@bastani/atomic 0.5.11 → 0.5.12-1

package/.agents/skills/adapt/SKILL.md

@@ -0,0 +1,199 @@
+---
+name: adapt
+description: Adapt designs to work across different screen sizes, devices, contexts, or platforms. Implements breakpoints, fluid layouts, and touch targets. Use when the user mentions responsive design, mobile layouts, breakpoints, viewport adaptation, or cross-device compatibility.
+version: 2.1.1
+user-invocable: true
+argument-hint: "[target] [context (mobile, tablet, print...)]"
+---
+
+Adapt existing designs to work effectively across different contexts - different screen sizes, devices, platforms, or use cases.
+
+## MANDATORY PREPARATION
+
+Invoke /impeccable — it contains design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet, you MUST run /impeccable teach first. Additionally gather: target platforms/devices and usage contexts.
+
+---
+
+## Assess Adaptation Challenge
+
+Understand what needs adaptation and why:
+
+1. **Identify the source context**:
+   - What was it designed for originally? (Desktop web? Mobile app?)
+   - What assumptions were made? (Large screen? Mouse input? Fast connection?)
+   - What works well in current context?
+
+2. **Understand target context**:
+   - **Device**: Mobile, tablet, desktop, TV, watch, print?
+   - **Input method**: Touch, mouse, keyboard, voice, gamepad?
+   - **Screen constraints**: Size, resolution, orientation?
+   - **Connection**: Fast wifi, slow 3G, offline?
+   - **Usage context**: On-the-go vs desk, quick glance vs focused reading?
+   - **User expectations**: What do users expect on this platform?
+
+3. **Identify adaptation challenges**:
+   - What won't fit? (Content, navigation, features)
+   - What won't work? (Hover states on touch, tiny touch targets)
+   - What's inappropriate? (Desktop patterns on mobile, mobile patterns on desktop)
+
+**CRITICAL**: Adaptation is not just scaling - it's rethinking the experience for the new context.
+
+## Plan Adaptation Strategy
+
+Create context-appropriate strategy:
+
+### Mobile Adaptation (Desktop → Mobile)
+
+**Layout Strategy**:
+- Single column instead of multi-column
+- Vertical stacking instead of side-by-side
+- Full-width components instead of fixed widths
+- Bottom navigation instead of top/side navigation
+
+**Interaction Strategy**:
+- Touch targets 44x44px minimum (not hover-dependent)
+- Swipe gestures where appropriate (lists, carousels)
+- Bottom sheets instead of dropdowns
+- Thumbs-first design (controls within thumb reach)
+- Larger tap areas with more spacing
+
+**Content Strategy**:
+- Progressive disclosure (don't show everything at once)
+- Prioritize primary content (secondary content in tabs/accordions)
+- Shorter text (more concise)
+- Larger text (16px minimum)
+
+**Navigation Strategy**:
+- Hamburger menu or bottom navigation
+- Reduce navigation complexity
+- Sticky headers for context
+- Back button in navigation flow
+
+### Tablet Adaptation (Hybrid Approach)
+
+**Layout Strategy**:
+- Two-column layouts (not single or three-column)
+- Side panels for secondary content
+- Master-detail views (list + detail)
+- Adaptive based on orientation (portrait vs landscape)
+
+**Interaction Strategy**:
+- Support both touch and pointer
+- Touch targets 44x44px but allow denser layouts than phone
+- Side navigation drawers
+- Multi-column forms where appropriate
+
+### Desktop Adaptation (Mobile → Desktop)
+
+**Layout Strategy**:
+- Multi-column layouts (use horizontal space)
+- Side navigation always visible
+- Multiple information panels simultaneously
+- Fixed widths with max-width constraints (don't stretch to 4K)
+
+**Interaction Strategy**:
+- Hover states for additional information
+- Keyboard shortcuts
+- Right-click context menus
+- Drag and drop where helpful
+- Multi-select with Shift/Cmd
+
+**Content Strategy**:
+- Show more information upfront (less progressive disclosure)
+- Data tables with many columns
+- Richer visualizations
+- More detailed descriptions
+
+### Print Adaptation (Screen → Print)
+
+**Layout Strategy**:
+- Page breaks at logical points
+- Remove navigation, footer, interactive elements
+- Black and white (or limited color)
+- Proper margins for binding
+
+**Content Strategy**:
+- Expand shortened content (show full URLs, hidden sections)
+- Add page numbers, headers, footers
+- Include metadata (print date, page title)
+- Convert charts to print-friendly versions
+
+### Email Adaptation (Web → Email)
+
+**Layout Strategy**:
+- Narrow width (600px max)
+- Single column only
+- Inline CSS (no external stylesheets)
+- Table-based layouts (for email client compatibility)
+
+**Interaction Strategy**:
+- Large, obvious CTAs (buttons not text links)
+- No hover states (not reliable)
+- Deep links to web app for complex interactions
+
+## Implement Adaptations
+
+Apply changes systematically:
+
+### Responsive Breakpoints
+
+Choose appropriate breakpoints:
+- Mobile: 320px-767px
+- Tablet: 768px-1023px
+- Desktop: 1024px+
+- Or content-driven breakpoints (where design breaks)
+
+### Layout Adaptation Techniques
+
+- **CSS Grid/Flexbox**: Reflow layouts automatically
+- **Container Queries**: Adapt based on container, not viewport
+- **`clamp()`**: Fluid sizing between min and max
+- **Media queries**: Different styles for different contexts
+- **Display properties**: Show/hide elements per context
+
+### Touch Adaptation
+
+- Increase touch target sizes (44x44px minimum)
+- Add more spacing between interactive elements
+- Remove hover-dependent interactions
+- Add touch feedback (ripples, highlights)
+- Consider thumb zones (easier to reach bottom than top)
+
+### Content Adaptation
+
+- Use `display: none` sparingly (still downloads)
+- Progressive enhancement (core content first, enhancements on larger screens)
+- Lazy loading for off-screen content
+- Responsive images (`srcset`, `picture` element)
+
+### Navigation Adaptation
+
+- Transform complex nav to hamburger/drawer on mobile
+- Bottom nav bar for mobile apps
+- Persistent side navigation on desktop
+- Breadcrumbs on smaller screens for context
+
+**IMPORTANT**: Test on real devices, not just browser DevTools. Device emulation is helpful but not perfect.
+
+**NEVER**:
+- Hide core functionality on mobile (if it matters, make it work)
+- Assume desktop = powerful device (consider accessibility, older machines)
+- Use different information architecture across contexts (confusing)
+- Break user expectations for platform (mobile users expect mobile patterns)
+- Forget landscape orientation on mobile/tablet
+- Use generic breakpoints blindly (use content-driven breakpoints)
+- Ignore touch on desktop (many desktop devices have touch)
+
+## Verify Adaptations
+
+Test thoroughly across contexts:
+
+- **Real devices**: Test on actual phones, tablets, desktops
+- **Different orientations**: Portrait and landscape
+- **Different browsers**: Safari, Chrome, Firefox, Edge
+- **Different OS**: iOS, Android, Windows, macOS
+- **Different input methods**: Touch, mouse, keyboard
+- **Edge cases**: Very small screens (320px), very large screens (4K)
+- **Slow connections**: Test on throttled network
+
+Remember: You're a cross-platform design expert. Make experiences that feel native to each context while maintaining brand and functionality consistency. Adapt intentionally, test thoroughly.

package/.agents/skills/advanced-evaluation/SKILL.md

@@ -0,0 +1,402 @@
+---
+name: advanced-evaluation
+description: This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment. Part of the context engineering skill suite — also activates when the user mentions "context engineering" or "context-engineering" in the context of evaluating LLM output quality.
+---
+
+# Advanced Evaluation
+
+This skill covers production-grade techniques for evaluating LLM outputs using LLMs as judges. It synthesizes research from academic papers, industry practices, and practical implementation experience into actionable patterns for building reliable evaluation systems.
+
+**Key insight**: LLM-as-a-Judge is not a single technique but a family of approaches, each suited to different evaluation contexts. Choosing the right approach and mitigating known biases is the core competency this skill develops.
+
+## When to Activate
+
+Activate this skill when:
+
+- Building automated evaluation pipelines for LLM outputs
+- Comparing multiple model responses to select the best one
+- Establishing consistent quality standards across evaluation teams
+- Debugging evaluation systems that show inconsistent results
+- Designing A/B tests for prompt or model changes
+- Creating rubrics for human or automated evaluation
+- Analyzing correlation between automated and human judgments
+
+## Core Concepts
+
+### The Evaluation Taxonomy
+
+Select between two primary approaches based on whether ground truth exists:
+
+**Direct Scoring** — Use when objective criteria exist (factual accuracy, instruction following, toxicity). A single LLM rates one response on a defined scale. Achieves moderate-to-high reliability for well-defined criteria. Watch for score calibration drift and inconsistent scale interpretation.
+
+**Pairwise Comparison** — Use for subjective preferences (tone, style, persuasiveness). An LLM compares two responses and selects the better one. Achieves higher human-judge agreement than direct scoring for preference tasks (Zheng et al., 2023). Watch for position bias and length bias.
+
+### The Bias Landscape
+
+Mitigate these systematic biases in every evaluation system:
+
+**Position Bias**: First-position responses get preferential treatment. Mitigate by evaluating twice with swapped positions, then apply majority vote or consistency check.
+
+**Length Bias**: Longer responses score higher regardless of quality. Mitigate by explicitly prompting to ignore length and applying length-normalized scoring.
+
+**Self-Enhancement Bias**: Models rate their own outputs higher. Mitigate by using different models for generation and evaluation.
+
+**Verbosity Bias**: Excessive detail scores higher even when unnecessary. Mitigate with criteria-specific rubrics that penalize irrelevant detail.
+
+**Authority Bias**: Confident tone scores higher regardless of accuracy. Mitigate by requiring evidence citation and adding a fact-checking layer.
+
+### Metric Selection Framework
+
+Match metrics to the evaluation task structure:
+
+| Task Type | Primary Metrics | Secondary Metrics |
+|-----------|-----------------|-------------------|
+| Binary classification (pass/fail) | Recall, Precision, F1 | Cohen's kappa |
+| Ordinal scale (1-5 rating) | Spearman's rho, Kendall's tau | Cohen's kappa (weighted) |
+| Pairwise preference | Agreement rate, Position consistency | Confidence calibration |
+| Multi-label | Macro-F1, Micro-F1 | Per-label precision/recall |
+
+Prioritize systematic disagreement patterns over absolute agreement rates because a judge that consistently disagrees with humans on specific criteria is more problematic than one with random noise.
+
+## Evaluation Approaches
+
+### Direct Scoring Implementation
+
+Build direct scoring with three components: clear criteria, a calibrated scale, and structured output format.
+
+**Criteria Definition Pattern**:
+```
+Criterion: [Name]
+Description: [What this criterion measures]
+Weight: [Relative importance, 0-1]
+```
+
+**Scale Calibration** — Choose scale granularity based on rubric detail:
+- 1-3: Binary with neutral option, lowest cognitive load
+- 1-5: Standard Likert, best balance of granularity and reliability
+- 1-10: Use only with detailed per-level rubrics because calibration is harder
+
+**Prompt Structure for Direct Scoring**:
+```
+You are an expert evaluator assessing response quality.
+
+## Task
+Evaluate the following response against each criterion.
+
+## Original Prompt
+{prompt}
+
+## Response to Evaluate
+{response}
+
+## Criteria
+{for each criterion: name, description, weight}
+
+## Instructions
+For each criterion:
+1. Find specific evidence in the response
+2. Score according to the rubric (1-{max} scale)
+3. Justify your score with evidence
+4. Suggest one specific improvement
+
+## Output Format
+Respond with structured JSON containing scores, justifications, and summary.
+```
+
+Always require justification before the score in all scoring prompts because research shows this improves reliability by 15-25% compared to score-first approaches.
+
+### Pairwise Comparison Implementation
+
+Apply position bias mitigation in every pairwise evaluation:
+
+1. First pass: Response A in first position, Response B in second
+2. Second pass: Response B in first position, Response A in second
+3. Consistency check: If passes disagree, return TIE with reduced confidence
+4. Final verdict: Consistent winner with averaged confidence
+
+**Prompt Structure for Pairwise Comparison**:
+```
+You are an expert evaluator comparing two AI responses.
+
+## Critical Instructions
+- Do NOT prefer responses because they are longer
+- Do NOT prefer responses based on position (first vs second)
+- Focus ONLY on quality according to the specified criteria
+- Ties are acceptable when responses are genuinely equivalent
+
+## Original Prompt
+{prompt}
+
+## Response A
+{response_a}
+
+## Response B
+{response_b}
+
+## Comparison Criteria
+{criteria list}
+
+## Instructions
+1. Analyze each response independently first
+2. Compare them on each criterion
+3. Determine overall winner with confidence level
+
+## Output Format
+JSON with per-criterion comparison, overall winner, confidence (0-1), and reasoning.
+```
+
+**Confidence Calibration** — Map confidence to position consistency:
+- Both passes agree: confidence = average of individual confidences
+- Passes disagree: confidence = 0.5, verdict = TIE
+
+### Rubric Generation
+
+Generate rubrics to reduce evaluation variance by 40-60% compared to open-ended scoring.
+
+**Include these rubric components**:
+1. **Level descriptions**: Clear boundaries for each score level
+2. **Characteristics**: Observable features that define each level
+3. **Examples**: Representative text for each level (optional but valuable)
+4. **Edge cases**: Guidance for ambiguous situations
+5. **Scoring guidelines**: General principles for consistent application
+
+**Set strictness calibration** for the use case:
+- **Lenient**: Lower passing bar, appropriate for encouraging iteration
+- **Balanced**: Typical production expectations
+- **Strict**: High standards for safety-critical or high-stakes evaluation
+
+Adapt rubrics to the domain — use domain-specific terminology. A code readability rubric mentions variables, functions, and comments. A medical accuracy rubric references clinical terminology and evidence standards.
+
+## Practical Guidance
+
+### Evaluation Pipeline Design
+
+Build production evaluation systems with these layers: Criteria Loader (rubrics + weights) -> Primary Scorer (direct or pairwise) -> Bias Mitigation (position swap, etc.) -> Confidence Scoring (calibration) -> Output (scores + justifications + confidence). See [Evaluation Pipeline Diagram](./references/evaluation-pipeline.md) for the full visual layout.
+
+### Decision Framework: Direct vs. Pairwise
+
+Apply this decision tree:
+
+```
+Is there an objective ground truth?
++-- Yes -> Direct Scoring
+|   Examples: factual accuracy, instruction following, format compliance
+|
++-- No -> Is it a preference or quality judgment?
+    +-- Yes -> Pairwise Comparison
+    |   Examples: tone, style, persuasiveness, creativity
+    |
+    +-- No -> Consider reference-based evaluation
+        Examples: summarization (compare to source), translation (compare to reference)
+```
+
+### Scaling Evaluation
+
+For high-volume evaluation, apply one of these strategies:
+
+1. **Panel of LLMs (PoLL)**: Use multiple models as judges and aggregate votes to reduce individual model bias. More expensive but more reliable for high-stakes decisions.
+
+2. **Hierarchical evaluation**: Use a fast cheap model for screening and an expensive model for edge cases. Requires calibration of the screening threshold.
+
+3. **Human-in-the-loop**: Automate clear cases and route low-confidence decisions to human review. Design feedback loops to improve automated evaluation over time.
+
+## Examples
+
+### Example 1: Direct Scoring for Accuracy
+
+**Input**:
+```
+Prompt: "What causes seasons on Earth?"
+Response: "Seasons are caused by Earth's tilted axis. As Earth orbits the Sun,
+different hemispheres receive more direct sunlight at different times of year."
+Criterion: Factual Accuracy (weight: 1.0)
+Scale: 1-5
+```
+
+**Output**:
+```json
+{
+  "criterion": "Factual Accuracy",
+  "score": 5,
+  "evidence": [
+    "Correctly identifies axial tilt as primary cause",
+    "Correctly explains differential sunlight by hemisphere",
+    "No factual errors present"
+  ],
+  "justification": "Response accurately explains the cause of seasons with correct
+scientific reasoning. Both the axial tilt and its effect on sunlight distribution
+are correctly described.",
+  "improvement": "Could add the specific tilt angle (23.5 degrees) for completeness."
+}
+```
+
+### Example 2: Pairwise Comparison with Position Swap
+
+**Input**:
+```
+Prompt: "Explain machine learning to a beginner"
+Response A: [Technical explanation with jargon]
+Response B: [Simple analogy-based explanation]
+Criteria: ["clarity", "accessibility"]
+```
+
+**First Pass (A first)**:
+```json
+{ "winner": "B", "confidence": 0.8 }
+```
+
+**Second Pass (B first)**:
+```json
+{ "winner": "A", "confidence": 0.6 }
+```
+(Note: Winner is A because B was in first position)
+
+**Mapped Second Pass**:
+```json
+{ "winner": "B", "confidence": 0.6 }
+```
+
+**Final Result**:
+```json
+{
+  "winner": "B",
+  "confidence": 0.7,
+  "positionConsistency": {
+    "consistent": true,
+    "firstPassWinner": "B",
+    "secondPassWinner": "B"
+  }
+}
+```
+
+### Example 3: Rubric Generation
+
+**Input**:
+```
+criterionName: "Code Readability"
+criterionDescription: "How easy the code is to understand and maintain"
+domain: "software engineering"
+scale: "1-5"
+strictness: "balanced"
+```
+
+**Output** (abbreviated):
+```json
+{
+  "levels": [
+    {
+      "score": 1,
+      "label": "Poor",
+      "description": "Code is difficult to understand without significant effort",
+      "characteristics": [
+        "No meaningful variable or function names",
+        "No comments or documentation",
+        "Deeply nested or convoluted logic"
+      ]
+    },
+    {
+      "score": 3,
+      "label": "Adequate",
+      "description": "Code is understandable with some effort",
+      "characteristics": [
+        "Most variables have meaningful names",
+        "Basic comments present for complex sections",
+        "Logic is followable but could be cleaner"
+      ]
+    },
+    {
+      "score": 5,
+      "label": "Excellent",
+      "description": "Code is immediately clear and maintainable",
+      "characteristics": [
+        "All names are descriptive and consistent",
+        "Comprehensive documentation",
+        "Clean, modular structure"
+      ]
+    }
+  ],
+  "edgeCases": [
+    {
+      "situation": "Code is well-structured but uses domain-specific abbreviations",
+      "guidance": "Score based on readability for domain experts, not general audience"
+    }
+  ]
+}
+```
+
+## Guidelines
+
+1. **Always require justification before scores** - Chain-of-thought prompting improves reliability by 15-25%
+
+2. **Always swap positions in pairwise comparison** - Single-pass comparison is corrupted by position bias
+
+3. **Match scale granularity to rubric specificity** - Don't use 1-10 without detailed level descriptions
+
+4. **Separate objective and subjective criteria** - Use direct scoring for objective, pairwise for subjective
+
+5. **Include confidence scores** - Calibrate to position consistency and evidence strength
+
+6. **Define edge cases explicitly** - Ambiguous situations cause the most evaluation variance
+
+7. **Use domain-specific rubrics** - Generic rubrics produce generic (less useful) evaluations
+
+8. **Validate against human judgments** - Automated evaluation is only valuable if it correlates with human assessment
+
+9. **Monitor for systematic bias** - Track disagreement patterns by criterion, response type, model
+
+10. **Design for iteration** - Evaluation systems improve with feedback loops
+
+## Gotchas
+
+1. **Scoring without justification**: Scores lack grounding and are difficult to debug. Always require evidence-based justification before the score.
+
+2. **Single-pass pairwise comparison**: Position bias corrupts results when positions are not swapped. Always evaluate twice with swapped positions and check consistency.
+
+3. **Overloaded criteria**: Criteria that measure multiple things at once produce unreliable scores. Enforce one criterion = one measurable aspect.
+
+4. **Missing edge case guidance**: Evaluators handle ambiguous cases inconsistently without explicit instructions. Include edge cases in rubrics with clear resolution rules.
+
+5. **Ignoring confidence calibration**: High-confidence wrong judgments are worse than low-confidence ones. Calibrate confidence to position consistency and evidence strength.
+
+6. **Rubric drift**: Rubrics become miscalibrated as quality standards evolve or model capabilities improve. Schedule periodic rubric reviews and re-anchor score levels against fresh human-annotated examples.
+
+7. **Evaluation prompt sensitivity**: Minor wording changes in evaluation prompts (e.g., reordering instructions, changing phrasing) can cause 10-20% score swings. Version-control evaluation prompts and run regression tests before deploying prompt changes.
+
+8. **Uncontrolled length bias**: Longer responses systematically score higher even when conciseness is preferred. Add explicit length-neutrality instructions to evaluation prompts and validate with length-controlled test pairs.
+
+## Integration
+
+This skill integrates with:
+
+- **context-fundamentals** - Evaluation prompts require effective context structure
+- **tool-design** - Evaluation tools need proper schemas and error handling
+- **context-optimization** - Evaluation prompts can be optimized for token efficiency
+- **evaluation** (foundational) - This skill extends the foundational evaluation concepts
+
+## References
+
+Internal reference:
+- [LLM-as-Judge Implementation Patterns](./references/implementation-patterns.md) - Read when: building an evaluation pipeline from scratch or integrating LLM judges into CI/CD
+- [Bias Mitigation Techniques](./references/bias-mitigation.md) - Read when: evaluation results show inconsistent or suspicious scoring patterns
+- [Metric Selection Guide](./references/metrics-guide.md) - Read when: choosing statistical metrics to validate evaluation reliability
+- [Evaluation Pipeline Diagram](./references/evaluation-pipeline.md) - Read when: designing the architecture of a multi-stage evaluation system
+
+External research:
+- [Eugene Yan: Evaluating the Effectiveness of LLM-Evaluators](https://eugeneyan.com/writing/llm-evaluators/) - Read when: surveying the state of the art in LLM evaluation
+- [Judging LLM-as-a-Judge (Zheng et al., 2023)](https://arxiv.org/abs/2306.05685) - Read when: understanding position bias and MT-Bench methodology
+- [G-Eval: NLG Evaluation using GPT-4 (Liu et al., 2023)](https://arxiv.org/abs/2303.16634) - Read when: implementing chain-of-thought evaluation scoring
+- [Large Language Models are not Fair Evaluators (Wang et al., 2023)](https://arxiv.org/abs/2305.17926) - Read when: diagnosing systematic bias in evaluation outputs
+
+Related skills in this collection:
+- evaluation - Foundational evaluation concepts
+- context-fundamentals - Context structure for evaluation prompts
+- tool-design - Building evaluation tools
+
+---
+
+## Skill Metadata
+
+**Created**: 2025-12-24
+**Last Updated**: 2026-03-17
+**Author**: Agent Skills for Context Engineering Contributors
+**Version**: 2.0.0