Loading...
Loading...
Found 540 Skills
Debugs the Buttercup CRS (Cyber Reasoning System) running on Kubernetes. Use when diagnosing pod crashes, restart loops, Redis failures, resource pressure, disk saturation, DinD issues, or any service misbehavior in the crs namespace. Covers triage, log analysis, queue inspection, and common failure patterns for: redis, fuzzer-bot, coverage-bot, seed-gen, patcher, build-bot, scheduler, task-server, task-downloader, program-model, litellm, dind, tracer-bot, merger-bot, competition-api, pov-reproducer, scratch-cleaner, registry-cache, image-preloader, ui.
Analyze Claude Code session logs - extract thinking blocks, tool usage stats, error patterns, debug trajectories. Triggers on: introspect, session logs, trajectory, analyze sessions, what went wrong, tool usage, thinking blocks, session history, my reasoning, past sessions, what did I do.
This skill should be used when the user wants to invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. Trigger phrases include "use codex", "ask codex", "run codex", "call codex", "codex cli", "GPT-5 reasoning", "OpenAI reasoning", or when users request complex implementation challenges, advanced reasoning, architecture design, or high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.
Integrate Perplexity API for web-grounded AI responses and search. Covers Sonar models, Search API, SDK usage (Python/TypeScript), streaming, structured outputs, filters, media attachments, Pro Search, and prompting. Keywords: Perplexity, Sonar, sonar-pro, sonar-reasoning-pro, sonar-deep-research, web search API, grounded LLM, chat completions, perplexityai SDK, image attachments, PDF analysis.
[Dev] Extracts and organizes best practices for a given topic into a minimal tree structure (max depth 3, max 5 children per node). Use during task planning when writing subtasks in Docs/{name}_Task.md - output is added under each subtask as a concise reference guide. Pure reasoning task with strict formatting rules: keywords/noun phrases only, no prose. (project)
Reasoning-driven image generation using structured creative briefs (Gemini 3 style) — generates high-fidelity images via muapi.ai with logic-based prompting
Comprehensive prompt and context engineering for any AI system. Four modes: (1) Craft new prompts from scratch, (2) Analyze existing prompts with diagnostic scoring and optional improvement, (3) Convert prompts between model families (Claude/GPT/Gemini/Llama), (4) Evaluate prompts with test suites and rubrics. Adapts all recommendations to model class (instruction-following vs reasoning). Validates findings against current documentation. Use for system prompts, agent prompts, RAG pipelines, tool definitions, or any LLM context design. NOT for running prompts, generating content, or building agents.
When the user wants to improve crawlability, fix orphan pages, or optimize site structure for search engines. Also use when the user mentions "crawlability," "crawl budget," "orphan pages," "internal links," "site structure," "site crawlability," "infinite scroll," "pagination," "masonry SEO," or "content not indexed."
Anticipate and neutralize every reason customers say "no" before they say it. Combine Chris Voss's negotiation psychology with systematic sales methodology to turn objections into opportunities. Use when: **Before sales calls** to prepare responses to common pushback; **After losing deals** to document and learn from objections; **Product positioning** to address concerns in marketing copy; **Pricing conversations** to defend value against price resistance; **Team training** to create an obje...
Use this skill when designing event-driven systems, implementing event sourcing, applying CQRS patterns, selecting message brokers, or reasoning about eventual consistency. Triggers on tasks involving Kafka, RabbitMQ, event stores, command-query separation, domain events, sagas, compensating transactions, idempotency, message ordering, and any architecture where components communicate through asynchronous events rather than direct synchronous calls.
Create session handoff artifacts (HANDOFF.json + .continue-here.md) that capture completed work, remaining tasks, decisions, uncommitted files, and reasoning context so the next session can resume without reconstruction overhead. Use for "pause", "save progress", "handoff", "stopping for now", "end session", "pick this up later". Do NOT use for task planning (use task_plan.md), session summaries (use /retro), or committing work (use /commit or git directly).
Fetch the latest financial signals and transmission-chain analyses from DeepEar Lite. Use when the user needs immediate insights into financial market trends, stock performance factors, and reasoning from the DeepEar Lite dashboard.