kochetkov-ma

GitHub Actions deployment — workflows, releases, GHCR, CI/CD with safety gates.

SSH server management — connect, configure, deploy, administer Linux servers with safety gates.

Universal documentation sync for skills, agents, and markdown files. Pulls latest docs from official sources and updates files in place. Modes: status, init <path>, global, file, folder. Triggers: sync docs, auto-sync, update documentation, refresh skill docs, sync agent docs, documentation sync, pull latest docs.

Creates SPEC.md task specification through codebase research and user interaction. First step in brewcode pipeline before plan and start. Triggers: create SPEC.md, brewcode spec, write task specification, generate spec from requirements, task SPEC from description, feature spec document.

Creates brewcode execution PLAN.md from a SPEC file or Plan Mode file with phases, tasks, agents, and dependencies. Part of brewcode workflow (spec -> plan -> start). Triggers: create PLAN.md, brewcode plan, generate execution plan from spec, build plan from SPEC.md, task plan from requirements, brewcode:plan.

Extended documentation skill for Claude Code installations. Complements built-in /team-onboarding with multi-mode research — internal setup analysis, external architecture docs, and web research from forums/GitHub/marketplaces.

Publish content to brewpage.app — text, markdown, JSON, file, or multi-file site. Asks namespace and password, returns public URL. Triggers: publish, share link, upload to brewpage, host page, brewpage, publish site, upload site, upload directory, deploy site, сделай публичную ссылку, опубликуй.

Syncs KNOWLEDGE.jsonl or session learnings to project rules. Use when - updating rules, syncing knowledge, extracting learnings, organizing anti-patterns. Trigger keywords - rules, knowledge sync, avoid patterns, best practices, session rules, extract rules.

Reviews code for project standards compliance and finds duplicates. Use when - reviewing code quality, checking standards, finding duplicates, analyzing compliance. Trigger keywords - standards review, check standards, find duplicates, code review, compliance check, reusable code.

Optimizes Claude Code memory in 4 interactive steps - removes duplicates, migrates to rules/CLAUDE.md, compresses, validates with cleanup

Orchestrates end-to-end testing workflow — sets up specialized agents, creates BDD scenarios, writes Playwright autotests, and runs quorum reviews. Modes: setup, create, update, review, rules, status. Triggers: e2e tests, end-to-end, BDD scenarios, write autotest, playwright e2e, create scenario, review e2e, e2e setup.

Orchestrates Claude Code skill management — lists skills, improves existing skills, or creates new ones with activation optimization and triggers. Triggers: create skill, new skill, improve skill, fix skill activation, skill doesn't trigger, list skills, skill management, optimize skill.

Publish content to brewpage.app — text, markdown, JSON, or file. Asks namespace and password, returns public URL. Triggers: publish, share link, upload to brewpage, host page, brewpage.

Converts design screenshots or text descriptions to HTML/CSS using GLM vision API (Z.ai). Trial version — HTML output, CREATE mode. Full version with React, Flutter, review/fix modes: brewcode plugin. Triggers: design to code, screenshot to html, mockup to code, d2c trial, convert design.

Manages grepai semantic search (setup, status, start, stop, reindex, optimize, upgrade).

Executes a brewcode task PLAN.md with infinite context and automatic session handoff (third pipeline step after spec and plan). Triggers: start brewcode task, execute PLAN.md, run task with handoff, infinite execution, brewcode start, execute brewcode plan, run the plan.

Creates and improves Claude Code subagents interactively — scaffolds new agents from descriptions, refines existing agent definitions, tunes frontmatter, tools, model, and prompts. Triggers: create agent, new agent, claude code agent, make a subagent, improve agent, update agent, fix agent description, refactor agent, agent frontmatter, agent prompt, scaffold agent.

Creates and manages dynamic teams of domain-specific agents (5-20 agents) for a project. Analyzes codebase, proposes team, scaffolds with tracking framework. Modes: create, update, status, cleanup. Triggers: create team, agent team, domain agents, team of agents for project, update team, team status, cleanup team.

Interactive guide and tutorial for brewcode plugin suite. Teaches all features step-by-step with progress tracking. Use when - help, tutorial, guide, how to use, getting started, onboarding, learn brewcode.

Removes brewcode project files (templates, configs, logs). Optional --full mode runs `claude project purge` to wipe ALL project state after typed PURGE confirmation.

Disables or enables individual plugin skills by writing skillOverrides to ~/.claude/settings.json (survives plugin updates). Modes: off, user-invocable-only, name-only. Triggers: disable skill, enable skill, toggle skill, hide skill, skill-toggle.

Optimizes text and docs for LLM token efficiency. Use when - optimizing prompts, reducing tokens, compressing text, condensing verbose content, encoding for CLAUDE.md, compressing for context/prompt/LLM. Trigger keywords - optimize, reduce tokens, compress, condense, slim, tighten, too verbose, shrink, encode, deep compress, deep encode, super compress, maximum compress.

Toggles terse-output mode for Claude Code - injects brief directives into main conversation (SessionStart) and sub-agent prompts (PreToolUse:Task) to cut preamble and filler. Profiles: light, medium, aggressive. Scope: global or project (project overrides). Triggers: think-short, be terse, think shorter, reduce tokens mode, level 1/2/3.

Analyzes project to extract etalon classes, reference patterns, and architecture by layer. Generates convention documents in .claude/convention/ and organizes project rules into a code style guide. Triggers: extract conventions, find etalon classes, analyze project patterns, code style guide, architecture conventions, convention docs, reference implementation, coding standards.

Checks prerequisites and analyzes project structure to generate adapted templates in .claude/tasks/templates/.

Converts Markdown to professional PDF. Two engines - reportlab (lightweight) or weasyprint (full CSS). Style customization, test mode, dependency management. Triggers - pdf, md to pdf, markdown to pdf, convert pdf, generate pdf.

Disables or enables individual plugin agents by renaming <name>.md and _<name>.md in the plugin cache. Persistent state: global (default) or project. Triggers: disable agent, enable agent, toggle agent, hide agent, agent-toggle.

Checks installed Claude Code plugins, installs missing brewcode plugins, updates outdated ones, reports versions. Triggers - "update plugins", "check plugin versions", "обнови плагины", "установить бриукод", "plugin update", "marketplace update".

Generates frontend code from design screenshots, mockups, text descriptions, HTML files, or URLs using external GLM vision API. Modes: CREATE, REVIEW, FIX. Output: HTML, React, Flutter. Triggers: design to code, screenshot to code, mockup to code, d2c, generate frontend from image.

Runs evidence-based multi-agent debates with mandatory Discovery phase (codebase + web research). Three modes: Challenge picks best variant from options, Strategy produces independent proposals via deep analysis, Critic finds all weaknesses. Triggers: debate, challenge this, compare options, strategy analysis, critique, find weaknesses, second opinion, pros and cons, evaluate alternatives.

Configure Claude Code alternative API providers — DeepSeek (priority), Z.ai/GLM, Qwen, MiniMax, OpenRouter. Creates shell aliases, manages API tokens, checks status. Triggers: 'provider', 'switch provider', 'alternative api', 'configure provider', 'claudeds', 'claudeglm', 'claudeqwen', 'openrouter setup', 'deepseek'.

Scans all git-tracked files for leaked secrets and credentials. Use when - scanning for secrets, security audit, finding leaked credentials. Trigger keywords - secrets scan, find credentials, security scan, leaked keys, security audit.

Removes AI artifacts, cleans comments, simplifies documentation in code. Use when - humanizing code, removing AI comments, cleaning docs, fixing unicode, making code human-readable. Trigger keywords - humanize, human, ai artifacts, ai comments, clean comments, simplify docs, unicode fix, remove generated, make readable.

Generates AI images via OpenRouter (Gemini/GPT-5), Z.ai GLM-image, Google Imagen 4, or OpenAI DALL-E 3 with anti-AI-slop controls. Modes: generate, edit, config, update. Triggers: generate image, create image, AI image, og image, blog image, illustration.

Optimizes Claude Code memory files in 4 interactive steps: removes duplicates, migrates rules to CLAUDE.md/rules files, compresses remaining entries, validates with cleanup. Typical reduction: 30-50% on token count.

Optimizes text, prompts, and documentation for LLM token efficiency. Applies 41 research-backed rules across 6 categories: Claude behavior, token efficiency, structure, reference integrity, perception, and LLM comprehension. Use when optimizing prompts, reducing tokens, compressing verbose docs, or improving LLM instruction quality.