Loading...
Loading...
Found 443 Skills
Meme token fast-trading assistant with two core capabilities: 1. Meme Rush - Real-time meme token lists from launchpads (Pump.fun, Four.meme, etc.) across new, finalizing, and migrated stages 2. Topic Rush - AI-powered market hot topics with associated tokens ranked by net inflow Use this skill when users ask about new meme tokens, meme launches, bonding curve, migration status, pump.fun tokens, four.meme tokens, fast meme trading, market hot topics, or trending narratives.
Update documentation based on lessons learned. Use after completing work to capture learnings and prevent future issues.
ORCA v1.1 — Hardened dual-mode emerging movers scanner. Every lesson from 5+ days of live trading across 22 agents baked into the code. v1.1 adds the DSL state template directly in scanner output — eliminating the dsl-profile.json override bugs that broke Fox, Grizzly, Jackal, and every Wolf-based agent. XYZ equities banned at scan level. Leverage 7-10x enforced. Stagnation TP mandatory. 10% daily loss limit. 2-hour per-asset cooldown. Conviction-scaled Phase 1 timing per-signal. The agent cannot override any of these — they are in the scanner, not instructions.
Transform photos into stunning artistic styles using each::sense AI. Apply Van Gogh, Picasso, anime, watercolor, oil painting, and more to any image.
This Skill is built based on Eastmoney's authoritative database and the latest underlying market data, supporting natural language queries for market data (real-time quotes, main capital flows, valuations, etc. of stocks, industries, sectors, indices, funds, bonds), financial data (basic information of listed companies, financial indicators, executive information, main business, etc.), and relationship and operation data (associated relationships, enterprise operation data). It prevents models from answering financial data questions based on outdated knowledge and provides authoritative and timely financial data.
Sharpen, refine, and optimize AI agent skills through real usage — learn from mistakes, review quality, and improve over time. Observes skill execution in the current conversation, analyzes three sources (conversation history, file diffs, user feedback), and proposes concrete improvements to the target skill's SKILL.md. Works with Claude Code and any SKILL.md-based agent framework. Use after executing any skill: `/skill-sharpen [name]` for a specific skill, or `/skill-sharpen` to auto-detect the last used. Three modes: interactive (propose one by one), observe-only (dump to LESSONS.md), review (process pending lessons).
Verifica a Stack do MySQL. Além disso analisa parâmetros, rotas Traefik, volumes, recursos e conformidade do stack MySQL de Acordo com as Recomendações da Promovaweb.
Manages MongoDB Atlas Stream Processing (ASP) workflows. Handles workspace provisioning, data source/sink connections, processor lifecycle operations, debugging diagnostics, and tier sizing. Supports Kafka, Atlas clusters, S3, HTTPS, and Lambda integrations for streaming data workloads and event processing. NOT for general MongoDB queries or Atlas cluster management. Requires MongoDB MCP Server with Atlas API credentials.
Check GPU usage on remote servers. Connect to servers via SSH, display video memory usage, running processes, and associated containers for each GPU card. Use this when the user says to check GPU, graphics card usage, or video memory usage.
Complete coaching skills for Taiwanese nursing staff to write evidence-based nursing reports (evidence-based reading reports, evidence-based case analyses), designed specifically for the N1–N4 nursing advancement system and the review formats of the Taiwan Nurses Association and Taiwan Evidence-Based Nursing Association. This skill must be triggered when users mention terms such as "evidence-based nursing report", "evidence-based case analysis", "evidence-based reading report", "N2 report", "N3 report", "N4 report", "nursing advancement report", "nursing promotion", "PICO", "5A Steps", "CASP Appraisal", "nursing EBP", "EBN", "evidence-based nursing", "evidence-based care", "evidence level", "literature appraisal", or when any nursing staff asks about promotion writing, transforming clinical problems into evidence-based topics, evidence-based literature search strategies, CASP appraisal forms, Oxford evidence levels, APA 7th edition format, applying evidence-based interventions to cases, challenging nursing routines, dispelling nursing myths, etc. Even if users casually say "I need to write a report", "I want to advance to N3", "Help me find a topic", "Help me set up PICO", "How to appraise this literature", this skill should be actively activated to provide complete structures, sentence patterns, and writing strategies with the highest review pass rate.
Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons. Use this skill whenever the user wants to run a postmortem, retrospective, AAR, or after-action review on any past event. Triggers on after-action report, AAR, postmortem, retrospective, retro, post-incident review, what went well what didn't, lessons learned, blameless postmortem, root cause analysis, RCA, five whys. Also triggers when the user has just shipped something or just resolved an incident and wants to capture learnings.
Scores completed OKR sets at cycle close with KR-level scoring per the canonical OKR type enum (committed | aspirational | learning | operational_health | compliance_or_safety), committed-vs-aspirational interpretation, evidence quality assessment, learning synthesis, and next-cycle recommendations. Refuses to retroactively change targets or shrink committed scope, average away guardrail KRs, treat 0.7 as success for committed or compliance_or_safety KRs, equate effort with impact, or use scores for individual performance. Hands off to iterate-lessons-log, iterate-retrospective, define-hypothesis, measure-dashboard-requirements, measure-instrumentation-spec, and foundation-okr-writer.