行動開發

Apply safe refactoring patterns to improve code structure without changing behavior. Use when cleaning up code, reducing technical debt, or improving maintainability.

Best practices for structured logging, correlation IDs, performance metrics, and debugging in Bun applications using @sidequest/core/logging and LogTape. Use when implementing logging, setting up observability, debugging production issues, tracking performance metrics, adding correlation IDs, configuring subsystem loggers, or working with JSONL log analysis. Covers plugin logger factory, hierarchical categories, log levels, metrics collection, and operational debugging workflows.

Complete asset management feature for Polkadot dApps using the Assets pallet. Use when user needs fungible token/asset functionality including creating custom tokens, minting tokens to accounts, transferring tokens between accounts, destroying tokens, viewing portfolios, or managing token metadata. Generates production-ready code (~2,200 lines across 15 files) with full lifecycle support (create→mint→transfer→destroy), real-time fee estimation, transaction tracking, and user-friendly error messages. Works with template infrastructure (WalletContext, ConnectionContext, TransactionContext, balance utilities, shared components). Load when user mentions assets, tokens, fungible tokens, token creation, minting, portfolio, or asset pallet.

Disrupt consensus or stagnation by taking unexpected positions that create productive tension. Use when: (1) asked to challenge premature consensus or stagnation, (2) agreement is present without underlying tensions being explored, (3) the same failed solutions keep reappearing, (4) substantive challenges are absent from the discussion.

Autonomous agent that uses Antigravity's browser integration to explore the web app, perform monkey testing, and verify visual regressions.

World of Darkness domain terminology and game concepts for the Tellurium Games application. Use when encountering WoD-specific terms, understanding gameline abbreviations, interpreting character stats, or working with game mechanics. Triggers on unfamiliar terms like ST, Disciplines, Spheres, Arete, Gnosis, or gameline-specific concepts.

Understand the structure and relationships of merge conflicts to resolve them systematically. Use when: (1) asked to resolve merge conflicts, (2) git merge or rebase halted with conflicts, (3) conflict markers appear in multiple files, (4) same logical change conflicts across several locations, (5) resolving conflicts without understanding what both sides intended.

Use when orchestrator generates new concepts or user says "vet concepts", "check conflicts", "find duplicates", "scan for overlaps" - scans story-tree database to detect duplicate, overlapping, or competing concepts. Returns conflict pairs with types and confidence scores for human review.

Master threat modeling with STRIDE, attack trees, risk assessment, and identifying security threats in systems and applications.

Applies JAX patterns for scientific Python development. Use when working with JAX, distrax, numpyro, blackjax, or scientific computing. Covers vmap, JIT, RNG handling.

Automated workflow to scaffold a new Home Manager application in nixos-hwc following Charter v6.0 patterns with full structure and validation

Add AI features to Glide apps using AI columns like Generate Text, Image to Text, Audio to Text. Use when adding AI-powered functionality, text generation, OCR, transcription, or auto-categorization.

Clones HEC-HMS components (basins, met models, control specs, runs) using the CLB Engineering LLM Forward approach. Creates non-destructive, traceable, GUI-verifiable copies for QAQC comparison, scenario analysis, and parameter sensitivity testing. Use when creating alternative scenarios, setting up QAQC workflows, comparing baseline vs updated models, or preserving original while testing modifications. All clones appear in HEC-HMS GUI with separate DSS outputs for side-by-side comparison. Trigger keywords: clone, duplicate, copy, QAQC, scenario, alternative, baseline, comparison, side-by-side, non-destructive, traceable.

View situations from multiple vantage points to gain comprehensive understanding, useful for breaking out of fixed viewpoints, understanding stakeholder needs, or seeing problems differently. Triggered when: (1) asked to examine a situation through contrasting viewpoints or consider what different roles perceive, (2) When stuck on a problem with only one approach emerging, when making design decisions affecting multiple stakeholders, when resolving disagreements between stakeholders, when designing experiences bridging technical and user needs, during analysis paralysis with competing priorities, when evaluating stakeholder objections or concerns, when searching for solutions satisfying competing needs, when stakeholder feedback conflicts with technical constraints, before finalizing approaches impacting different user groups, or when tradeoffs between perspectives feel irreconcilable

Check a PR for unresolved automated review feedback (Copilot, CodeRabbit) and invoke the appropriate resolver skills. Use when the user says "resolve PR feedback", "check PR comments", "address review comments", or wants to handle all automated review feedback on a PR.

Apply context-driven testing principles where practices are chosen based on project context, not universal 'best practices'. Use when making testing decisions, questioning dogma, or adapting approaches to specific project needs.

Generate structured comparisons and decision matrices across analyzed frameworks. Use when (1) comparing multiple frameworks or approaches side-by-side, (2) making architectural decisions between alternatives, (3) creating best-of-breed selection documentation, (4) synthesizing findings from multiple analysis skills into actionable decisions, or (5) producing recommendation reports for technical stakeholders.

Comprehensive mobile testing for iOS and Android platforms including gestures, sensors, permissions, device fragmentation, and performance. Use when testing native apps, hybrid apps, or mobile web, ensuring quality across 1000+ device variants.

Firebase Authentication specialist covering Google ecosystem, social auth, phone auth, and mobile-first patterns. Use when building Firebase-backed or Google ecosystem apps.

Recognize when thinking is going in circles, useful when stuck, repeating yourself, or not making progress despite continued effort. Use when: (1) explicit request to detect reasoning loops or check for circular thinking, (2) same points or decision points recur in multiple responses without new conclusions, (3) information gathering or analysis steps haven't changed the approach to the problem, (4) revision cycles continue with diminishing returns while central questions remain unresolved.