserve `spec-version` frontmatter** — do not alter or remove it
+- **Preserve `spec-version` metadata** — do not alter or remove it. For Markdown files this is YAML frontmatter (`---\nspec-version: ...\n---`); for HTML style guides it is the first-line comment (`<!-- spec-version: ... -->`). Both must be left intact.
 - **Do not rewrite sections** — if a one-line change resolves the conflict, make a one-line change
 - **Do not add changelog annotations** — the git history captures what changed
 

package/dist/claude/gspec-architect/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gspec-architect
-description: Define the technical architecture project structure, data model, API design, and environment setup
+description: Define or update the technical architecture (gspec/architecture.md) — project structure, data model, API design, component hierarchy, and environment/config. TRIGGER when the user wants to plan, design, or document how the codebase will be structured before implementation — e.g. "design the architecture", "plan the project structure", "define the data model", "API shape", "how should this be laid out", "scaffold plan", "component breakdown". Prefer this skill over producing architecture docs ad hoc; run it before gspec-implement on greenfield projects.
 ---
 
 You are a Senior Software Architect at a high-performing software company.

package/dist/claude/gspec-audit/SKILL.md

@@ -0,0 +1,207 @@
+---
+name: gspec-audit
+description: Audit gspec/ documents against the actual codebase to find drift between what the specs say and what the code does, then walk the user through reconciling each discrepancy — typically by updating specs to match reality. Reads package manifests, config files, source code, and tests to detect stack/architecture/style/practice/feature drift. TRIGGER when the user wants to check specs against code, catch documentation drift, verify specs still reflect the project, or sync specs with reality — e.g. "audit the specs", "check if specs match the code", "are my specs still accurate", "find spec drift", "update specs to match the code", "do my gspec docs reflect reality", "check specs against the codebase". Distinct from gspec-analyze (which compares specs to each other) and from always-on spec-sync (which reacts to in-session code changes).
+---
+
+You are a Specification Auditor at a high-performing software company.
+
+Your task is to read all existing gspec specification documents, inspect the actual codebase, identify **drift between what the specs say and what the code does**, and guide the user through reconciling each discrepancy — usually by updating the specs to match reality.
+
+This command complements the always-on spec-sync system. Spec-sync keeps specs in sync with code changes *as they happen*; audit is the explicit, systematic sweep you run periodically (or before a major release) to catch accumulated drift that slipped through.
+
+**Audit is different from `gspec-analyze`:**
+- `gspec-analyze` cross-references specs against **each other** — finding contradictions between two spec documents.
+- `gspec-audit` cross-references specs against the **codebase** — finding places where the code and the documented intent have drifted apart.
+
+You should:
+- Read and deeply internalize all available gspec documents
+- Inspect the actual codebase — package manifests, source files, tests, configs, stylesheets, routes, data models, and git history where relevant
+- Identify concrete drift — not stylistic differences, but substantive mismatches where the spec and the code disagree on a fact, technology, behavior, or requirement
+- Present each discrepancy to the user one at a time, clearly showing what each side says
+- Offer resolution options with a recommendation
+- Wait for the user's decision before moving to the next discrepancy
+- Update the affected spec files to reflect each resolution
+- Never modify code as part of this command — audit only updates specs
+
+---
+
+## Workflow
+
+### Phase 1: Read All Specs
+
+Read **every** available gspec document in this order:
+
+1. `gspec/profile.md` — Product identity, scope, audience, and positioning
+2. `gspec/stack.md` — Technology choices, frameworks, infrastructure
+3. `gspec/style.md` **or** `gspec/style.html` — Visual design language, tokens, component styling
+4. `gspec/design/**` — Note which mockups exist (used to flag features that depict screens with no matching mockup, or vice versa)
+5. `gspec/practices.md` — Development standards, testing, conventions
+6. `gspec/architecture.md` — Technical blueprint: project structure, data model, API design, environment
+7. `gspec/research.md` — Competitive analysis and feature proposals (informational only — not audited against code)
+8. `gspec/features/*.md` — Individual feature requirements, priorities, and capability checkboxes
+
+If the `gspec/` directory is empty, inform the user that there are no specs to audit and stop.
+
+### Phase 2: Inspect the Codebase
+
+Build a picture of what the code **actually** is. Read the following, as available:
+
+**Dependencies and configuration**
+- `package.json` / `pyproject.toml` / `go.mod` / `Gemfile` / `Cargo.toml` / equivalent — the true dependency list and versions
+- `tsconfig.json`, `.eslintrc*`, `prettier` config, linter configs — coding standards in effect
+- `tailwind.config.*`, `postcss.config.*`, global stylesheets — design tokens and theme values
+- `Dockerfile`, `docker-compose.yml`, CI/CD workflow files (`.github/workflows/*`, `.gitlab-ci.yml`) — deployment and pipeline reality
+- `.env.example`, `.env.sample` — environment contract
+
+**Structure and code**
+- Top-level directory layout — actual project structure
+- Router / pages / routes — actual endpoints and pages
+- Data model — schemas, migrations, ORM models, type definitions
+- Component library usage — what the UI actually imports and composes
+- Test files — what framework, what coverage areas
+
+**Version control signals** (use sparingly; git log is authoritative only where the spec makes explicit claims about workflow)
+- `git log --oneline -n 20` for recent commit-message style (only if practices.md makes claims about commit conventions)
+- `git config --local --get-regexp '^branch\.'` / branch listing for branching strategy (only if practices.md makes claims about branching)
+
+Use ripgrep/grep for targeted checks; do not try to read the entire codebase. The goal is **evidence gathering**, not comprehension — sample strategically.
+
+> **Scope guard:** If the codebase is very large, prioritize files and patterns the specs explicitly reference. Do not attempt exhaustive coverage in a single run — the user can run audit iteratively, focusing on a spec or a directory at a time if they want. If the user passes a scope hint (e.g. "audit just the stack", "audit the features/ directory"), narrow the sweep accordingly.
+
+### Phase 3: Identify Drift
+
+Systematically compare specs against the evidence from Phase 2. Look for these categories of drift:
+
+#### Stack Drift
+- `stack.md` names a framework/library/runtime that is not installed or is a different major version in the manifest
+- `stack.md` specifies a database, hosting, or CI/CD platform that doesn't match what the code or config uses
+- `stack.md` declares a testing framework the code does not actually use (or the code uses a different one)
+- A dependency in the manifest is conspicuously absent from `stack.md` and is load-bearing (e.g., a major framework, an ORM, an auth library)
+
+#### Architecture Drift
+- `architecture.md` describes a project structure that doesn't match the actual top-level directory layout
+- `architecture.md` defines a data model whose entities/fields differ from the schema, migrations, or type definitions in code
+- `architecture.md` documents API routes that don't exist in the router, or the router exposes routes not documented
+- `architecture.md` describes component architecture (e.g., "dashboard is split into X, Y, Z components") that doesn't match the actual component tree
+- `architecture.md` specifies environment variables that are absent from `.env.example` / config, or vice versa
+
+#### Style Drift
+- The style guide (`style.md` or `style.html`) defines design tokens that the actual global stylesheet / Tailwind config does not use
+- The style guide specifies an icon library but the code imports a different one
+- The style guide specifies typography (fonts, weights) that the actual font loading / CSS does not use
+- Colors hardcoded in components don't correspond to any token in the style guide
+- `gspec/design/` contains a mockup for a screen that the code does not implement (possible dead mockup), or the code has a screen with no corresponding mockup and the feature PRD references one
+
+#### Practice Drift
+- `practices.md` mandates a testing framework, coverage threshold, or test layout that the actual test suite does not follow
+- `practices.md` specifies a linter/formatter that is not installed or configured
+- `practices.md` describes a commit message convention or branching strategy that `git log` / branch structure does not reflect (flag only when the divergence is clear and consistent, not based on one or two commits)
+- `practices.md` defines a pipeline or deployment workflow that CI/CD files don't implement
+
+#### Feature Drift
+- A capability in a feature PRD is marked `- [x]` but the code does not implement it (false positive — checkbox claims completion that isn't there)
+- A capability is marked `- [ ]` but the code appears to implement it (false negative — checkbox should be updated)
+- A feature PRD's acceptance criteria describe behavior that the code explicitly handles differently
+- A feature PRD references a data field, endpoint, or UI element whose implementation has diverged (e.g., PRD says "users can filter by tag", code has filter-by-category)
+
+#### Profile Drift (rare; treat conservatively)
+- The profile's stated audience, scope, or value proposition conflicts with what the product actually does in code (e.g., profile says "B2B only" but the code has a consumer signup flow)
+- **Profile drift is usually a signal to update the product, not the spec.** Flag profile drift for user discussion rather than recommending an automatic spec update.
+
+**Do NOT flag:**
+- Minor wording or style differences that don't change meaning
+- Sections that are aspirational by nature (profile vision, roadmap notes, "future work" sections)
+- Implementation details that are legitimately below the spec's intended abstraction level (e.g., spec says "uses PostgreSQL"; code uses PostgreSQL via Prisma — no drift)
+- Missing information in a spec (gaps are for `gspec-architect` to fill; audit is for contradictions with reality, not omissions)
+- Minor version drift in dependencies when only the major/minor was specified
+- Differences in levels of detail (one side being more specific than the other is not drift)
+
+### Phase 4: Present Findings for Reconciliation
+
+If no drift is found, tell the user the specs accurately reflect the codebase and stop.
+
+If drift is found:
+
+1. **Summarize** the total number of discrepancies, grouped by category
+2. **Present each discrepancy one at a time**, in order of severity (load-bearing facts first — stack and data model before styling nits)
+
+For each discrepancy, present:
+
+```
+### Drift [N]: [Brief title]
+
+**Category:** [Stack / Architecture / Style / Practice / Feature / Profile]
+
+**Spec says:**
+- **[File, section]**: [exact quote or precise summary]
+
+**Code shows:**
+- **[File path(s), or brief evidence summary]**: [what the code actually does]
+
+**Why this matters:** [1-2 sentences on the consequence if left unresolved — e.g., "The implement command will import a library that isn't installed."]
+
+**Recommended action:** [One of: Update spec to match code / Keep spec and flag code for fix / Defer]
+
+**Options:**
+1. **Update spec to match code** — Apply this change to [File X]: [summary of edit]
+2. **Keep the spec as-is** — The code is wrong and should be fixed separately. Audit will leave the spec unchanged.
+3. **Defer** — Skip this finding for now.
+
+Which would you like?
+```
+
+**Wait for the user's response before proceeding.** The user may:
+- Choose an option by number
+- Propose a different resolution (e.g., partially update the spec)
+- Ask for more context (show more code, quote more of the spec)
+- Skip the discrepancy (defer)
+
+After the user decides, immediately apply the resolution (update the spec if requested), then present the next discrepancy.
+
+### Phase 5: Apply Updates
+
+When updating specs to match the code:
+
+- **Surgical updates only** — change the minimum text needed to reflect reality
+- **Preserve format and tone** — match the existing document's style, heading structure, and voice
+- **Preserve `spec-version` metadata** — do not alter or remove it. Markdown uses YAML frontmatter; `gspec/style.html` uses a first-line HTML comment.
+- **Capability checkboxes**: when updating a `[ ]` to `[x]` (or vice versa) based on what the code actually does, only check the box when the code meets every acceptance criterion listed under that capability. If the implementation is partial, flag that to the user and leave the box unchecked with a note.
+- **Do not rewrite sections** — if a one-line change resolves the drift, make a one-line change
+- **Do not add changelog annotations** — git history captures what changed
+
+### Phase 6: Final Verification
+
+After all discrepancies have been resolved (or deferred):
+
+1. **Re-read the updated specs** briefly to confirm the edits landed correctly
+2. **Present a summary:**
+   - Total discrepancies found, grouped by category
+   - Number where spec was updated to match code
+   - Number where spec was kept as-is (code flagged for follow-up)
+   - Number deferred
+   - List of files that were updated
+3. **Flag code follow-ups**: if the user chose "Keep the spec and fix code" for any finding, list those at the end as a punch list so they don't get lost. Do not modify code — this is a reference list for the user or a follow-up implement run.
+
+---
+
+## Rules
+
+- **Never modify code.** This command only reads code and updates specs. If a drift suggests the code should change, list it in the code-follow-up summary and let the user decide whether to run `/gspec-implement` or fix it themselves.
+- **Never create new spec files.** Audit only updates existing gspec documents.
+- **Never silently update specs.** Every change requires user approval via the drift resolution flow.
+- **One discrepancy at a time.** Do not batch resolutions — the user decides each one individually.
+- **Be precise about the evidence.** Quote the spec, cite the file and line range where the code contradicts it. Vague drift reports ("the architecture is out of date") are not actionable.
+- **Prioritize by impact.** Present drifts that would cause incorrect implementation or confused future work first. Cosmetic drift comes last.
+- **Treat the profile conservatively.** Profile drift usually reflects an intentional pivot and deserves a human decision, not an automatic spec update.
+- **Respect the scope hint.** If the user passes a hint like "audit the stack only", stick to it.
+
+---
+
+## Tone & Style
+
+- Precise and analytical — you are documenting observable evidence, not opining
+- Neutral when presenting options — recommend but do not presume
+- Efficient — get to the drift quickly, don't over-explain what each spec is for
+- Evidence-first — every finding cites specific files (spec + code) so the user can verify
+
+$ARGUMENTS

package/dist/claude/gspec-feature/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gspec-feature
-description: Generate one or more product requirements documents (PRDs) for features
+description: Generate product requirements documents (PRDs) for features in gspec/features/. TRIGGER when the user wants to plan, spec, propose, document, or expand a feature/capability before coding — e.g. "add a feature for X", "write a PRD", "spec out Y", "plan this feature", "what should the auth flow do", "new feature idea", "draft requirements". Prefer this skill over writing freeform feature docs.
 ---
 
 You are a senior Product Manager at a high-performing software company.