Productivity & Automation for Claude Code

Walk through the NASA Phase A concept development lifecycle: ideation, problem definition, black-box architecture, drill-down with gap analysis, and document generation. 7 agents, 6 scripts (source/assumption tracking, crawl4ai web research), 9 commands, hooks for auto-state updates, and tiered research tool detection.

Transform documentation using the Diátaxis framework

ElevenLabs Claude Code plugins enabling voice-based interactions and audio processing for AI workflows.

Convert text content into natural-sounding audio using TTS technology for accessibility and audio content creation.

Create Fishbone (Ishikawa/Cause-and-Effect) diagrams for structured root cause brainstorming with 6Ms, 8Ps, 4Ss, or custom categories. Generates SVG diagrams and HTML reports.

Conduct rigorous 5 Whys root cause analysis with guided questioning, quality scoring, and professional report generation. Includes validation tests and countermeasure development.

A portable GTD skill for Claude Code: capture / clarify / organize / engage / review over plain-Markdown lists in memory/gtd/. The bundled skill auto-activates; /gtd and /gtd-* commands are included. Calendar writes are confirmation-gated and fail-closed.

English skills: evidence-disciplined testing framework, Playwright test review, test cases, Jira bug reports

Русская версия скиллов: дотошное тестирование с доказательной дисциплиной

Conduct Pareto Analysis (80/20 Rule) to identify vital few causes driving majority of problems. Generates Pareto charts and prioritization reports.

4 Perforce version control skills covering basic operations, changelist management, conflict resolution, and shelving workflows

Structural codebase indexer (MCP): search_symbols, get_file_summary, find_usages, get_dependencies + passive session memory. Cuts token usage on medium-to-large codebases (break-even ~40+ files). Self-configuring, no per-project setup.

Automatically generate Claude plugins from user prompts. Supports plugin creation, documentation, and testing.

Guide RCCA/8D problem definition using 5W2H and IS/IS NOT analysis. Transforms failure data into precise, measurable problem statements without embedded cause or solution.

Project-scoped knowledge base for Claude Code with progressive disclosure (INDEX.md dispatcher, sed-extracted summaries) and contrarian-pass investigation via background Opus subagents. Conflict-handling history prevents re-trying refuted approaches across sessions.

Persistent session memory with searchable storage and checkpoints

Systematic analysis and refinement of specifications with SEAMS framework, sequential clarification questioning, and 9-phase workflow

Specification and task management with PLANS taxonomy, ADR-style decisions, SMART acceptance criteria, SEAMS clarification, anti-pattern detection (50 patterns), 4-level verification (stub detection + wiring checks), execution orchestration (deviation rules, checkpoint taxonomy, auth gates, session continuity), tech-specific designer agents, git checkpoints, and session-memory hooks. Outputs to speckit/ directory.

Handle streaming output patterns

Accelerated speech-to-text transcription using optimized Whisper model for faster audio processing and transcription.

Windows toast notifications for Claude Code events using BurntToast

Windows filesystem navigation, PowerShell commands, and path handling utilities to prevent shell errors in Claude Code on Windows

Every Claude-compatible skill — all 47 skills plus the internet-researcher agents. Heaviest context cost; prefer a themed bundle or single skill.

Skills plugin for Claude Code: analysis, TDD, debugging, and structured workflows

Auto-kills stuck Claude Code processes when CPU stays above 70% after stopping. Fixes the React/Ink render loop bug.

Skills that compound with your codebase — generates a personalized .claude/ setup from real code patterns and keeps skills in sync as your codebase evolves.

Dream-briefing for AI coding agents: a cognitive checkpoint at session end, a 'while you were away' briefing at session start.

Generate docxtemplater-compatible DOCX templates from example files

Publish single-page HTML to the public web instantly via ht-ml.app — create, update, assets, password protection, and 20 ready-made page templates.

Persistent AI project memory — restore session context, recall & save knowledge, setup, and an MCP smoke test

Upload a CSV, ask a question, and a team of specialist agents builds a custom analysis you own — regression, clustering, forecasting, A/B tests, churn prediction — delivered as an interactive HTML report with charts and AI insights.

Access large Markdown files using declarative selectors via the mdsel CLI

Merit Aktiva accounting + Merit Palk payroll for Claude Code — full API coverage via the elnora-merit CLI, plus how-to skills for the correct procedure (accounting: sales/purchase invoices, payments/bank, VAT/KMD, reports, reverse charge; payroll: employees, salaries/absences, reports, settings), agents, and slash commands.

Skills for using Claude Code with mossnotes.app notes, packaged for reference use and customization.

Block destructive shell commands before execution. Prevents rm -rf, git push --force, AWS deletions, and more.

Email automation skill for AI agents enabling programmatic email sending and management for notification and communication workflows.

Expert advertising agent for Meta, Google, X.com, and YouTube paid campaigns with campaign planning, creative briefs, and optimization workflows

Multi-model orchestration and advisor routing: tri-model review and canonical advisor routing.

22 validated skills and 4 specialized agents for systematic AI methodology engineering via OCA cycles and dual-layer value functions