productivity▌

Parallel multi-model consensus review with configurable perspectives, debate rounds, and deep exploration. \n \n Supports three task modes: validate (PASS/WARN/FAIL verdicts), brainstorm (explore alternatives), and research (deep analysis with trade-offs) \n Spawns 2–3 independent judges by default; scales to 6+ agents with --deep , --mixed (Claude + Codex), and --explorers sub-agents, capped at 12 total \n Debate mode ( --debate ) runs two-round adversarial review with verdict exchange and posi

Tactile feedback for web apps using the Web Vibration API across React, Vue, Svelte, and vanilla JavaScript. \n \n Four trigger categories: notifications (success, warning, error), impacts (light, medium, heavy), selection (picker/slider detents), and extra presets (soft, rigid, nudge, buzz) \n Framework-specific hooks and composables for React, Vue, Svelte; vanilla JS class; automatic SSR handling in Nuxt and SvelteKit \n Zero dependencies, silent no-op on unsupported platforms (desktop), no fe

Execute a written implementation plan with critical review and task checkpoints. \n \n Requires loading and critically reviewing the plan before execution; raises concerns with the human partner if issues are identified \n Executes tasks sequentially, marking progress and running verifications as specified in the plan \n Stops immediately on blockers (missing dependencies, test failures, unclear instructions) rather than guessing; asks for clarification \n Integrates with git-worktrees for isola

Safely package codebases with repomix by automatically detecting and removing hardcoded credentials.

This skill provides comprehensive guidance for GitHub operations using the gh CLI tool and GitHub REST/GraphQL APIs. Use this skill when performing any GitHub-related tasks including pull request management, issue tracking, repository operations, workflow automation, and API interactions.

Use openhue to control Philips Hue lights and scenes via a Hue Bridge.

Use this skill to turn a cloud server into a safely reachable web host without leaning on stale distro-specific memory or outdated Debian-10-era tutorials.

Natural conversation with AI through speech, balancing latency against control. \n \n Choose between speech-to-speech models (lowest latency, less controllable) or pipeline architectures (STT→LLM→TTS for fine-grained control) \n Core challenges: latency budgeting across all components, voice activity detection, barge-in handling, and turn-taking to avoid awkward pauses or overlaps \n Requires semantic VAD, response length constraints in prompts, and noise handling to achieve natural conversation

Real-time subscriptions, optimistic updates, intelligent caching, and cursor-based pagination for reactive Convex applications. \n \n Automatic subscriptions via useQuery with smart caching and consistent database views across components \n Optimistic updates for immediate UI feedback on mutations, with automatic rollback on errors \n Cursor-based pagination with usePaginatedQuery supporting load-more and infinite-scroll patterns \n Conditional query execution using \"skip\" to avoid hook call v

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities. \n \n Searches the skills directory using npx skills find [query] to match user requests against available skills across domains like React, testing, DevOps, design, and documentation \n Presents matching skills with installation commands and links to skills.sh for detailed documentation \n Installs selected skills globally using the install-skill.sh script, automatically linking them to