Skill Creator

krzemienski

56 published skills · 64 GitHub stars across the catalog. View on GitHub ↗

anthropic-streaming-patterns

krzemienski's avatarfrom krzemienski★ 2

Use when integrating Claude API with streaming responses, implementing tool execution in streams, tracking API costs, or encountering streaming errors - provides Anthropic SDK 0.30.1+ patterns with mandatory cost monitoring

claude-mobile-cost-tracking

krzemienski's avatarfrom krzemienski★ 2

Use when implementing Claude API cost tracking, monitoring token usage, displaying cost metrics in Settings, or user asks about costs - calculates exact costs using $0.003/1k input and $0.015/1k output pricing with per-session aggregation

claude-mobile-ios-testing

krzemienski's avatarfrom krzemienski★ 2

Use when testing iOS apps on simulator, capturing screenshots for validation gates, automating UI testing with expo-mcp and xc-mcp, or verifying visual correctness - combines expo-mcp autonomous testing (React Native level) with xc-mcp simulator management (iOS level)

claude-mobile-metro-manager

krzemienski's avatarfrom krzemienski★ 2

Use when starting Metro bundler for Expo development, debugging Metro errors, or enabling expo-mcp local capabilities - manages Metro lifecycle with EXPO_UNSTABLE_MCP_SERVER=1 flag for autonomous testing

claude-mobile-validation-gate

krzemienski's avatarfrom krzemienski★ 2

Use when executing validation gates 3A, 4A, or 6A-E, verifying phase completion with expo-mcp visual testing, or encountering test failures - automates gate execution with expo-mcp autonomous verification and HARD STOP enforcement

idb-claude-mobile-testing

krzemienski's avatarfrom krzemienski★ 2

Use when testing Claude Code Mobile app on iOS simulator with IDB CLI, when xc-mcp tools unavailable, or when needing testID-based UI automation - provides systematic workflow for finding elements by testID, tapping, typing, and verifying interactions using IDB accessibility tree

react-native-expo-development

krzemienski's avatarfrom krzemienski★ 2

Use when developing React Native components, installing packages via expo-mcp, implementing screens, or following RN best practices - integrates expo-mcp workflows (add_library, search_documentation) with production patterns from Gifted Chat and Stream

websocket-integration-testing

krzemienski's avatarfrom krzemienski★ 2

Use when testing WebSocket servers, validating message protocols, executing Gate 3A, or tempted to use mocks - enforces functional testing with wscat and real filesystem operations, NO MOCKS allowed

testing-claude-plugins-with-python-sdk

krzemienski's avatarfrom krzemienski★ 1

Use when testing Claude Code plugins programmatically, building SDK applications, encountering plugin loading failures (plugins array empty), getting AttributeError on message.type, or needing verified Claude Agents SDK Python patterns - provides complete reference for correct message handling (isinstance not .type), plugin loading (setting_sources required), content block iteration, and all working patterns from official documentation

architecture-evolution-tracking

krzemienski's avatarfrom krzemienski★ 1

Track architectural decisions and detect drift from ADRs (Architecture Decision Records). Calculate alignment score (0.00-1.00) showing code-to-design conformance. Auto-detect architectural violations and suggest refactoring. Integrate with Serena for architectural health monitoring. Use when: maintaining architectural integrity, reviewing large changes, documenting decisions, detecting drift, enforcing standards.

brainstorming

krzemienski's avatarfrom krzemienski★ 1

Use when creating or developing ideas before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning with Shannon quantitative validation, alternative exploration, and incremental validation. Don't use during clear mechanical processes

condition-based-waiting

krzemienski's avatarfrom krzemienski★ 1

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests with quantitative reliability tracking

confidence-check

krzemienski's avatarfrom krzemienski★ 1

5-check quantitative validation ensuring 90% confidence before implementation. Preventswrong-direction work through systematic verification: duplicate check (25%), architecturecompliance (25%), official docs (20%), working OSS (15%), root cause (15%). Thresholds:≥90% proceed, ≥70% clarify, <70% STOP. Proven 25-250x token ROI from SuperClaude.

context-preservation

krzemienski's avatarfrom krzemienski★ 1

PROTOCOL skill for checkpoint-based context preservation using Serena MCP.Automatically creates checkpoints at wave boundaries and before PreCompact.Enables zero-context-loss multi-session work with structured metadata collection.Use this skill for ALL Shannon projects - checkpoints are mandatory, not optional.

context-restoration

krzemienski's avatarfrom krzemienski★ 1

Restore previous session state from Serena MCP checkpoints. Retrieves checkpoint by ID orauto-selects most recent, deserializes context, restores command/skill/phase/wave state.Use when: resuming after context loss, continuing previous session, recovering from interruption.

defense-in-depth

krzemienski's avatarfrom krzemienski★ 1

Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through using Shannon validation gates to make bugs structurally impossible with quantitative coverage tracking

dispatching-parallel-agents

krzemienski's avatarfrom krzemienski★ 1

Use for 3+ independent failures - dispatches parallel subagents with Shannon wave coordination, success scoring (0.00-1.00) per domain, and MCP result aggregation

exec

krzemienski's avatarfrom krzemienski★ 1

Autonomous task execution with library discovery, 3-tier validation, and atomic git commits.Integrates with Shannon CLI Python modules for platform-specific execution. Invokes /shannon:wavefor code generation, validates outputs functionally, commits only validated changes. Use when: userrequests autonomous execution, wants library-first development, needs validated commits.

executing-plans

krzemienski's avatarfrom krzemienski★ 1

Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically with Shannon quantitative analysis, executes tasks in complexity-based batches, runs validation gates, reports for review between batches

finishing-a-development-branch

krzemienski's avatarfrom krzemienski★ 1

Use at development completion - guides branch integration with Shannon 3-tier validation (0.00-1.00 readiness score), MCP merge pattern analysis, and Serena risk assessment

forced-reading-auto-activation

krzemienski's avatarfrom krzemienski★ 1

Use automatically when prompts exceed 3000 characters, files exceed 500 lines, or large files are referenced - enforces complete line-by-line reading protocol with quantitative comprehension verification before processing, preventing partial comprehension and ensuring thorough understanding

forced-reading-protocol

krzemienski's avatarfrom krzemienski★ 1

Use when analyzing critical documents, specifications, or large files (>3000 lines), before any synthesis or conclusions - enforces complete line-by-line reading with quantitative verification to prevent skimming that leads to incomplete understanding

functional-testing

krzemienski's avatarfrom krzemienski★ 1

Enforce NO MOCKS testing philosophy with real systems. Iron Law: no mock objects, no unit tests,no stubs. Test with real browsers (Puppeteer MCP), real databases, real APIs. Enforced viapost_tool_use.py hook. Use when: writing any tests, tempted to use mocks, need testing guidance.

goal-alignment

krzemienski's avatarfrom krzemienski★ 1

QUANTITATIVE skill for validating wave deliverables against goal milestones using0-100% alignment scoring. Prevents scope drift, detects misalignment, enforcesgoal-wave consistency. Requires goal-management for milestone data. Essential formulti-wave projects to maintain North Star alignment throughout execution.