natureco-cli 5.18.3 → 5.20.0

package/skills/brutalist-skill/SKILL.md

@@ -0,0 +1,92 @@
+---
+name: industrial-brutalist-ui
+description: Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
+---
+
+# SKILL: Industrial Brutalism & Tactical Telemetry UI
+
+## 1. Skill Meta
+**Name:** Industrial Brutalism & Tactical Telemetry Interface Engineering
+**Description:** Advanced proficiency in architecting web interfaces that synthesize mid-century Swiss Typographic design, industrial manufacturing manuals, and retro-futuristic aerospace/military terminal interfaces. This discipline requires absolute mastery over rigid modular grids, extreme typographic scale contrast, purely utilitarian color palettes, and the programmatic simulation of analog degradation (halftones, CRT scanlines, bitmap dithering). The objective is to construct digital environments that project raw functionality, mechanical precision, and high data density, deliberately discarding conventional consumer UI patterns.
+
+## 2. Visual Archetypes
+The design system operates by merging two distinct but highly compatible visual paradigms. **Pick ONE per project and commit to it. Do not alternate or mix both modes within the same interface.**
+
+### 2.1 Swiss Industrial Print
+Derived from 1960s corporate identity systems and heavy machinery blueprints.
+*   **Characteristics:** High-contrast light modes (newsprint/off-white substrates). Reliance on monolithic, heavy sans-serif typography. Unforgiving structural grids outlined by visible dividing lines. Aggressive, asymmetric use of negative space punctuated by oversized, viewport-bleeding numerals or letterforms. Heavy use of primary red as an alert/accent color.
+
+### 2.2 Tactical Telemetry & CRT Terminal
+Derived from classified military databases, legacy mainframes, and aerospace Heads-Up Displays (HUDs).
+*   **Characteristics:** Dark mode exclusivity. High-density tabular data presentation. Absolute dominance of monospaced typography. Integration of technical framing devices (ASCII brackets, crosshairs). Application of simulated hardware limitations (phosphor glow, scanlines, low bit-depth rendering).
+
+## 3. Typographic Architecture
+Typography is the primary structural and decorative infrastructure. Imagery is secondary. The system demands extreme variance in scale, weight, and spacing.
+
+### 3.1 Macro-Typography (Structural Headers)
+*   **Classification:** Neo-Grotesque / Heavy Sans-Serif.
+*   **Optimal Web Fonts:** Neue Haas Grotesk (Black), Inter (Extra Bold/Black), Archivo Black, Roboto Flex (Heavy), Monument Extended.
+*   **Implementation Parameters:**
+    *   **Scale:** Deployed at massive scales using fluid typography (e.g., `clamp(4rem, 10vw, 15rem)`).
+    *   **Tracking (Letter-spacing):** Extremely tight, often negative (`-0.03em` to `-0.06em`), forcing glyphs to form solid architectural blocks.
+    *   **Leading (Line-height):** Highly compressed (`0.85` to `0.95`).
+    *   **Casing:** Exclusively uppercase for structural impact.
+
+### 3.2 Micro-Typography (Data & Telemetry)
+*   **Classification:** Monospace / Technical Sans.
+*   **Optimal Web Fonts:** JetBrains Mono, IBM Plex Mono, Space Mono, VT323, Courier Prime.
+*   **Implementation Parameters:**
+    *   **Scale:** Fixed and small (`10px` to `14px` / `0.7rem` to `0.875rem`).
+    *   **Tracking:** Generous (`0.05em` to `0.1em`) to simulate mechanical typewriter spacing or terminal matrices.
+    *   **Leading:** Standard to tight (`1.2` to `1.4`).
+    *   **Casing:** Exclusively uppercase. Used for all metadata, navigation, unit IDs, and coordinates.
+
+### 3.3 Textural Contrast (Artistic Disruption)
+*   **Classification:** High-Contrast Serif.
+*   **Optimal Web Fonts:** Playfair Display, EB Garamond, Times New Roman.
+*   **Implementation Parameters:** Used exceedingly sparingly. Must be subjected to heavy post-processing (halftone filters, 1-bit dithering) to degrade vector perfection and create textural juxtaposition against the clean sans-serifs.
+
+## 4. Color System
+The color architecture is uncompromising. Gradients, soft drop shadows, and modern translucency are strictly prohibited. Colors simulate physical media or primitive emissive displays.
+
+**CRITICAL: Choose ONE substrate palette per project and use it consistently. Never mix light and dark substrates within the same interface.**
+
+### If Swiss Industrial Print (Light):
+*   **Background:** `#F4F4F0` or `#EAE8E3` (Matte, unbleached documentation paper).
+*   **Foreground:** `#050505` to `#111111` (Carbon Ink).
+*   **Accent:** `#E61919` or `#FF2A2A` (Aviation/Hazard Red). This is the ONLY accent color. Used for strike-throughs, thick structural dividing lines, or vital data highlights.
+
+### If Tactical Telemetry (Dark):
+*   **Background:** `#0A0A0A` or `#121212` (Deactivated CRT. Avoid pure `#000000`).
+*   **Foreground:** `#EAEAEA` (White phosphor). This is the primary text color.
+*   **Accent:** `#E61919` or `#FF2A2A` (Aviation/Hazard Red). Same red, same rules.
+*   **Terminal Green (`#4AF626`):** Optional. Use ONLY for a single specific UI element (e.g., one status indicator or one data readout) — never as a general text color. If it doesn't serve a clear purpose, omit it entirely.
+
+## 5. Layout and Spatial Engineering
+The layout must appear mathematically engineered. It rejects conventional web padding in favor of visible compartmentalization.
+
+*   **The Blueprint Grid:** Strict adherence to CSS Grid architectures. Elements do not float; they are anchored precisely to grid tracks and intersections.
+*   **Visible Compartmentalization:** Extensive utilization of solid borders (`1px` or `2px solid`) to delineate distinct zones of information. Horizontal rules (`<hr>`) frequently span the entire container width to segregate operational units.
+*   **Bimodal Density:** Layouts oscillate between extreme data density (tightly packed monospace metadata clustered together) and vast expanses of calculated negative space framing macro-typography.
+*   **Geometry:** Absolute rejection of `border-radius`. All corners must be exactly 90 degrees to enforce mechanical rigidity.
+
+## 6. UI Components and Symbology
+Standard web UI conventions are replaced with utilitarian, industrial graphic elements.
+
+*   **Syntax Decoration:** Utilization of ASCII characters to frame data points.
+    *   *Framing:* `[ DELIVERY SYSTEMS ]`, `< RE-IND >`
+    *   *Directional:* `>>>`, `///`, `\\\\`
+*   **Industrial Markers:** Prominent integration of registration (`®`), copyright (`©`), and trademark (`™`) symbols functioning as structural geometric elements rather than legal text.
+*   **Technical Assets:** Integration of crosshairs (`+`) at grid intersections, repeating vertical lines (barcodes), thick horizontal warning stripes, and randomized string data (e.g., `REV 2.6`, `UNIT / D-01`) to simulate active mechanical processes.
+
+## 7. Textural and Post-Processing Effects
+To prevent the design from appearing purely digital, simulated analog degradation is engineered into the frontend via CSS and SVG filters.
+
+*   **Halftone and 1-Bit Dithering:** Transforming continuous-tone images or large serif typography into dot-matrix patterns. Achieved via pre-processing or CSS `mix-blend-mode: multiply` overlays combined with SVG radial dot patterns.
+*   **CRT Scanlines:** For terminal interfaces, applying a `repeating-linear-gradient` to the background to simulate horizontal electron beam sweeps (e.g., `repeating-linear-gradient(0deg, transparent, transparent 2px, rgba(0,0,0,0.1) 2px, rgba(0,0,0,0.1) 4px)`).
+*   **Mechanical Noise:** A global, low-opacity SVG static/noise filter applied to the DOM root to introduce a unified physical grain across both dark and light modes.
+
+## 8. Web Engineering Directives
+1.  **Grid Determinism:** Utilize `display: grid; gap: 1px;` with contrasting parent/child background colors to generate mathematically perfect, razor-thin dividing lines without complex border declarations.
+2.  **Semantic Rigidity:** Construct the DOM using precise semantic tags (`<data>`, `<samp>`, `<kbd>`, `<output>`, `<dl>`) to accurately reflect the technical nature of the telemetry.
+3.  **Typography Clamping:** Implement CSS `clamp()` functions exclusively for macro-typography to ensure massive text scales aggressively while maintaining structural integrity across viewports.

package/skills/bulk-file-operations/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: bulk-file-operations
+description: Perform bulk file rename, move, copy, and format conversions
+category: Productivity
+---
+
+# Bulk File Operations
+
+## Overview
+Perform bulk file rename, move, copy, and format conversions. This skill helps you apply structured, repeatable methods for consistent results.
+
+## When to Use
+- When you need to apply bulk file operations best practices
+- When establishing processes or standards for your workflow
+- When training team members on bulk file operations
+- When automating or optimizing bulk file operations tasks
+
+## Instructions
+1. **Assess**: Evaluate the current state, requirements, and constraints
+2. **Plan**: Define the approach, steps, and success criteria
+3. **Execute**: Follow the established patterns and best practices
+4. **Verify**: Check results against expected outcomes and quality standards
+5. **Iterate**: Refine based on feedback and lessons learned
+
+## Examples
+```
+User: Help me apply bulk file operations for my current project
+Assistant: I'll help you apply bulk file operations step by step...
+```
+
+## Related Skills
+- Use with `workflow` tool for orchestrated execution
+- Combine with `task` tool for delegated processing
+- Reference `system-prompt` for system-level integration

package/skills/cache-responses/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: cache-responses
+description: Cache LLM responses for identical or similar queries to avoid redundant API calls
+category: Token Savings
+---
+
+# Cache Responses
+
+## Overview
+Cache LLM responses for identical or similar queries to avoid redundant API calls. This skill helps you apply structured, repeatable methods for consistent results.
+
+## When to Use
+- When you need to apply cache responses best practices
+- When establishing processes or standards for your workflow
+- When training team members on cache responses
+- When automating or optimizing cache responses tasks
+
+## Instructions
+1. **Assess**: Evaluate the current state, requirements, and constraints
+2. **Plan**: Define the approach, steps, and success criteria
+3. **Execute**: Follow the established patterns and best practices
+4. **Verify**: Check results against expected outcomes and quality standards
+5. **Iterate**: Refine based on feedback and lessons learned
+
+## Examples
+```
+User: Help me apply cache responses for my current project
+Assistant: I'll help you apply cache responses step by step...
+```
+
+## Related Skills
+- Use with `workflow` tool for orchestrated execution
+- Combine with `task` tool for delegated processing
+- Reference `system-prompt` for system-level integration

package/skills/caching-strategy/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: caching-strategy
+description: Design caching strategy with Redis, CDN, browser cache, and cache invalidation patterns
+category: Software Development
+---
+
+# Caching Strategy
+
+## Overview
+Design caching strategy with Redis, CDN, browser cache, and cache invalidation patterns. This skill helps you apply structured, repeatable methods for consistent results.
+
+## When to Use
+- When you need to apply caching strategy best practices
+- When establishing processes or standards for your workflow
+- When training team members on caching strategy
+- When automating or optimizing caching strategy tasks
+
+## Instructions
+1. **Assess**: Evaluate the current state, requirements, and constraints
+2. **Plan**: Define the approach, steps, and success criteria
+3. **Execute**: Follow the established patterns and best practices
+4. **Verify**: Check results against expected outcomes and quality standards
+5. **Iterate**: Refine based on feedback and lessons learned
+
+## Examples
+```
+User: Help me apply caching strategy for my current project
+Assistant: I'll help you apply caching strategy step by step...
+```
+
+## Related Skills
+- Use with `workflow` tool for orchestrated execution
+- Combine with `task` tool for delegated processing
+- Reference `system-prompt` for system-level integration

package/skills/calendar-optimization/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: calendar-optimization
+description: Optimize calendar scheduling with time blocking and meeting buffers
+category: Productivity
+---
+
+# Calendar Optimization
+
+## Overview
+Optimize calendar scheduling with time blocking and meeting buffers. This skill helps you apply structured, repeatable methods for consistent results.
+
+## When to Use
+- When you need to apply calendar optimization best practices
+- When establishing processes or standards for your workflow
+- When training team members on calendar optimization
+- When automating or optimizing calendar optimization tasks
+
+## Instructions
+1. **Assess**: Evaluate the current state, requirements, and constraints
+2. **Plan**: Define the approach, steps, and success criteria
+3. **Execute**: Follow the established patterns and best practices
+4. **Verify**: Check results against expected outcomes and quality standards
+5. **Iterate**: Refine based on feedback and lessons learned
+
+## Examples
+```
+User: Help me apply calendar optimization for my current project
+Assistant: I'll help you apply calendar optimization step by step...
+```
+
+## Related Skills
+- Use with `workflow` tool for orchestrated execution
+- Combine with `task` tool for delegated processing
+- Reference `system-prompt` for system-level integration

package/skills/canvas-design/SKILL.md

@@ -0,0 +1,130 @@
+---
+name: canvas-design
+description: Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
+license: Complete terms in LICENSE.txt
+---
+
+These are instructions for creating design philosophies - aesthetic movements that are then EXPRESSED VISUALLY. Output only .md files, .pdf files, and .png files.
+
+Complete this in two steps:
+1. Design Philosophy Creation (.md file)
+2. Express by creating it on a canvas (.pdf file or .png file)
+
+First, undertake this task:
+
+## DESIGN PHILOSOPHY CREATION
+
+To begin, create a VISUAL PHILOSOPHY (not layouts or templates) that will be interpreted through:
+- Form, space, color, composition
+- Images, graphics, shapes, patterns
+- Minimal text as visual accent
+
+### THE CRITICAL UNDERSTANDING
+- What is received: Some subtle input or instructions by the user that should be taken into account, but used as a foundation; it should not constrain creative freedom.
+- What is created: A design philosophy/aesthetic movement.
+- What happens next: Then, the same version receives the philosophy and EXPRESSES IT VISUALLY - creating artifacts that are 90% visual design, 10% essential text.
+
+Consider this approach:
+- Write a manifesto for an art movement
+- The next phase involves making the artwork
+
+The philosophy must emphasize: Visual expression. Spatial communication. Artistic interpretation. Minimal words.
+
+### HOW TO GENERATE A VISUAL PHILOSOPHY
+
+**Name the movement** (1-2 words): "Brutalist Joy" / "Chromatic Silence" / "Metabolist Dreams"
+
+**Articulate the philosophy** (4-6 paragraphs - concise but complete):
+
+To capture the VISUAL essence, express how the philosophy manifests through:
+- Space and form
+- Color and material
+- Scale and rhythm
+- Composition and balance
+- Visual hierarchy
+
+**CRITICAL GUIDELINES:**
+- **Avoid redundancy**: Each design aspect should be mentioned once. Avoid repeating points about color theory, spatial relationships, or typographic principles unless adding new depth.
+- **Emphasize craftsmanship REPEATEDLY**: The philosophy MUST stress multiple times that the final work should appear as though it took countless hours to create, was labored over with care, and comes from someone at the absolute top of their field. This framing is essential - repeat phrases like "meticulously crafted," "the product of deep expertise," "painstaking attention," "master-level execution."
+- **Leave creative space**: Remain specific about the aesthetic direction, but concise enough that the next Claude has room to make interpretive choices also at a extremely high level of craftmanship.
+
+The philosophy must guide the next version to express ideas VISUALLY, not through text. Information lives in design, not paragraphs.
+
+### PHILOSOPHY EXAMPLES
+
+**"Concrete Poetry"**
+Philosophy: Communication through monumental form and bold geometry.
+Visual expression: Massive color blocks, sculptural typography (huge single words, tiny labels), Brutalist spatial divisions, Polish poster energy meets Le Corbusier. Ideas expressed through visual weight and spatial tension, not explanation. Text as rare, powerful gesture - never paragraphs, only essential words integrated into the visual architecture. Every element placed with the precision of a master craftsman.
+
+**"Chromatic Language"**
+Philosophy: Color as the primary information system.
+Visual expression: Geometric precision where color zones create meaning. Typography minimal - small sans-serif labels letting chromatic fields communicate. Think Josef Albers' interaction meets data visualization. Information encoded spatially and chromatically. Words only to anchor what color already shows. The result of painstaking chromatic calibration.
+
+**"Analog Meditation"**
+Philosophy: Quiet visual contemplation through texture and breathing room.
+Visual expression: Paper grain, ink bleeds, vast negative space. Photography and illustration dominate. Typography whispered (small, restrained, serving the visual). Japanese photobook aesthetic. Images breathe across pages. Text appears sparingly - short phrases, never explanatory blocks. Each composition balanced with the care of a meditation practice.
+
+**"Organic Systems"**
+Philosophy: Natural clustering and modular growth patterns.
+Visual expression: Rounded forms, organic arrangements, color from nature through architecture. Information shown through visual diagrams, spatial relationships, iconography. Text only for key labels floating in space. The composition tells the story through expert spatial orchestration.
+
+**"Geometric Silence"**
+Philosophy: Pure order and restraint.
+Visual expression: Grid-based precision, bold photography or stark graphics, dramatic negative space. Typography precise but minimal - small essential text, large quiet zones. Swiss formalism meets Brutalist material honesty. Structure communicates, not words. Every alignment the work of countless refinements.
+
+*These are condensed examples. The actual design philosophy should be 4-6 substantial paragraphs.*
+
+### ESSENTIAL PRINCIPLES
+- **VISUAL PHILOSOPHY**: Create an aesthetic worldview to be expressed through design
+- **MINIMAL TEXT**: Always emphasize that text is sparse, essential-only, integrated as visual element - never lengthy
+- **SPATIAL EXPRESSION**: Ideas communicate through space, form, color, composition - not paragraphs
+- **ARTISTIC FREEDOM**: The next Claude interprets the philosophy visually - provide creative room
+- **PURE DESIGN**: This is about making ART OBJECTS, not documents with decoration
+- **EXPERT CRAFTSMANSHIP**: Repeatedly emphasize the final work must look meticulously crafted, labored over with care, the product of countless hours by someone at the top of their field
+
+**The design philosophy should be 4-6 paragraphs long.** Fill it with poetic design philosophy that brings together the core vision. Avoid repeating the same points. Keep the design philosophy generic without mentioning the intention of the art, as if it can be used wherever. Output the design philosophy as a .md file.
+
+---
+
+## DEDUCING THE SUBTLE REFERENCE
+
+**CRITICAL STEP**: Before creating the canvas, identify the subtle conceptual thread from the original request.
+
+**THE ESSENTIAL PRINCIPLE**:
+The topic is a **subtle, niche reference embedded within the art itself** - not always literal, always sophisticated. Someone familiar with the subject should feel it intuitively, while others simply experience a masterful abstract composition. The design philosophy provides the aesthetic language. The deduced topic provides the soul - the quiet conceptual DNA woven invisibly into form, color, and composition.
+
+This is **VERY IMPORTANT**: The reference must be refined so it enhances the work's depth without announcing itself. Think like a jazz musician quoting another song - only those who know will catch it, but everyone appreciates the music.
+
+---
+
+## CANVAS CREATION
+
+With both the philosophy and the conceptual framework established, express it on a canvas. Take a moment to gather thoughts and clear the mind. Use the design philosophy created and the instructions below to craft a masterpiece, embodying all aspects of the philosophy with expert craftsmanship.
+
+**IMPORTANT**: For any type of content, even if the user requests something for a movie/game/book, the approach should still be sophisticated. Never lose sight of the idea that this should be art, not something that's cartoony or amateur.
+
+To create museum or magazine quality work, use the design philosophy as the foundation. Create one single page, highly visual, design-forward PDF or PNG output (unless asked for more pages). Generally use repeating patterns and perfect shapes. Treat the abstract philosophical design as if it were a scientific bible, borrowing the visual language of systematic observation—dense accumulation of marks, repeated elements, or layered patterns that build meaning through patient repetition and reward sustained viewing. Add sparse, clinical typography and systematic reference markers that suggest this could be a diagram from an imaginary discipline, treating the invisible subject with the same reverence typically reserved for documenting observable phenomena. Anchor the piece with simple phrase(s) or details positioned subtly, using a limited color palette that feels intentional and cohesive. Embrace the paradox of using analytical visual language to express ideas about human experience: the result should feel like an artifact that proves something ephemeral can be studied, mapped, and understood through careful attention. This is true art. 
+
+**Text as a contextual element**: Text is always minimal and visual-first, but let context guide whether that means whisper-quiet labels or bold typographic gestures. A punk venue poster might have larger, more aggressive type than a minimalist ceramics studio identity. Most of the time, font should be thin. All use of fonts must be design-forward and prioritize visual communication. Regardless of text scale, nothing falls off the page and nothing overlaps. Every element must be contained within the canvas boundaries with proper margins. Check carefully that all text, graphics, and visual elements have breathing room and clear separation. This is non-negotiable for professional execution. **IMPORTANT: Use different fonts if writing text. Search the `./canvas-fonts` directory. Regardless of approach, sophistication is non-negotiable.**
+
+Download and use whatever fonts are needed to make this a reality. Get creative by making the typography actually part of the art itself -- if the art is abstract, bring the font onto the canvas, not typeset digitally.
+
+To push boundaries, follow design instinct/intuition while using the philosophy as a guiding principle. Embrace ultimate design freedom and choice. Push aesthetics and design to the frontier. 
+
+**CRITICAL**: To achieve human-crafted quality (not AI-generated), create work that looks like it took countless hours. Make it appear as though someone at the absolute top of their field labored over every detail with painstaking care. Ensure the composition, spacing, color choices, typography - everything screams expert-level craftsmanship. Double-check that nothing overlaps, formatting is flawless, every detail perfect. Create something that could be shown to people to prove expertise and rank as undeniably impressive.
+
+Output the final result as a single, downloadable .pdf or .png file, alongside the design philosophy used as a .md file.
+
+---
+
+## FINAL STEP
+
+**IMPORTANT**: The user ALREADY said "It isn't perfect enough. It must be pristine, a masterpiece if craftsmanship, as if it were about to be displayed in a museum."
+
+**CRITICAL**: To refine the work, avoid adding more graphics; instead refine what has been created and make it extremely crisp, respecting the design philosophy and the principles of minimalism entirely. Rather than adding a fun filter or refactoring a font, consider how to make the existing composition more cohesive with the art. If the instinct is to call a new function or draw a new shape, STOP and instead ask: "How can I make what's already here more of a piece of art?"
+
+Take a second pass. Go back to the code and refine/polish further to make this a philosophically designed masterpiece.
+
+## MULTI-PAGE OPTION
+
+To create additional pages when requested, create more creative pages along the same lines as the design philosophy but distinctly different as well. Bundle those pages in the same .pdf or many .pngs. Treat the first page as just a single page in a whole coffee table book waiting to be filled. Make the next pages unique twists and memories of the original. Have them almost tell a story in a very tasteful way. Exercise full creative freedom.

package/skills/cavecrew/SKILL.md

@@ -0,0 +1,82 @@
+---
+name: cavecrew
+description: >
+  Decision guide for delegating to caveman-style subagents. Tells the main
+  thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder`
+  (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the
+  work inline or using vanilla `Explore`. Subagent output is caveman-compressed
+  so the tool-result injected back into main context is ~60% smaller — main
+  context lasts longer across long sessions.
+  Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer",
+  "save context", "compressed agent output".
+---
+
+Cavecrew = three subagent presets that emit caveman output. Same job as Anthropic defaults (`Explore`, edit-style agents, reviewer); difference is the tool-result they return is compressed, so main context shrinks per delegation.
+
+## When to use cavecrew vs alternatives
+
+| Task | Use |
+|---|---|
+| "Where is X defined / what calls Y / list uses of Z" | `cavecrew-investigator` |
+| Same but you also want suggestions/architecture commentary | `Explore` (vanilla) |
+| Surgical edit, ≤2 files, scope obvious | `cavecrew-builder` |
+| New feature / 3+ files / cross-cutting refactor | Main thread or `feature-dev:code-architect` |
+| Review diff, branch, or file for bugs | `cavecrew-reviewer` |
+| Deep code review with rationale + alternatives | `Code Reviewer` (vanilla) |
+| One-line answer you already know | Main thread, no subagent |
+
+Rule of thumb: **if you'd want the subagent's output in 1/3 the tokens, pick cavecrew. If you'd want prose, pick vanilla.**
+
+## Why this exists (the real win)
+
+Subagent tool results get injected into main context verbatim. A vanilla `Explore` that returns 2k tokens of prose costs 2k tokens of main-context budget every time. The same finding from `cavecrew-investigator` returns ~700 tokens. Across 20 delegations in one session that's the difference between context exhaustion and finishing the task.
+
+## Output contracts
+
+What main thread can rely on per agent:
+
+**`cavecrew-investigator`**
+```
+<Header>:
+- path:line — `symbol` — short note
+totals: <counts>.
+```
+Or `No match.` Always file-path-first, line-number-attached, backticked symbols. Safe to grep with `path:\d+`.
+
+**`cavecrew-builder`**
+```
+<path:line-range> — <change ≤10 words>.
+verified: <re-read OK | mismatch @ path:line>.
+```
+Or one of: `too-big.` / `needs-confirm.` / `ambiguous.` / `regressed.` (terminal first token).
+
+**`cavecrew-reviewer`**
+```
+path:line: <emoji> <severity>: <problem>. <fix>.
+totals: N🔴 N🟡 N🔵 N❓
+```
+Or `No issues.` Findings sorted file → line ascending.
+
+## Chaining patterns
+
+**Locate → fix → verify** (most common):
+1. `cavecrew-investigator` returns site list.
+2. Main thread picks 1-2 sites, hands paths to `cavecrew-builder`.
+3. `cavecrew-reviewer` audits the diff.
+
+**Parallel scout** (when investigation is broad):
+Spawn 2-3 `cavecrew-investigator` calls in one message (different angles: defs vs callers vs tests). Aggregate in main thread.
+
+**Single-shot edit** (when site is already known):
+Skip investigator. Hand exact path:line to `cavecrew-builder` directly.
+
+## What NOT to do
+
+- Don't use `cavecrew-builder` when you don't already know the file. Spawn investigator first or main thread will eat tokens passing context.
+- Don't chain `cavecrew-investigator → cavecrew-builder` for a 5-file refactor. Builder will return `too-big.` and you'll have wasted a turn.
+- Don't ask `cavecrew-reviewer` for "general feedback" — it returns findings only, no architecture opinions. Use `Code Reviewer` for that.
+- Don't expect prose. Cavecrew output is structured, sometimes terse to the point of cryptic. If a human will read it directly, paraphrase.
+
+## Auto-clarity (inherited)
+
+Subagents drop caveman → normal English for security warnings, irreversible-action confirmations, and any output where fragment ambiguity could be misread. Resume caveman after.

package/skills/caveman-commit/SKILL.md

@@ -0,0 +1,65 @@
+---
+name: caveman-commit
+description: >
+  Ultra-compressed commit message generator. Cuts noise from commit messages while preserving
+  intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why"
+  isn't obvious. Use when user says "write a commit", "commit message", "generate commit",
+  "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
+---
+
+Write commit messages terse and exact. Conventional Commits format. No fluff. Why over what.
+
+## Rules
+
+**Subject line:**
+- `<type>(<scope>): <imperative summary>` — `<scope>` optional
+- Types: `feat`, `fix`, `refactor`, `perf`, `docs`, `test`, `chore`, `build`, `ci`, `style`, `revert`
+- Imperative mood: "add", "fix", "remove" — not "added", "adds", "adding"
+- ≤50 chars when possible, hard cap 72
+- No trailing period
+- Match project convention for capitalization after the colon
+
+**Body (only if needed):**
+- Skip entirely when subject is self-explanatory
+- Add body only for: non-obvious *why*, breaking changes, migration notes, linked issues
+- Wrap at 72 chars
+- Bullets `-` not `*`
+- Reference issues/PRs at end: `Closes #42`, `Refs #17`
+
+**What NEVER goes in:**
+- "This commit does X", "I", "we", "now", "currently" — the diff says what
+- "As requested by..." — use Co-authored-by trailer
+- "Generated with Claude Code" or any AI attribution — unless the user's own rule requires an `Assisted-by`/AI-attribution trailer, then add it as a trailer
+- Emoji (unless project convention requires)
+- Restating the file name when scope already says it
+
+## Examples
+
+Diff: new endpoint for user profile with body explaining the why
+- ❌ "feat: add a new endpoint to get user profile information from the database"
+- ✅
+  ```
+  feat(api): add GET /users/:id/profile
+
+  Mobile client needs profile data without the full user payload
+  to reduce LTE bandwidth on cold-launch screens.
+
+  Closes #128
+  ```
+
+Diff: breaking API change
+- ✅
+  ```
+  feat(api)!: rename /v1/orders to /v1/checkout
+
+  BREAKING CHANGE: clients on /v1/orders must migrate to /v1/checkout
+  before 2026-06-01. Old route returns 410 after that date.
+  ```
+
+## Auto-Clarity
+
+Always include body for: breaking changes, security fixes, data migrations, anything reverting a prior commit. Never compress these into subject-only — future debuggers need the context.
+
+## Boundaries
+
+Only generates the commit message. Does not run `git commit`, does not stage files, does not amend. Output the message as a code block ready to paste. "stop caveman-commit" or "normal mode": revert to verbose commit style.

package/skills/caveman-help/SKILL.md

@@ -0,0 +1,63 @@
+---
+name: caveman-help
+description: >
+  Quick-reference card for all caveman modes, skills, and commands.
+  One-shot display, not a persistent mode. Trigger: /caveman-help,
+  "caveman help", "what caveman commands", "how do I use caveman".
+---
+
+# Caveman Help
+
+Display this reference card when invoked. One-shot — do NOT change mode, write flag files, or persist anything. Output in caveman style.
+
+## Modes
+
+| Mode | Trigger | What change |
+|------|---------|-------------|
+| **Lite** | `/caveman lite` | Drop filler. Keep sentence structure. |
+| **Full** | `/caveman` | Drop articles, filler, pleasantries, hedging. Fragments OK. Default. |
+| **Ultra** | `/caveman ultra` | Extreme compression. Bare fragments. Tables over prose. |
+| **Wenyan-Lite** | `/caveman wenyan-lite` | Classical Chinese style, light compression. |
+| **Wenyan-Full** | `/caveman wenyan` | Full 文言文. Maximum classical terseness. |
+| **Wenyan-Ultra** | `/caveman wenyan-ultra` | Extreme. Ancient scholar on a budget. |
+
+Mode stick until changed or session end.
+
+## Skills
+
+| Skill | Trigger | What it do |
+|-------|---------|-----------|
+| **caveman-commit** | `/caveman-commit` | Terse commit messages. Conventional Commits. ≤50 char subject. |
+| **caveman-review** | `/caveman-review` | One-line PR comments: `L42: bug: user null. Add guard.` |
+| **caveman-compress** | `/caveman-compress <file>` | Compress .md files to caveman prose. Saves ~46% input tokens. |
+| **caveman-help** | `/caveman-help` | This card. |
+
+## Deactivate
+
+Say "stop caveman" or "normal mode". Resume anytime with `/caveman`.
+
+## Language
+
+Keep user's language by default. User write Portuguese → reply Portuguese caveman. Compress the style, not the language. Technical terms, code, commands, commit types, and exact error strings stay verbatim unless user ask for translation.
+
+## Configure Default Mode
+
+Default mode = `full`. Change it:
+
+**Environment variable** (highest priority):
+```bash
+export CAVEMAN_DEFAULT_MODE=ultra
+```
+
+**Config file** (`~/.config/caveman/config.json`):
+```json
+{ "defaultMode": "lite" }
+```
+
+Set `"off"` to disable auto-activation on session start. User can still activate manually with `/caveman`.
+
+Resolution: env var > config file > `full`.
+
+## More
+
+Full docs: https://github.com/JuliusBrussee/caveman

package/skills/caveman-review/SKILL.md

@@ -0,0 +1,55 @@
+---
+name: caveman-review
+description: >
+  Ultra-compressed code review comments. Cuts noise from PR feedback while preserving
+  the actionable signal. Each comment is one line: location, problem, fix. Use when user
+  says "review this PR", "code review", "review the diff", "/review", or invokes
+  /caveman-review. Auto-triggers when reviewing pull requests.
+---
+
+Write code review comments terse and actionable. One line per finding. Location, problem, fix. No throat-clearing.
+
+## Rules
+
+**Format:** `L<line>: <problem>. <fix>.` — or `<file>:L<line>: ...` when reviewing multi-file diffs.
+
+**Severity prefix (optional, when mixed):**
+- `🔴 bug:` — broken behavior, will cause incident
+- `🟡 risk:` — works but fragile (race, missing null check, swallowed error)
+- `🔵 nit:` — style, naming, micro-optim. Author can ignore
+- `❓ q:` — genuine question, not a suggestion
+
+**Drop:**
+- "I noticed that...", "It seems like...", "You might want to consider..."
+- "This is just a suggestion but..." — use `nit:` instead
+- "Great work!", "Looks good overall but..." — say it once at the top, not per comment
+- Restating what the line does — the reviewer can read the diff
+- Hedging ("perhaps", "maybe", "I think") — if unsure use `q:`
+
+**Keep:**
+- Exact line numbers
+- Exact symbol/function/variable names in backticks
+- Concrete fix, not "consider refactoring this"
+- The *why* if the fix isn't obvious from the problem statement
+
+## Examples
+
+❌ "I noticed that on line 42 you're not checking if the user object is null before accessing the email property. This could potentially cause a crash if the user is not found in the database. You might want to add a null check here."
+
+✅ `L42: 🔴 bug: user can be null after .find(). Add guard before .email.`
+
+❌ "It looks like this function is doing a lot of things and might benefit from being broken up into smaller functions for readability."
+
+✅ `L88-140: 🔵 nit: 50-line fn does 4 things. Extract validate/normalize/persist.`
+
+❌ "Have you considered what happens if the API returns a 429? I think we should probably handle that case."
+
+✅ `L23: 🟡 risk: no retry on 429. Wrap in withBackoff(3).`
+
+## Auto-Clarity
+
+Drop terse mode for: security findings (CVE-class bugs need full explanation + reference), architectural disagreements (need rationale, not just a one-liner), and onboarding contexts where the author is new and needs the "why". In those cases write a normal paragraph, then resume terse for the rest.
+
+## Boundaries
+
+Reviews only — does not write the code fix, does not approve/request-changes, does not run linters. Output the comment(s) ready to paste into the PR. "stop caveman-review" or "normal mode": revert to verbose review style.

package/skills/caveman-stats/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: caveman-stats
+description: >
+  Show real token usage and estimated savings for the current session.
+  Reads directly from the Claude Code session log — no AI estimation.
+  Triggers on /caveman-stats. Output is injected by the mode-tracker hook;
+  the model itself does not compute the numbers.
+---
+
+This skill is delivered by `hooks/caveman-stats.js` (read by `hooks/caveman-mode-tracker.js` on `/caveman-stats`). The model does not need to do anything when this skill fires — the hook returns `decision: "block"` with the formatted stats as the reason. The user sees the numbers immediately.