skills

Adversarial three-agent bug review pipeline. Runs search → adversary → judge to find high-confidence bugs with reduced false positives. Use: /find-bugs src/

Root cause analysis technique for self-improvement. Use after any failure, mistake, or suboptimal outcome to find systemic causes and actionable changes. Triggers: analyzing why something went wrong, debugging repeated failures, post-mortem analysis, retrospectives, understanding root causes, reflecting on what could be improved.

Radical Simplicity Audit. Use when the user asks for advice on simplifying an idea, product, architecture, or system. Helps distinguish essential from superfluous.

Generate images using the `imagen` CLI (Gemini and OpenAI models). Use when the user says "nano banana", "generate an image", "create an image", "make me a picture", "image gen", "draw", "illustrate", or wants to create images from text prompts.

Develop brand creative treatments from GTM data. Use when the user says 'creative direction', 'brand treatments', 'brand tone', 'creative brief', 'brand identity direction', or wants to develop visual/verbal brand direction from their GTM decomposition.

Take a messy business idea and work through to structured GTM primitives — Product, ICP segments, value prop, beachhead market, and channel strategy. Use when the user shares a product idea, says 'decompose my idea', 'help me find my ICP', 'who should I sell to', 'idea to ICP', or wants to structure their go-to-market thinking.

Analyze autonomous loop session efficiency, track improvements, and view trends. Use when the user says "check loop metrics", "how are sessions doing", "analyze iterations", "self-improvement", "loop performance", "session efficiency", or wants to add/search/fix improvement records.

Foundational patterns for building accessible autocomplete/combobox components with state management, ARIA patterns, keyboard navigation, async suggestions, and framework-agnostic implementation. Use when building autocomplete inputs, command palettes, search inputs, select replacements, or any dropdown with keyboard navigation and suggestions.

Domain-specific filter query building with AST representation, operator handling, query serialization, and field-type-specific inputs. Use when building advanced filter UIs for observability tools, data analytics, search interfaces, or any system requiring structured query construction with boolean logic, comparison operators, and URL/string serialization.

Multi-value token/chip input patterns for tag inputs, filter bars, and email "To" fields. Builds on webdev-combobox-autocomplete with token state management, key:value parsing, context-dependent suggestions, and token editing patterns. Use when building filter inputs, tag selectors, multi-select chips, or any input that creates visual tokens/pills from text.

Iterates on data-intensive UI designs to improve scannability, hierarchy, accessibility, and systematization. Use when improving an existing UI, reviewing a design for UX issues, or transforming a functional-but-flat interface into a polished product.

Generate a Phase Spec/PRD by extracting features from an annotated Vision PRD. Use when user wants to create quarterly phase documentation, extract requirements from vision, plan a development phase, or decompose features into R-nnnn requirements. Requires annotated Vision PRD with F-nnn tags and Coverage Index.

Annotate a Spec/PRD with Feature IDs and generate a Coverage Index. Use when user wants to add spec tags to a vision document, create F-nnn identifiers, set up traceability, or initialize a PRD framework for phased development.

Enrich a Phase Sepc/PRD with Quality Requirements (Q-nnn) and Acceptance Criteria (AC-nnnn). Use when user wants to add QA perspective, define test criteria, identify non-functional requirements, add verification steps, or prepare a Phase PRD for test planning.