productivity▌

Keep the manifest as the single source of truth for build and deploy behavior.

Search conversation history to avoid reinventing solutions and inform architectural decisions. \n \n Dispatch the search-conversations subagent to query past conversations; the agent synthesizes results into actionable insights with sources \n Use after understanding the task when facing \"how should I...\" questions, architectural decisions, or unfamiliar workflows \n Activate when stuck on complex problems, following past patterns, or when user references previous work or decisions \n Avoid se

Natural speech synthesis from text across 70+ languages with multiple quality and latency models. \n \n Six models available ranging from highest-quality eleven_v3 to ultra-low-latency eleven_flash_v2_5 (~75ms), with language and speed tradeoffs documented \n Supports 13+ output formats including MP3, PCM, WAV, Opus, and telephony codecs (μ-law, A-law) for web, streaming, and real-time applications \n Fine-tune voice characteristics via stability, similarity boost, style, speaker boost, and spee

Comprehensive verification system running build, type, lint, test, and security checks across Claude Code sessions. \n \n Executes six sequential verification phases: build compilation, type checking, linting, test suite with coverage reporting, security scanning for secrets and debug statements, and git diff review \n Supports both JavaScript/TypeScript (npm/pnpm, tsc, ESLint) and Python (pyright, ruff) projects with language-specific commands \n Produces a structured verification report indica

Orchestrate subagents, plan multi-step tasks, and require human approval for sensitive operations. \n \n Delegate work to specialized subagents via the task tool; custom subagents support isolated tool sets and system prompts, while the default \"general-purpose\" subagent inherits main agent configuration \n Plan and track complex workflows with write_todos , organizing tasks across pending, in-progress, and completed states; requires a thread_id for persistence across invocations \n Implement

Sync App Store Connect metadata and localizations with validation and legacy format migration support. \n \n Manage two localization types: version-specific fields (description, keywords, what's new, support/marketing URLs) and app-level fields (name, subtitle, privacy policy) \n Download, validate, and upload .strings files in bulk for multi-language workflows with built-in character limit enforcement \n Export current metadata state, validate against App Store requirements, and import updates

Remove background noise and isolate vocals from audio files via inference.sh CLI. \n \n Supports five audio formats (WAV, MP3, FLAC, OGG, AAC) up to 500MB and 1 hour duration \n Removes ambient noise, background music, reverb, wind, traffic, electrical hum, and other non-voice sounds \n Integrates into multi-step workflows for transcription, voice transformation, and video production \n Requires inference.sh CLI ( infsh ) installation and login to run \n

Multi-tenant B2B SaaS with organization switching, role-based access control, and enterprise SSO. \n \n Supports dynamic org-based routing via URL slugs, role-based access checks ( org:admin , org:member ), and custom role creation through the dashboard \n Includes OrganizationSwitcher component for user-facing org selection and <Show> conditional rendering for role-gated UI \n Provides server-side organization context via auth() helper with membership verification and permission checks \n

Find similar vulnerabilities and bugs across codebases using pattern-based analysis. \n \n Guides a five-step process: understand root cause, create exact match, identify abstraction points, iteratively generalize patterns, and analyze results with confidence/exploitability triage \n Supports ripgrep for quick searches, Semgrep for simple pattern matching, and CodeQL for cross-function data flow analysis \n Includes ready-to-use CodeQL and Semgrep templates for Python, JavaScript, Java, Go, and

Persistent file-based planning system for organizing complex multi-step tasks and maintaining context across sessions. \n \n Creates three markdown files (task_plan.md, findings.md, progress.md) in your project directory to serve as persistent working memory \n Includes session recovery via script to sync context after /clear commands and resume interrupted work \n Enforces structured workflows: plan first, update after each phase, log all errors, and never repeat failed actions \n Provides temp