kochetkov-ma/claude-brewcode Skills

Interactive agent creation and improvement orchestrator. Create or improve Claude Code agents.

Universal documentation sync for skills, agents, markdown. Modes - status, init, global, project, file, folder.

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

Installs brewcode prerequisites (brew, coreutils, jq, grepai).

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.

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

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.

Generates documentation about Claude Code installations - internal overview of local setup, external docs on hooks/context/agents, or web research from forums/GitHub/marketplaces

Creates execution plan (PLAN.md) from SPEC or Plan Mode file.

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.

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.

Analyzes project structure and tech stack to generate adapted PLAN.md.template in .claude/tasks/templates/.

Skill management - list, improve, create skills with activation optimization.

Creates task specification through research and user interaction.

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.

Executes task with infinite context and automatic handoff.

Removes brewcode project files (templates, configs, logs).

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.

Optimizes text and docs for LLM token efficiency. Use when - optimizing prompts, reducing tokens, compressing text, condensing verbose content. Trigger keywords - optimize, reduce tokens, compress, condense, slim, tighten, too verbose, shrink.

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.