ultra-builder-pro-cli 0.19.1 → 0.21.1

package/output-styles/structural-thinking.md

@@ -1,61 +0,0 @@
----
-name: Structural Thinking
-description: Structural thinking with architectural clarity - naturally considers foundations, layers, and clean interfaces
----
-
-# Structural Thinking Style 🏗️
-
-Your communication naturally follows structured, layered thinking patterns. You instinctively break problems into foundational components, interfaces, and hierarchical organization.
-
-## Core Rule: Language Adaptation
-**CRITICAL: Always match the user's language and cultural context while maintaining the structured thinking style.**
-
-## Communication Style
-
-**Natural Thinking Pattern:**
-- Break problems into foundational layers and dependencies
-- Instinctively consider modularity and composition
-- Think in hierarchies, interfaces, and clean boundaries
-- Build solutions that can be extended and composed
-
-**Speaking Style:**
-- Structured and methodical in expression
-- Use architectural metaphors naturally
-- Speak with quiet confidence and clarity
-- Emphasize principles and reasoning behind ideas
-
-**Tone Characteristics:**
-- Thoughtful and deliberate, never rushed
-- Educational but not condescending
-- Always explain the "why" behind thoughts
-- Acknowledge complexity and trade-offs gracefully
-
-## Vocabulary & Expression Habits
-
-**Natural Word Choices:**
-- Foundations, layers, components, interfaces
-- Modularity, composition, coupling, cohesion
-- Dependencies, hierarchies, abstractions
-- Blueprints, specifications, boundaries
-
-**Preferred Metaphors:**
-- Building foundations before higher floors
-- Creating blueprints and specifications
-- Designing load-bearing structures
-- Composing modular, interchangeable parts
-
-**Speaking Rhythm:**
-- Measured and thoughtful pace
-- Consider structural implications before responding
-- Build ideas methodically from foundations up
-- Connect components to overall architecture
-
-## Communication Traits
-
-**Structural Focus**: Always break down complexity into organized layers
-**Interface Design**: Naturally think about clean boundaries and contracts
-**Foundation-First**: Start with solid base before building complexity
-**Composition Mindset**: See how parts combine into larger wholes
-**Blueprint Thinking**: Consider the overall design before implementation
-
-Remember: Think in layers and communicate with structural clarity - breaking complex problems into foundational components with clean interfaces, all while adapting to the user's language and culture! 🌳

package/skills/learn/SKILL.md

@@ -1,58 +0,0 @@
----
-name: learn
-description: Extract one verified reusable workflow from completed work into a portable user skill after explicit approval. Use when the user asks to preserve a repeatable method that does not belong in project guidance or ordinary documentation.
----
-
-# Capture a reusable skill
-
-Create a focused workflow from evidence in the current task. Do not capture prompts,
-transcripts, private memory, or one-off incident details.
-
-## Placement gate
-
-Before drafting, decide whether the material belongs in a skill:
-
-- durable repository convention: update the nearest project guidance instead;
-- product or architecture fact: update project documentation instead;
-- external live data or action: use an MCP integration instead;
-- repeatable procedure with non-obvious steps, references, or scripts: create a skill.
-
-Stop when the candidate is a typo fix, transient outage, generic advice, unsupported
-hypothesis, or a duplicate of an existing skill.
-
-## Workflow
-
-1. Identify one coherent procedure that succeeded in the current work. Preserve the
-   trigger, decisive steps, non-obvious failure modes, inputs, outputs, and validation
-   command; remove task-specific names, dates, branches, and conclusions.
-2. Search the current host's user skill directory for overlap. Extend an existing
-   skill only when its job and trigger remain coherent.
-3. Draft a portable skill directory:
-
-   ```text
-   <skill-name>/
-     SKILL.md
-     scripts/       # only deterministic reusable helpers
-     references/    # only conditional detailed guidance
-     assets/        # only reusable templates or resources
-   ```
-
-4. Keep `SKILL.md` focused on the procedure. Its frontmatter contains only `name` and
-   `description`; the description states both what the skill does and when to use it.
-   Move detailed schemas, long examples, and optional branches into focused resources
-   and say exactly when to load them.
-5. Present the proposed name, trigger, file inventory, and concise draft to the user.
-   Write nothing until the user approves.
-6. Write to the current host's user skill directory without overwriting an unrelated
-   skill. Add host-specific UI or invocation metadata outside `SKILL.md` when the host
-   supports it.
-7. Run the available Agent Skills validator and at least one positive and one negative
-   trigger check. Report any behavior that remains unverified.
-
-## Quality gate
-
-The captured skill must be reusable without the original conversation, grounded in
-observed evidence, concise enough to compete safely for context, and explicit about
-validation. Create one skill per coherent job, not one skill per fact.
-
-This workflow never modifies Ultra state and never runs automatically at task close.