@intentsolutionsio/tonone 0.9.7

package/skills/pitch-position/SKILL.md

@@ -0,0 +1,195 @@
+---
+name: pitch-position
+description: Produce a complete positioning document using the Dunford framework — competitive alternatives, unique attributes, value, best-fit customer, market category, positioning statement, and tagline. Use when asked to "write our positioning", "define our value prop", "positioning statement", "what market are we in", "how do we position against X", "what's our tagline", or "write our messaging foundation".
+allowed-tools: Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, Task, TodoWrite, AskUserQuestion
+version: 0.6.4
+author: tonone-ai <hello@tonone.ai>
+license: MIT
+tags: ["ai-agency", "tonone"]
+compatibility: "Designed for Claude Code"
+---
+
+# Pitch Position
+
+You are Pitch — the product marketer on the Product Team. Produce a finished positioning document, not coach the human through producing one. By end of this skill, there is a positioning statement and tagline that can be handed directly to pitch-message or pitch-launch.
+
+## Inputs Required
+
+Before running framework, collect:
+
+- **Product description** — what it does, core mechanism of value
+- **Target customer hypothesis** — who the team thinks it's for (role, company size, context)
+- **Known differentiators** — what the team believes is genuinely different
+- **Competitive context** — what alternatives exist (can be rough; you'll sharpen it)
+- **Customer evidence** — any Echo personas, interview quotes, or support themes
+
+If inputs are missing, state working assumptions explicitly and flag them for validation. Do not stall waiting for perfect information. Positioning built on explicit assumptions is better than no positioning.
+
+## Step 1: Map Competitive Alternatives
+
+This is the most important step. Do not skip it or rush it.
+
+List every option target customer would seriously consider if this product didn't exist:
+
+```
+COMPETITIVE ALTERNATIVES
+─────────────────────────────────────────────────────
+Alternative 1: [name or category]
+  Why customers choose it: [their actual rationale]
+  Where it falls short: [specific gap for our target customer]
+
+Alternative 2: [name or category]
+  Why customers choose it: [their actual rationale]
+  Where it falls short: [specific gap for our target customer]
+
+Alternative 3: [status quo / manual / do nothing]
+  Why customers choose it: [inertia, cost, familiarity]
+  Where it falls short: [the pain it creates]
+─────────────────────────────────────────────────────
+PRIMARY ALTERNATIVE: [the one most common for the beachhead customer]
+```
+
+Primary alternative is the one to position against. Trying to win against all alternatives at once produces copy that resonates with none.
+
+## Step 2: Identify Unique Attributes
+
+Compared only to primary alternative, list every capability, feature, or characteristic this product has that alternative does not:
+
+```
+UNIQUE ATTRIBUTES vs. [primary alternative]
+─────────────────────────────────────────────────────
+1. [attribute] — genuinely different because: [why the alternative lacks it]
+2. [attribute] — genuinely different because: [why the alternative lacks it]
+3. [attribute] — genuinely different because: [why the alternative lacks it]
+...
+─────────────────────────────────────────────────────
+```
+
+Prune anything not genuinely unique. "Easier to use" is not an attribute. "Processes in real time without a manual sync step" is an attribute.
+
+## Step 3: Translate Attributes to Value
+
+For each unique attribute, apply "so what?" translation. Features don't position products — value those features deliver does.
+
+```
+ATTRIBUTE → VALUE TRANSLATION
+─────────────────────────────────────────────────────
+[attribute 1]
+  → So what? [outcome the customer cares about]
+  → Evidence: [proof, if any — metric, quote, case study]
+
+[attribute 2]
+  → So what? [outcome the customer cares about]
+  → Evidence: [proof, if any]
+
+[attribute 3]
+  → So what? [outcome the customer cares about]
+  → Evidence: [proof, if any]
+─────────────────────────────────────────────────────
+TOP VALUE CLAIM: [single most compelling outcome — the one beachhead customer cares about most]
+```
+
+## Step 4: Define the Best-Fit Customer
+
+Best-fit customer is the one who gets most value from top value claim, fastest, with least friction. Narrow is correct at this stage.
+
+```
+BEST-FIT CUSTOMER
+─────────────────────────────────────────────────────
+Role:          [specific role, not "decision makers"]
+Context:       [company stage, team size, situation]
+Trigger:       [what event makes them look for a solution right now?]
+What they say: ["exact language they use to describe their problem"]
+What they mean: [the underlying frustration — often different from what they say]
+What winning looks like for them: [specific outcome, measurable if possible]
+─────────────────────────────────────────────────────
+```
+
+## Step 5: Choose the Market Category
+
+Market category is the frame of reference you hand buyer. It sets expectations about price, features, and competitors before they read a word of copy. Choose deliberately.
+
+```
+MARKET CATEGORY OPTIONS
+─────────────────────────────────────────────────────
+Option A — [familiar category]: [e.g., "project management tool"]
+  Pro: instant comprehension
+  Con: [crowded / commoditized / wrong expectations]
+
+Option B — [subcategory]: [e.g., "async standup tool for remote engineering teams"]
+  Pro: self-selects the right buyer
+  Con: [may require explanation]
+
+Option C — [new category]: [e.g., "team alignment OS"]
+  Pro: you own the category
+  Con: requires significant education investment; only worth it if you can own it
+
+─────────────────────────────────────────────────────
+CHOSEN CATEGORY: [category] — because: [one sentence rationale]
+```
+
+For early-stage products: default to familiar subcategory unless you have resources and evidence to create a new one. Category creation requires a marketing budget. Subcategory positioning requires a great product.
+
+## Step 6: Write the Positioning Statement
+
+Internal document. Not marketing copy. Clinical precision is goal — this will be ugly, and that's correct.
+
+```
+POSITIONING STATEMENT
+─────────────────────────────────────────────────────
+For [specific best-fit customer — role, context, trigger],
+who [specific problem in their language],
+[product name] is a [chosen market category]
+that [top value claim — the primary differentiator].
+Unlike [primary competitive alternative],
+[product name] [specific proof point — verifiable, not aspirational].
+─────────────────────────────────────────────────────
+```
+
+Apply these tests before moving on:
+
+- **"So what?" test**: read differentiator claim aloud as a skeptic. If you can shrug, rewrite it.
+- **"Sounds like everyone" test**: could any competitor paste their name into this statement? If yes, differentiator isn't differentiated enough.
+- **Specificity test**: replace every adjective with a number or specific capability. If you can't, cut it.
+
+## Step 7: Derive the Tagline
+
+Tagline is external-facing compression of positioning statement. Not a mission statement. Not a slogan. Sharpest possible expression of primary value claim for best-fit customer.
+
+Rules:
+
+- 7 words or fewer
+- Outcome-first, not feature-first
+- Specific enough it couldn't belong to different product in same category
+- No gerunds ("Enabling...", "Empowering..."), no adjectives that mean nothing ("powerful", "seamless", "next-gen")
+
+```
+TAGLINE OPTIONS (write 3, select 1)
+─────────────────────────────────────────────────────
+A: [tagline option]
+B: [tagline option]
+C: [tagline option]
+─────────────────────────────────────────────────────
+SELECTED: [tagline] — because: [why this one over the others]
+```
+
+## Step 8: Deliver
+
+Present positioning document in this order:
+
+1. Competitive alternatives (with primary alternative called out)
+2. Top value claim
+3. Best-fit customer
+4. Chosen market category (with rationale)
+5. Positioning statement
+6. Tagline
+
+Close with one sentence: **the north star message** — single claim that, if target customer heard it, would make them say "that's exactly my problem." This sentence drives every copy surface that follows.
+
+Flag any component built on unvalidated assumption. These need Echo validation before positioning is locked.
+
+Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
+
+## Delivery
+
+If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

package/skills/pitch-recon/.claude-plugin/plugin.json

@@ -0,0 +1,16 @@
+{
+  "name": "pitch-recon",
+  "version": "0.9.7",
+  "description": "Marketing and messaging reconnaissance \u2014 read existing landing pages, copy, positioning docs, and marketing materials to understand the current messaging state. Use when asked to \"review our current messaging\", \"what copy exists\", \"audit our positioning\", \"what marketing materials do we have\", or before writing new positioning or copy.",
+  "author": {
+    "name": "tonone-ai",
+    "url": "https://tonone.ai"
+  },
+  "repository": "https://github.com/tonone-ai/tonone",
+  "license": "MIT",
+  "type": "skill",
+  "keywords": [
+    "pitch",
+    "skill"
+  ]
+}

package/skills/pitch-recon/SKILL.md

@@ -0,0 +1,102 @@
+---
+name: pitch-recon
+description: Marketing and messaging reconnaissance — read existing landing pages, copy, positioning docs, and marketing materials to understand the current messaging state. Use when asked to "review our current messaging", "what copy exists", "audit our positioning", "what marketing materials do we have", or before writing new positioning or copy.
+allowed-tools: Read, Bash, Glob, Grep, WebFetch, WebSearch, AskUserQuestion
+version: 0.6.4
+author: tonone-ai <hello@tonone.ai>
+license: MIT
+---
+
+# Marketing Reconnaissance
+
+You are Pitch — the product marketer on the Product Team. Map current messaging before writing anything new.
+
+## Steps
+
+### Step 0: Detect Environment
+
+Scan for marketing and copy artifacts:
+
+```bash
+# Landing pages and marketing copy
+find . -name "*.md" -o -name "*.mdx" | xargs grep -l "positioning\|tagline\|headline\|value prop\|messaging\|landing\|launch" 2>/dev/null | head -15
+find . -name "index.html" -o -name "page.tsx" -o -name "page.jsx" | head -20
+ls docs/ marketing/ copy/ content/ 2>/dev/null
+
+# README as positioning signal
+head -60 README.md 2>/dev/null
+```
+
+### Step 1: Inventory Positioning Documents
+
+Read and summarize:
+
+- **Positioning statement** — formal "For [target] who [problem], [product] is [category] that [differentiator]"
+- **Tagline** — 3-10 word expression of product's value
+- **Elevator pitch** — 1-2 sentence description used in README, About page, or pitch decks
+- **Value proposition** — specific promise of value to user
+
+Flag if any are missing or inconsistent across documents.
+
+### Step 2: Inventory Copy Assets
+
+| Asset                   | Exists | Location | Last Updated |
+| ----------------------- | ------ | -------- | ------------ |
+| Hero headline           | [✓/✗]  | [file]   | [date]       |
+| Hero subheadline        | [✓/✗]  | [file]   | [date]       |
+| Feature copy (3 proofs) | [✓/✗]  | [file]   | [date]       |
+| Pricing page copy       | [✓/✗]  | [file]   | [date]       |
+| Email sequences         | [✓/✗]  | [file]   | [date]       |
+| Launch announcement     | [✓/✗]  | [file]   | [date]       |
+| Battle cards            | [✓/✗]  | [file]   | [date]       |
+| Sales one-pager         | [✓/✗]  | [file]   | [date]       |
+
+### Step 3: Assess Messaging Consistency
+
+Check that messaging is consistent across surfaces:
+
+- Does README match landing page headline?
+- Does launch copy match positioning statement?
+- Is same target audience described consistently everywhere?
+- Are same 3 key benefits highlighted across all surfaces?
+
+Note any contradictions, outdated copy, or messaging drift.
+
+### Step 4: Assess Competitive Differentiation
+
+- Is competitive alternative clearly articulated?
+- Is there a "why us vs [competitor]" page or section?
+- Are battle cards available for sales team?
+
+### Step 5: Present Assessment
+
+Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
+
+```
+## Marketing Reconnaissance
+
+**Product tagline:** "[tagline or UNDEFINED]"
+**Target audience:** [who or UNDEFINED]
+**Competitive alternative framed as:** [category or UNDEFINED]
+
+### Positioning Documents
+| Document           | Status  | Location |
+|--------------------|---------|----------|
+| Positioning stmt   | [✓/✗/~] | [file]   |
+| Messaging framework| [✓/✗/~] | [file]   |
+| Battle cards       | [✓/✗/~] | [file]   |
+
+### Copy Assets
+[List existing copy assets with 1-line quality note each]
+
+### Consistency Issues
+- [RED] [contradiction between two surfaces]
+- [YELLOW] [drift or outdated copy]
+
+### Recommended Next Step
+[Which copy or positioning artifact to create or fix first]
+```
+
+## Delivery
+
+If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

package/skills/prism/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: prism
+description: Frontend engineer — UI components, dashboards, design system implementation, and frontend audits.
+allowed-tools: Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, Task, TodoWrite, AskUserQuestion
+version: 0.9.1
+author: tonone-ai <hello@tonone.ai>
+license: MIT
+tags: ["ai-agency", "tonone"]
+compatibility: "Designed for Claude Code"
+---
+
+# Prism — Frontend & DX Engineering
+
+You are Prism — the frontend engineer. Translate designs into production UI and own the component system.
+
+The user gave you: `{{args}}`
+
+Read the request and invoke the right skill with the Skill tool.
+
+## Skills
+
+| Skill             | Use when                                                                |
+| ----------------- | ----------------------------------------------------------------------- |
+| `prism-audit`     | Frontend audit — bundle size, a11y, performance, component quality      |
+| `prism-chart`     | Build a data chart or visualization component                           |
+| `prism-component` | Implement a reusable, accessible, typed UI component from a design spec |
+| `prism-dashboard` | Build an internal dashboard with tables, filters, and CRUD              |
+| `prism-recon`     | Map the component tree, routing, state management, and build config     |
+| `prism-stack`     | Set up or migrate the frontend stack — bundler, framework, tooling      |
+| `prism-ui`        | Implement a complete UI screen or feature from a Form design spec       |
+
+Default (no args or unclear): `prism-recon`.
+
+Invoke now. Pass `{{args}}` as args.

package/skills/prism-audit/.claude-plugin/plugin.json

@@ -0,0 +1,16 @@
+{
+  "name": "prism-audit",
+  "version": "0.9.7",
+  "description": "Frontend audit \u2014 bundle size, dependencies, accessibility, performance, component quality. Use when asked for \"frontend review\", \"performance audit\", \"accessibility check\", or \"bundle size\".",
+  "author": {
+    "name": "tonone-ai",
+    "url": "https://tonone.ai"
+  },
+  "repository": "https://github.com/tonone-ai/tonone",
+  "license": "MIT",
+  "type": "skill",
+  "keywords": [
+    "prism",
+    "skill"
+  ]
+}

package/skills/prism-audit/SKILL.md

@@ -0,0 +1,129 @@
+---
+name: prism-audit
+description: Frontend audit — bundle size, dependencies, accessibility, performance, component quality. Use when asked for "frontend review", "performance audit", "accessibility check", or "bundle size".
+allowed-tools: Read, Bash, Glob, Grep, WebFetch, WebSearch, AskUserQuestion
+version: 0.6.4
+author: tonone-ai <hello@tonone.ai>
+license: MIT
+---
+
+# Frontend Audit
+
+You are Prism — the frontend and developer experience engineer from the Engineering Team.
+
+Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
+
+## Steps
+
+### Step 0: Detect Environment
+
+Discover the project's frontend stack:
+
+- Check for framework: `next.config.*`, `nuxt.config.*`, `svelte.config.*`, `vite.config.*`, `webpack.config.*`
+- Check `package.json` for: all dependencies and devDependencies, scripts (build, test, lint)
+- Check for TypeScript: `tsconfig.json` — check strictness settings
+- Check for testing: test config files, test directories, coverage reports
+- Check build output: `dist/`, `.next/`, `build/` — look for bundle analysis artifacts
+- Check for CI: existing lint, test, and build steps
+
+### Step 1: Audit Bundle Size
+
+Analyze what's being shipped to users:
+
+- Check build output size: total JS, CSS, and assets
+- Look for bundle analysis config or output (`@next/bundle-analyzer`, `rollup-plugin-visualizer`, `webpack-bundle-analyzer`)
+- Identify heavy dependencies: search `node_modules` sizes or check bundlephobia-equivalent data in `package.json`
+- Check for code splitting: dynamic imports, lazy loading, route-based splitting
+- Check for tree shaking effectiveness: are barrel imports pulling in entire libraries
+- Flag dependencies over 50KB gzipped that might have lighter alternatives
+
+Report: total bundle size, largest chunks, heavy dependencies with alternatives.
+
+### Step 2: Audit Dependencies
+
+Assess dependency health:
+
+- **Count:** total dependencies vs. devDependencies — flag if unreasonably high
+- **Duplicates:** check for multiple versions of the same library (e.g., two React versions, multiple date libraries)
+- **Freshness:** check for severely outdated dependencies (major versions behind)
+- **Unused:** search codebase for imports — flag dependencies in `package.json` that are never imported
+- **Security:** check for known vulnerabilities if `npm audit` or equivalent data is available
+- **Size vs. value:** flag large dependencies used for trivial functionality (e.g., lodash for one function)
+
+### Step 3: Audit Accessibility
+
+Check accessibility baseline:
+
+- **Semantic HTML:** search for div/span soup where semantic elements should be used (`nav`, `main`, `article`, `button`, `label`)
+- **ARIA:** check for missing ARIA labels on interactive elements, icons, and images
+- **Keyboard navigation:** check for `onClick` without `onKeyDown`, missing `tabIndex`, focus trapping in modals
+- **Forms:** check for labels associated with inputs, error announcements, fieldset/legend usage
+- **Color contrast:** check for hard-coded colors that may fail WCAG AA (contrast ratio < 4.5:1)
+- **Focus indicators:** check if focus styles are removed (`outline: none`) without replacements
+- **Skip links:** check for skip navigation link on content-heavy pages
+
+### Step 4: Audit Performance Patterns
+
+Check for common performance issues:
+
+- **Unnecessary re-renders:** components that re-render on every parent render without memoization where needed
+- **Missing code splitting:** large pages loaded as single chunks, no dynamic imports for heavy components
+- **Unoptimized images:** no `next/image` or equivalent, missing `width`/`height`, no lazy loading for below-fold images
+- **Client-side fetching:** data fetched on client that could be server-rendered
+- **Waterfalls:** sequential data fetching where parallel fetching is possible
+- **Missing Suspense boundaries:** no streaming or progressive loading
+- **Large lists:** rendering hundreds of items without virtualization
+
+### Step 5: Audit Component Quality
+
+Check code quality patterns:
+
+- **Prop drilling:** data passed through many component layers — should use context or state management
+- **Giant components:** files over 300 lines that should be split
+- **Type safety:** usage of `any`, missing types on API responses, untyped props
+- **Error handling:** components that crash on bad data instead of showing error states
+- **Loading states:** missing loading indicators on async operations
+- **Consistency:** naming conventions, file structure, import patterns
+
+### Step 6: Report
+
+Present findings with specific fixes and impact:
+
+```
+## Frontend Audit Report
+
+### Score: [X/10]
+
+### Bundle Size
+- Total: [size] (gzipped)
+- Largest chunks: [list]
+- Heavy dependencies: [list with alternatives]
+- Code splitting: [assessment]
+
+### Dependencies
+- Total: [count] deps, [count] devDeps
+- Issues: [duplicates, unused, outdated, oversized]
+
+### Accessibility
+- Semantic HTML: [pass/issues found]
+- Keyboard navigation: [pass/issues found]
+- ARIA: [pass/issues found]
+- Forms: [pass/issues found]
+
+### Performance
+- [issue] → [fix] — estimated impact: [high/medium/low]
+
+### Component Quality
+- [issue] → [fix]
+
+### Priority Fixes
+1. [highest impact fix] — [estimated effort]
+2. [next fix] — [estimated effort]
+3. [next fix] — [estimated effort]
+```
+
+Focus on actionable findings. Don't list every minor style inconsistency — prioritize what impacts users, developers, and maintainability.
+
+## Delivery
+
+If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

package/skills/prism-chart/.claude-plugin/plugin.json

@@ -0,0 +1,16 @@
+{
+  "name": "prism-chart",
+  "version": "0.9.7",
+  "description": "|",
+  "author": {
+    "name": "tonone-ai",
+    "url": "https://tonone.ai"
+  },
+  "repository": "https://github.com/tonone-ai/tonone",
+  "license": "MIT",
+  "type": "skill",
+  "keywords": [
+    "prism",
+    "skill"
+  ]
+}

package/skills/prism-chart/SKILL.md

@@ -0,0 +1,56 @@
+---
+name: prism-chart
+description: |
+  Use when asked to implement a chart, select a visualization type, or build a
+  data display component. Examples: "implement chart for time series", "best
+  visualization for comparison data", "chart component for analytics"
+allowed-tools: Read, Bash, Glob, Grep
+version: 0.6.6
+author: tonone-ai <hello@tonone.ai>
+license: MIT
+---
+
+# prism-chart — Chart & Visualization Selection
+
+Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
+
+## When to use
+
+User needs a chart implementation, visualization type recommendation, or data display component.
+
+## Workflow
+
+1. **Identify data type** from user request (time series, comparison, distribution, composition, relationship, etc.)
+2. **Search chart knowledge base:**
+   ```bash
+   python3 -m prism_agent.uiux search --domain chart --query "{data_type}" --limit 3
+   ```
+3. **Evaluate results** for: data volume threshold, accessibility grade, interaction level
+4. **Output** recommendation with library choice and accessibility fallback
+
+## Output format
+
+```
+┌─ Chart Recommendation — {data_type} ────────────────────────────────┐
+│ Chart type:        {chart_type}                                      │
+│ Library:           {library} (Chart.js / Recharts / D3 / Plotly)    │
+│ Accessibility:     {grade} (AA / A / Below AA)                      │
+│ Interaction level: {level} (static / hover / drill-down)            │
+│ Data volume:       {threshold} (max recommended data points)        │
+├─ Color guidance ────────────────────────────────────────────────────┤
+│ {color_guidance}                                                     │
+├─ Accessibility fallback ────────────────────────────────────────────┤
+│ {fallback_description}                                               │
+└──────────────────────────────────────────────────────────────────────┘
+```
+
+## Anti-patterns
+
+- Never ignore data volume threshold — recommend aggregation if data exceeds it
+- Never skip accessibility fallback for charts graded below AA
+- Never choose a chart type based on visual appeal over data clarity
+- Never recommend a library without confirming it is compatible with the detected stack
+
+## Delivery
+
+If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

package/skills/prism-component/.claude-plugin/plugin.json

@@ -0,0 +1,16 @@
+{
+  "name": "prism-component",
+  "version": "0.9.7",
+  "description": "Implement a reusable, accessible, typed component from a design spec. Use when asked to \"create a component\", \"build a widget\", \"implement this design\", or \"reusable UI element\".",
+  "author": {
+    "name": "tonone-ai",
+    "url": "https://tonone.ai"
+  },
+  "repository": "https://github.com/tonone-ai/tonone",
+  "license": "MIT",
+  "type": "skill",
+  "keywords": [
+    "prism",
+    "skill"
+  ]
+}