daymade/claude-code-skills
Overview
This skill analyzes macOS disk usage and produces safe, actionable cleanup recommendations to reclaim space. It follows a safety-first philosophy: thorough analysis, clear impact descriptions, and explicit user confirmation before any deletions. The skill prioritizes conserving useful caches and avoiding destructive shortcuts.
How this skill works
The skill runs a staged workflow: quick diagnosis, deep analysis with a TTY-aware tool (Mole), category-by-category inspection, and conservative cleanup suggestions. It reports progress during long scans, explains consequences for each candidate, and outputs precise commands for the user to run manually after confirmation. Dangerous operations are flagged and require stepwise, per-item approval.
When to use it
- When a user reports low or shrinking disk space on macOS
- Before performing any automated cleanup on a Mac
- To identify large files, duplicate data, and leftover app remnants
- When assessing developer environment storage (Docker, Homebrew, npm, pip)
- When you need safe, explainable recommendations rather than one-click cleaning
Best practices
- Always run mo analyze in a TTY (use tmux) and be patient—home directory scans can take 5–10+ minutes
- Show what will happen if a file or folder is deleted for every recommendation
- Preserve caches that speed up downloads or builds if network or rebuild cost is high
- Never execute rm -rf or global prune commands without explicit, per-item user consent
- Provide cleanup commands for users to run themselves; do not auto-delete
Example use cases
- Diagnose a Mac with <10 GB free and identify largest reclaimable folders
- Find orphaned Application Support folders after apps were uninstalled
- List large files (>100 MB) and surface duplicates for user review
- Audit developer caches: Homebrew cache, npm/pip caches, Docker images and volumes with per-volume confirmation
- Generate step-by-step Mole tmux workflow and progress updates during long analyses
FAQ
No. It never deletes files automatically. It provides recommendations, explains impact, and prints commands for you to run after explicit confirmation.
Is it safe to remove caches suggested by the tool?
Most app caches are safe to remove, but the tool flags caches that are expensive to re-download or rebuild so you can decide. When in doubt, keep them.
How long does a full analysis take?
Home directory and deep scans typically take 5–10 minutes or longer for large data sets. The skill reports progress regularly during the scan.
24 skills
This skill analyzes macOS disk usage and provides safe, user-confirmed cleanup recommendations to reclaim space without deleting essential data.
This skill conducts multi-path parallel product analysis using Claude Code and Codex to generate actionable optimization plans and competitive benchmarks.
This skill diagnoses and fixes conflicts between Tailscale and proxy/VPN tools on macOS, improving connectivity for SSH, curl, and browsers.
This skill diagnoses Windows Remote Desktop connection issues on macOS by analyzing transport protocol, VPN interference, and Windows App logs to improve
This skill downloads YouTube videos and HLS streams, handling authentication, errors, and quality options, and saves the final file to your chosen location.
This skill helps you set up, audit, and enforce i18n in React/TS apps, ensuring locale parity, proper pluralization, and key-based translations.
This skill helps you generate professional animated CLI demos and GIFs from verbal or config inputs for tutorials and showcases.
This skill transforms raw meeting transcripts into structured, evidence-based minutes with speaker mapping, multi-turn review, and iterative human-in-the-loop
This skill safely packages codebases with repomix by detecting and removing hardcoded credentials before distribution.
This skill corrects speech-to-text errors in transcripts using dictionary rules, AI corrections, and learned patterns to build a personalized correction
This skill helps diagnose and resolve Claude Code plugin and skill activation issues, guiding you through installation, enablement, and cache problems.
This skill creates high quality PDFs from markdown with Chinese font support using WeasyPrint, ideal for formal documents and reports.
This skill optimizes CLAUDE.md using progressive disclosure to maximize information efficiency, readability, and maintainability for complex documentation.
This skill compares two videos and generates an interactive HTML report with PSNR/SSIM metrics and frame-by-frame visual comparisons.
This skill helps you locate and download AI model icons from the lobe-icons library in SVG, PNG, or WEBP formats.
This skill consolidates redundant documentation while preserving all valuable content, reducing bloat without sacrificing essential details.
This skill helps you troubleshoot Cloudflare configurations using API evidence, guiding systematic diagnosis and fixes for redirects, SSL, DNS, and related
This skill helps you locate, recover, and analyze content from Claude Code session history files across projects to track changes and retrieve deleted code.
This skill orchestrates GitHub tasks using gh CLI and APIs, from PRs and issues to workflows and API queries, boosting automation and accuracy.
This skill fact checks factual claims in documents by consulting authoritative sources and proposes corrections for user confirmation.
This skill converts documents to high-quality markdown using quick or heavy mode, merging tools for best structure and imagery.
This skill fetches Twitter/X post content via the Jina API, returning author, time, text, media, and thread data for quick insights.
This skill creates persuasive, ready-to-deliver slide decks from topics, including outlines, charts, speaker notes, and multiple export formats.
This skill helps you establish comprehensive QA testing with Google standards, OWASP security, and autonomous execution for fast, reliable software validation.
