All Skills

This skill should be used when the user asks to "run a security audit", "check firewall status", "enable the firewall", "review privacy permissions", "check what apps have camera access", "list login items", "harden my Mac", "check security settings", "revoke app permissions", "auto-fix security issues", "export firewall rules", "import firewall rules", "export privacy permissions", "monitor security score", "security events", "login attempts", "permission changes", "firewall blocks", "app install history", "TCC events", or mentions macdog, macOS security, privacy audit, TCC permissions, system hardening, firewall export, continuous security monitoring, or security event log.

Use this for setting up monitoring, logging, distributed tracing, and alerting for applications and infrastructure.

Step-by-step instructions for designing table schemas and setting up TimescaleDB with hypertables, indexes, compression, retention policies, and continuous aggregates. Instructions for selecting: partition columns, segment_by columns, order_by columns, chunk time interval, real-time aggregation.

Orchestrate Ralph automation loops for spec-driven development. Use when starting, stopping, monitoring, or checking status of Ralph loops. Triggers on Ralph start, Ralph stop, Ralph status, spec automation, task loop, run tasks, check progress, kill Ralph, resume Ralph, or tmux session management.

Execute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools from AGENTS.md, and reports progress to orchestrator.

Generate comprehensive plans for new features by exploring the codebase, synthesizing approaches, validating with spikes, and decomposing into beads. Use when asked to plan a feature, create a roadmap, or design an implementation approach.

Plan and coordinate multi-agent bead execution. Use when starting a new epic, assigning tracks to agents, or monitoring parallel work progress.

This skill should be used when the user mentions "Neo4j", "Cypher", "graph database", "graph query", discusses graph relationships, traversals, path finding, or needs help with Cypher syntax. Addresses Neo4j fundamentals, query patterns, performance optimization, and integration with relational databases.

This skill should be used when the user asks to "identify trends", "analyze market trends", "trend forecasting", "macro trends", "micro trends", "emerging patterns", "future projections", "industry trends", or needs guidance on trend identification, pattern recognition, or market forecasting methodologies.

This skill should be used when the user mentions "dark patterns", "accessibility", "a11y", "privacy", "tracking", "analytics", "notifications", "user data", "GDPR", "consent", "manipulation", "sustainability", "performance budget", or when building user-facing features that collect data, send notifications, display urgency, or gate access. Addresses ethical constraints in software design — manipulation, accessibility, privacy, and sustainability.

Orchestrates documentation updates after version bumps, feature additions, or periodic maintenance. Analyses git history since the last release, identifies which docs are affected, and delegates to existing skills (changelog, feature-benefits, docs-verify, ai-context, llms-txt, user-guides) for selective refresh. Use when releasing a new version or refreshing stale docs.

Use this skill when the user asks to watch, view, or analyze a video file (.mov, .mp4, .webm, .avi). Extracts frames as images since Claude cannot view videos directly.

This skill should be used when the user mentions "git", "branch", "commit", "merge", "pull request", "PR", "version control", discusses branching strategy, commit conventions, collaboration workflows, or needs help with git operations. Addresses git best practices, branch management, commit messages, and LazyGit integration.

This skill should be used when the user mentions "layout issues", "styling problems", "CSS fixes", "style consistency", "unify styles", "visual bugs", discusses frontend styling, works on UI components, or asks about component styling approaches. Applies to Svelte/SvelteKit projects primarily, with general frontend principles.

Use this skill when the user asks to orchestrate a team, use multiple agents, or parallelize work across Claude Code sessions. Decomposes tasks, spawns teammates, and coordinates execution.

# Validation Skill Comprehensive app validation with REAL verification - discovers all interactive elements, tests them with actual verification, and generates HTML reports. ## Invocation ``` /validate [app-url] ``` If no URL provided, looks for running dev server or asks user. --- ## Core Pri

Compare model candidates using weighted metrics and deterministic ranking outputs. Use for benchmark leaderboards and model promotion decisions.

Audits architectural patterns against best practices (MCP Ref, Context7, WebSearch). Maintains patterns catalog, calculates 4 scores. Output: docs/project/patterns_catalog.md. Use when user asks to: (1) Check architecture health, (2) Audit patterns before refactoring, (3) Find undocumented patterns in codebase.

This skill should be used when conducting a comprehensive agent-native architecture review with scored principles. It launches 8 parallel sub-agents to audit action parity, tools as primitives, context injection, shared workspace, CRUD completeness, UI integration, capability discovery, and prompt-native features. Triggers on \"agent-native audit\", \"architecture review\", \"agent parity check\", \"score agent-native\".

This skill should be used when the user mentions "debugging", "troubleshooting", "bug", "error", "issue", "not working", "broken", discusses investigating problems, asks about debugging techniques, DevTools usage, or mentions they need to fix something. Addresses methodical problem-solving approach for software issues.

Use when calculating daily morphine milligram equivalents (MME) to assess opioid dose risk, document totals, or support taper planning. Based on CDC conversion factors and safety cautions.

Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.

Maps Claude Code changes to Shipkit gaps. Reads scout report and audits all skills, agents, hooks, and settings against current CC capabilities. Identifies deprecated patterns, missing features, and update opportunities. Use after running shipkit-scout.

Validates Shipkit framework integrity before release. Checks for broken references, manifest/disk sync, installer validity, hook references, cross-skill dependencies, documentation accuracy, and Claude Code changelog compatibility. Auto-fetches latest changelog and flags deprecated patterns, unknown hook events, and feature adoption gaps. Uses caching to skip unchanged files. Use when preparing releases or after refactoring.