AfterRealm

Analyze your work patterns over time — when you typically work, peak vs off-peak usage, night owl detection. Use when asking about work habits, schedule patterns, optimal work times, "am I a night owl", "when do I actually work", weekday vs weekend ratios, or questions about self-observation of work rhythm.

Estimate the token cost of reading a file or directory before doing it. Use when asking "how many tokens would this cost", "how big is this file in tokens", "is this file too big to read", before reading large files, or when weighing whether to read something with limited context budget remaining.

Get a morning briefing with peak hour status, schedule outlook, and work recommendations for the day. Use at the start of a new day, when asking for a daily summary, "what should I work on today", "plan my day", "morning check-in", or when the user wants a quick orientation before settling into work.

Start a focus timer for deep work sessions. Tracks elapsed time and optionally reminds about breaks. Use when the user wants to focus, start a timer, or do a pomodoro session.

Check real rate limit usage from the Anthropic API — session (5-hour), weekly, and Opus utilization. Use when asking about rate limits, pacing, token usage, "how much runway do I have", "should I keep working", "am I burning too fast", "will I hit my limit", or wanting a forecast of remaining subscription budget.

Check if you're in Anthropic's peak throttling window. Shows status for any timezone. Use when asking about peak hours, rate limits, or best time to work.

Check your current session's health — real context usage from JSONL token data, compaction proximity, session weight, and rate limit status. Use when asking about session size, compaction, context window, rate limits, "how big is my session", "how close to compaction", or "should I checkpoint".

Check how long the current session has been running. Use when asking about session length, duration, "how long have I been at this", "how long have I been working", whether it's time to checkpoint, or any time-since-start question.

Deep audit of exported Blueprint data — full pattern scan, graph health checks, and cross-function analysis. Use after blueprint-export has generated T3D or snapshot files.

Analyze pasted Blueprint data for bugs and anti-patterns. Use when the user pastes Blueprint nodes or T3D text and wants a review.

Export Blueprints from a running UE5 Editor for analysis. Use when the user wants to export, scan, or snapshot their Blueprints.

Generate step-by-step fix instructions for Blueprint bugs found during audit. Use when the user wants to fix specific issues.

Set up the UE5 Blueprint plugin — enables Python remote execution in the Unreal Editor so Claude can export and analyze Blueprints.

Use this skill whenever a user pastes, attaches, or points at code and asks for opinionated critique — especially brutal, savage, funny, harsh, honest, or merciless feedback. Strong triggers: "review this," "what's wrong with," "tell me everything wrong," "brutal/savage feedback," "roast," "judge," "audit," "grade," "rip apart," "don't hold back," "is this bad," "embarrassing," profanity about their own code ("garbage/dogshit/trash"), diff reviews before committing, "should I push this," comparing two snippets, whole-project grading, or meta-reviews of SKILL.md files. User wants findings with severity ratings, concrete fixes, and personality — not a dry lint report. Trigger even when "roast" or "blunt cake" never appear; the signal is subjective code critique with attitude. Do NOT trigger for: writing new code, adding features, translating languages, running formatters/linters, writing tests, explaining how code works, or library recommendations.

Use when the user wants to start a voice conversation with the Claude Desktop App, enable a hold-to-talk hotkey, use voice input in French / Spanish / German / Japanese / any non-English language, dictate prompts by speaking instead of typing, or invokes "/voice", "voice mode", "speak to Claude", "voice chat", "hands-free", "talk to Claude", or similar. Walks the user through choosing language and Whisper model size, then launches a standalone Python voice loop that records mic, runs local Whisper STT, and pastes the transcript into whatever window is focused (typically Claude Desktop). Fills the gap where official voice mode is English-only.

Use this skill when the user wants to manage, inspect, promote, merge, or analyze usage of their Claude Code agents. IMPORTANT: Contains scanner scripts that search all .claude/agents/ directories and session history. Triggers: "list agents", "show agents", "promote to global", "agent manager", "level up", "manage agents", "inspect agent", "merge agents", "combine agents", "agent stats", "agent usage", "which agents are unused", "most used agents", or follow-ups like "move that one to global" when agents are discussed. Do NOT trigger for: running agents (/agents), debugging agent errors, or general questions. Note: Claude handles agent CREATION natively — no skill needed. If user says "create an agent", respond directly without invoking this skill.

Use this skill whenever a user shares web code (HTML, JSX, TSX, Vue, Svelte) and wants to know if it's accessible — keyboard usable, screen reader compatible, WCAG compliant, or ready to ship from an a11y standpoint. The trigger is code + an accessibility question: "does this pass WCAG", "check this for a11y", "is this keyboard accessible", "audit before I ship", "compliance report for a client". Does NOT apply when the user wants to write new accessible components, understand WCAG concepts abstractly, find accessibility libraries, or write accessibility tests.

Image editor sidecar — when the user wants to modify, transform, filter, animate, or compose images, this skill exposes a full image-manipulation toolkit Claude can call directly. Results render inline in the chat by default; an optional live web canvas is available for visual tasks like interactive crop or text placement. Use this whenever the user says "edit this image," "apply [a filter / sepia / a polaroid / a watermark / etc.]," "resize / crop / rotate," "make it look [vintage / cartoon / etc.]," "animate this," or shares an image and wants any kind of manipulation done. Also use it for image creation primitives (gradients, color palettes, QR codes) and image-to-audio sonification. Don't reach for this skill for image generation from prompts (that's a different model); reach for it whenever there's an existing image and the user wants something done TO it.