aarshsharma2803-stack
- 14 skills
- 0 followers
- 8 hours ago last updated
- ▌ Caveman · aarshsharma2803-stackTerse output mode — drop articles, filler, pleasantries. Keep all technical substance exactly. Fragments OK. Code blocks unchanged. Trigger: /caveman, "caveman mode", "be terse", "shorter responses", "less words", "drop the fluff"
- ▌ Ponytail · aarshsharma2803-stackCode minimalism — no premature abstractions, no speculative features, smallest correct implementation only. Auto-activates when complexity budget is minimal or user asks for simpler/smaller code. Trigger: complexity_budget:minimal, goal contains refactor/simplify/minimize/clean/slim, or user says "keep it simple", "no abstractions", "smaller diff".
- ▌ Output Mode · aarshsharma2803-stackEnforces structural output compression — eliminates preamble, wrap-up, and elaboration on self-documenting code. Targets 70-80% token reduction by attacking response volume, not just style. Stronger than caveman: caveman strips filler words; output-mode eliminates entire paragraphs. Auto-injected by OptimusPrime pre-response hook every prompt. Also activatable with /output-mode.
- ▌ Scope Guard · aarshsharma2803-stackActivates at the start of a Claude Code session when the user's first message describes a task or coding goal. Triggers on opening messages containing: fix, build, implement, refactor, add, update, create, debug, test, review, deploy, migrate, optimize, write, remove, rename. Also triggers on: "set scope", "define contract", "what's in scope", "let's work on", "I need to". Does NOT re-trigger mid-session. Does NOT trigger on questions or follow-ups in an ongoing session. Only fires on the opening task-description message.
- ▌ Superpowers · aarshsharma2803-stackFull engineering rigor for complex work — plan before code, name the pattern, verify before marking done. Auto-activates on full-complexity tasks, multi-file builds, or architectural changes. Trigger: complexity_budget:full, goal contains build/implement/architect/design/system, or user says "superpowers", "do this properly", "full methodology".
- ▌ Decision Log · aarshsharma2803-stackAlways active throughout every Claude Code session. Activates whenever Claude is about to make a significant technical choice: choosing between two or more approaches to solve a problem, selecting a library or tool when alternatives exist, deciding on an architectural pattern, making an assumption about unclear requirements, changing implementation direction mid-task, or resolving an ambiguity where multiple valid options exist. Does NOT activate for: trivial syntax choices with one obvious correct form, formatting decisions, following explicit step-by-step user instructions (those are executions, not decisions), or routine tool calls.
- ▌ UI UX Pro Max · aarshsharma2803-stackDesign intelligence for frontend work — component critique, layout review, accessibility checks, dark mode, responsive design, UX patterns. Trigger: /ui-ux-pro-max, "design review", "ux check", "accessibility audit", "review my UI", "is this accessible", "dark mode", files contain .tsx/.jsx/.css/.vue
- ▌ Cost Awareness · aarshsharma2803-stackActivates when user asks about token usage or cost: "how much has this session cost", "what's my token usage", "am I close to my budget", "cost report", "how many tokens", "what have I spent", "token count", "check my usage". Also activates proactively when session shows very high token consumption: responses consistently exceeding 400 lines, more than 15 tool calls in one turn, or user mentions slow responses, context limits, or approaching compaction.
- ▌ Context Restorer · aarshsharma2803-stackActivates when user pastes a session snapshot or references prior session context at the start of a new session. Trigger on: content starting with "# OPTIMUSPRIME SESSION SNAPSHOT"; multi-line content containing "## Goal", "## Changed", and "## Decisions" sections together; explicit phrases "restore context", "continue from last session", "here is my snapshot", "pick up where we left off", "resume session", "load context", "here's the snapshot", "context from last time". Also triggers on content starting with "GOAL:", "Generated:", "CAPTURED:" that looks like a structured session summary. Does NOT trigger on normal task descriptions without these snapshot markers.
- ▌ Confidence Signal · aarshsharma2803-stackActivates when Claude has internal uncertainty below 70% about whether the chosen approach is correct before executing. Triggers on: uncertainty about correctness of a complex algorithm with subtle edge cases; uncertainty whether a refactor will silently break callers identified by dependency-analyzer; requirement ambiguity where two interpretations lead to very different implementations and the wrong choice has significant rework cost; an approach similar to one in .optimusprime/attempts.md (previously failed this session). Does NOT activate for HIGH confidence. Only fires before executing, not after.
- ▌ Claude Md Generator · aarshsharma2803-stackActivates when user requests CLAUDE.md generation or update: "generate CLAUDE.md", "update CLAUDE.md", "my CLAUDE.md is outdated", "create project context file", "claude-md generate", "regenerate project instructions", "write CLAUDE.md". Also activates when CLAUDE.md is missing from a project root containing package.json, pyproject.toml, Cargo.toml, or go.mod and the user appears to be starting work on that project.
- ▌ Optimusprime · aarshsharma2803-stackSession memory + guardrails for Claude Code. Remembers decisions across sessions, blocks repeated failures, compresses output, activates helper bots automatically. Subcommands: /optimusprime status|compact|repair|bots|tokens|quality|dashboard. Trigger: /optimusprime, /op, "activate optimusprime", "op status", "is op running".
- ▌ Optimusprime Compact · aarshsharma2803-stackCompact the current conversation — preserve decisions, requirements, errors, architecture, and active task state; strip repeated or low-value content; reduce token usage; prepare clean context for Claude. Trigger: /optimusprime-compact, user says "compact", "compress conversation", "clean up context", "too many tokens", or /compact-conversation.
- ▌ Op · aarshsharma2803-stackOptimusPrime — short trigger. Identical to /optimusprime. Session memory, guardrails, output compression, Auto Bots. Subcommands: status | compact | slim | repair | bots | tokens | quality | dashboard Trigger: /op, "op status", "op slim", "what does op say", "check op", "op repair"