Remove AI-generated writing patterns from text or files to make them sound natural and human-written. Use when user says "humanize this", "humanise this", "make it more readable", "no AI talk", "remove AI patterns", "make this sound human", or pastes text that sounds AI-generated. Loads full 29-pattern reference + examples on every humanize task for best output quality.
Behavioral discipline rules for writing and modifying code. Use when fixing bugs, implementing features, refactoring, adding features, or editing/modifying source code files. Do NOT use for explaining code, reviewing PRs, research, writing docs, or Confluence tasks. Rigid — follow all rules exactly.
Expert skill for writing high-quality software documentation including PRDs, Design Docs, RFCs, ADRs, User Guides, Runbooks, Changelogs, Release Notes, and Postmortems. Use when user asks to write, create, or draft any technical or product document. Triggers: "write a PRD", "create design doc", "draft RFC", "write ADR", "create runbook", "write release notes", "create changelog", "write postmortem", "write user guide", "document this feature", "create incident report". Add --human / --humanise / --humanize anywhere in the prompt to auto-humanize the final doc after writing.
Generate draw.io diagrams (.drawio files) for any visual — system design, DSA patterns, LLD class diagrams, Claude Code workflows, interview frameworks, architecture flows, and AWS cloud architectures with native AWS iconography (EC2, S3, Lambda, etc. via mxgraph.aws4). No render pipeline needed. Triggered by "generate diagram", "draw this", "diagram for", "visualise", "aws diagram", "aws architecture", "cloud architecture", "generate architectural diagram using aws", or proactively when a visual would sharpen an explanation.
Generate draw.io diagrams (.drawio files) for any visual — system design, DSA patterns, LLD class diagrams, Claude Code workflows, interview frameworks, architecture flows. No render pipeline needed. Triggered by "generate diagram", "draw this", "diagram for", "visualise", or proactively when a visual would sharpen an explanation.
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Life coach planning skill. /forge day = daily review, /forge week = Sunday week plan, /forge month = last-Sunday month plan. Auto-detects mode from $ARGUMENTS and current date. Ends with Google Calendar push option. Trigger: "forge", "plan my day/week/month", "daily/weekly/monthly review".