菜单
这个仓库中的 skills
SkillsMP 已收集 evolution-foundation/evo-nexus 中的 192 个 Skill。打开任一 Skill 可查看来源和详情。
evolution-foundation/evo-nexus已展示 40 / 192 个已收集 Skill。
Create a Mission, Project, or Goal (Mission → Project → Goal → Task hierarchy) in EvoNexus. Guides the user through picking a mission, choosing or creating a project, defining a measurable goal with metric_type and target_value. Writes to the SQLite goals…
原文语言：英语
Create a new heartbeat (proactive agent scheduled with a decision prompt) for EvoNexus. Guides the user through picking an agent, setting interval, wake triggers, and the decision prompt that governs when the agent acts. Writes to config/heartbeats.yaml with…
原文语言：英语
Create a new ticket (persistent conversation/work thread) in EvoNexus. Assigns to an agent, sets priority, optionally links to a goal or project. Writes via POST /api/tickets. Use when the user says 'create a ticket', 'open an issue', 'add to Zara's queue',…
原文语言：英语
List, enable, disable, or manually trigger heartbeats (proactive agents). Shows last 10 runs with status and cost. Use when the user says 'list heartbeats', 'show active heartbeats', 'enable atlas-4h', 'disable zara-2h', 'run atlas heartbeat now', 'which…
原文语言：英语
Create, update, list, or run scheduled tasks (one-off actions). Schedule a skill, prompt, or script to run at a specific date/time without creating a full routine. Use when user says 'schedule this for', 'run this at', 'agendar para', 'roda isso amanha',…
原文语言：英语
Create, manage, and test reactive triggers (webhook & event-based). Triggers execute skills or routines in response to external events (GitHub push, Stripe payment, Linear issue, etc.). Use when user says 'create trigger', 'list triggers', 'novo trigger',…
原文语言：英语
Generate PNG images using AI (multiple models via OpenRouter including Gemini, FLUX.2, Riverflow, SeedDream, GPT-5 Image, proxied through Cloudflare AI Gateway BYOK). Also analyze/describe existing images using multimodal AI vision. Use when user asks to…
原文语言：英语
Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated panel, evolves winners through multiple rounds, outputs optimized version + full experiment log. Use when optimizing landing pages, email…
原文语言：英语
Autonomous growth experimentation framework. Creates A/B/multivariate experiments with hypotheses, logs data points, runs statistical analysis (bootstrap CI + Mann-Whitney U), auto-promotes winners to a living playbook, and suggests next experiments. Use when…
原文语言：英语
Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts. Handles copy, sequences, landing pages, strategy docs, titles, charts, recruiting evaluations, or anything else that needs a quality gate.…
原文语言：英语
AI-powered SEO operations with keyword intelligence, competitor gap analysis, GSC optimization, and trend detection. Use for keyword research, content briefs, quick-win keyword identification, competitor gaps, trending topics, and decaying content analysis.
原文语言：英语
Write long-form X (Twitter) posts and threads in a founder/CEO voice. Use when drafting X articles, long tweets, thought leadership threads, or viral content. Produces contrarian, data-backed posts with ASCII diagrams and code block visuals. Includes…
原文语言：英语
Analyze YouTube channels for outlier videos and packaging patterns. Identifies what's working (2x+ average views) across any set of channels. Use when asked for YouTube competitive analysis, viral video patterns, or packaging/title inspiration.
原文语言：英语
Extract 1–5 atomic facts from pasted text and save them as spaced-repetition cards in workspace/learning/facts/ with SM-2 frontmatter. Use when the user says "capture this", "save fact", "learn this", "memorize this", or pastes content they want to retain.
原文语言：英语
Generate open-ended quiz questions from facts in a specific deck (or all facts). Read-only — does NOT update SM-2 state or review-log. Use when the user says "quiz", "test me", "pratique", "/learn-quiz", or wants to practice without triggering a formal review.
原文语言：英语
Review spaced-repetition facts that are due today. Applies SM-2 algorithm to update interval, ease, and next_review in each fact's frontmatter. Updates review-log.jsonl. Use when the user says "revisar", "review facts", "study", or "/learn-review".
原文语言：英语
Report spaced-repetition statistics: total facts, overdue count, retention rate, active decks, and facts added this week. Use when the user says "stats", "estatísticas", "como está meu aprendizado", "/learn-stats", or wants a dashboard of their learning loop.
原文语言：英语
Bling ERP integration via API v3. Manage products, sales orders, contacts, fiscal invoices (NF-e), and stock. Use when users ask about ERP data, products, orders, contacts, invoices, or inventory from Bling. Integração com ERP Bling: produtos, pedidos,…
原文语言：英语
Asaas payment platform integration via API v3. Manage payments (Pix, boleto, credit card), customers, subscriptions, transfers, balance, and marketplace subaccounts. Use when users ask about payment collection, billing automation, Pix, boleto, subscriptions,…
原文语言：英语
Create a phased activation plan using the EvoNexus standard structure — single index file + folder-per-phase + file-per-item, each item detailed with owner, dependencies, decisions pending, suggested agent team. Use when the user asks for an activation plan,…
原文语言：英语
Query YouTube Data API v3 — channel stats, recent videos, top videos, comments. Supports multi-account (OAuth or API Key). Use when user asks about YouTube metrics, YouTube channel, subscribers, views, videos, engagement, or any reference to YouTube analytics.
原文语言：英语
Post-AI-generation cleanup — remove single-use helpers, over-abstractions, generic naming, and unnecessary configurability. Use after dev-autopilot or any LLM-generated code burst.
原文语言：英语
Advisory router — query Claude, Codex, or Gemini for a quick second opinion. Experimental — only Claude is guaranteed available; other models require dev-mcp-setup configuration.
原文语言：英语
Tri-model orchestration — run the same task through Claude + Codex + Gemini in parallel and synthesize the best answer. Use for high-stakes decisions where multi-model consensus reduces single-model bias.
原文语言：英语
Set up Telegram, Discord, or Slack webhooks for engineering layer alerts — long-running task completion, build failures, security audit alerts.
原文语言：英语
Two-stage investigation — causal trace (via @trail-tracer) followed by requirements crystallization (via @echo-analyst + dev-deep-interview). Use when a problem is both unclear in cause AND unclear in scope.
原文语言：英语
Deep codebase initialization — generate hierarchical AGENTS.md / CLAUDE.md context files for a new project so engineering agents have full context from session start.
原文语言：英语
Parallel external documentation lookup. Spawn multiple @scroll-docs agents simultaneously to fetch SDK refs, API docs, and framework guides for different topics in one pass.
原文语言：英语
Meta-skill — extract reusable skills from the current conversation. Identifies patterns that appeared 3+ times and proposes them as new skills. Pairs with skill-creator builtin.
原文语言：英语
Configure MCP servers for the workspace — web search, filesystem, GitHub, Stripe, etc. Use when adding a new integration that needs MCP-level access.
原文语言：英语
Worktree-first development environment — create per-issue or per-PR git worktrees, optionally with tmux sessions, so multiple work streams don't collide.
原文语言：英语
Persistence loop — keep working on a task until it's resolved or until a circuit breaker stops you. Different from /loop (which is time-based) — ralph is iteration-based with state.
原文语言：英语
Multi-perspective consensus planning with Planner/Architect/Critic loop. Use when high-stakes decisions need RALPLAN-DR structured deliberation (auth, migrations, public APIs, irreversible changes). Pairs with @compass-planner + @apex-architect +…
原文语言：英语
Release preparation — changelog generation, version bump, tag creation. Generic version (not project-specific). For EvoNexus releases, use custom-release instead.
原文语言：英语
Persist context across engineering sessions — save important decisions, gotchas, or patterns that should survive beyond the current conversation. For long-term workspace memory, prefer mempalace.
原文语言：英语
Scientific method scaffolding — hypothesis → experiment → evidence → conclusion. Use when you need rigorous causal reasoning rather than vibes-based debugging.
原文语言：英语
On-demand spawning of multiple engineering agents in parallel for large-context work. Use when a task is too big for a single agent and the work can be split into independent streams.
原文语言：英语
Evidence-driven causal tracing with competing hypotheses. Use when an observation has multiple plausible explanations and you need to systematically rank them with evidence FOR and AGAINST each. Pairs with @trail-tracer.
原文语言：英语
QA cycling workflow — repeat build/lint/test/fix cycles up to 5 times until all checks pass. Stops early if the same error repeats 3 times (signals a fundamental issue, not a fixable one).
原文语言：英语
Visual regression testing — capture before/after screenshots of UI changes and compare. Use when a UI change might have unintended visual impact across components.
原文语言：英语