grok-custom-skills

Turn real-life personal stories into high-quality cinematic rap lyrics optimized for Suno.ai. Use when user says "use suno on this", "turn this into a suno rap", "make a suno song about", or wants to convert a story into rap lyrics. Handles story extraction via questions, cinematic structure, length targeting, Suno safety filtering, and multiple styles.

Composes multi-step agent workflows from goals and available skills. Use whe ntasks need orchestration or user says compose workflow, plan steps, adaptiv epipeline. Triggers: compose workflow, plan steps.

Scores task uncertainty to calibrate memory depth and iteration count. Use w hen stakes are high, facts are sparse, or user says quantify uncertainty, fa st slow think, uncertainty score. Triggers: quantify uncertainty, fast slow think,uncertainty score, how sure.

Extracts shareable insights from long agent sessions for export. Use when us erwants a summary to share, export takeaways, or create share card. Triggers :extract shares, shareable summary, export insights.

Runs validation tests on code, skills, or outputs after changes. Use after i mplementations or when user says run tests, auto test, validate changes. Tri ggers: run tests, auto test, validate changes. Use when the user needs this capability.

Guides enabling beta or experimental Grok features safely. Use when user ask sabout beta features, early access, or unlock experimental tools. Triggers: beta feature, early access, unlock experimental, enable beta.

Identifies and resolves performance bottlenecks in agent workflows. Use when tasks are slow, stuck, or user says find bottleneck, speed up. Triggers: fi nd bottleneck, speed up, why so slow, optimize workflow.

Reviews code changes for bugs, style, security, and maintainability. Use aft erwriting code or when user says review code, code review, check my PR. Trig gers: review code, code review, check my changes. Use when the user needs th is capability.

Checks images for policy compliance before generation or publish. Use before sharing images or when user says compliance check, safe image. Use when the user needs this capability. Triggers: compliance check, safe image, image p olicy,can I publish this.

Bridges desktop automation to agent tool calls. Use when tasks need GUI inte raction, screen control, or user says computer use, desktop control. Trigger s: computer use, desktop control, click on screen, GUI automation.

Connects external services (GitHub, Notion, Drive) to agent workflows. Use w hen integrating APIs or user says connect service, bridge API. Triggers: con nectservice, bridge API, integrate GitHub, hook up Notion.

Provides control-panel overview of active skills, workflows, and status. Use when user says overview, status dashboard, what skills are active. Triggers : overview, status dashboard, what skills, control panel.

Schedules recurring or delayed agent tasks. Use when the user says schedulet his, run daily, cron job, or set timer. Parses schedules from SKILL.md orcro n-jobs.md. Triggers: schedule this, run daily, cron job, set timer.

Creates charts and visual summaries from tabular or numeric data. Use when u ser says visualize data, chart this, plot results. Triggers: visualize data, chart this, plot results, graph this.

Enables thorough multi-source research beyond quick answers. Use for complex research or user says deep search, comprehensive research. Use when the use r needs this capability. Triggers: deep search, comprehensive research, rese arch thoroughly.

Runs a defensive, read-only security audit of the local machine for MCP and AIagent risks: risky bindings, MCP config issues, and confused-deputy exposu re.Use before enabling MCP servers or when the user says audit mcp, check lo calhost exposure, mcp security. Outputs text, JSON, SARIF, or HTML. Triggers : audit mcp, mcp security, defensive-mcp-audit. Use when the user needs this capability.

Spawns desktop subagents for isolated GUI or local tasks. Use when delegatin gscreen work or user says desktop subagent, spawn local agent. Triggers: des ktop subagent, spawn local agent, delegate desktop.

Persists agent artifacts to cloud drive storage. Use when saving reports, ba ckups, or user says save to drive, persist output. Triggers: save to drive, persist output, upload report, cloud backup.

Tunes prompts iteratively using reflection and success metrics. Use when the user says optimize this prompt, dspy tune, or improve prompt with reflectio n. Integrates self-refine-loop for critique cycles. Triggers: optimize this prompt, dspy tune, improve prompt with reflection.

Tracks incremental improvements to skills and workflows over time. Use when iterating on skill quality or user says evolve skill, track evolution. Trigg ers:evolve skill, track evolution, improve over time.

Lightweight skill mutation helper for quick iterations. Use for small skill tweaks or user says quick evolve, mutate skill. Use when the user needs this capability. Triggers: quick evolve, mutate skill, tweak skill.

Triages exposed TCP listeners found by security audits. Identifies processes on risky bindings and recommends safe remediation. Use after mcp audit or w henuser asks what is on port X, fix exposed service. Triggers: exposed port, whatis listening, fix exposed service. Use when the user needs this capabil ity.

Investigates a GitHub repository from a URL: README, file tree, local clones tatus, and recommended next steps. Use when the user pastes a github.com URL or says check this repo, what is this project. Read-only; no credentialacces s. Triggers: github URL, check this repo, scout repo.

Verifies task completion against stated goals before marking work done. Usew hen the user asks to verify success, confirm completion, or says 'did Iachie ve this'. Runs checks + optional self-refine pass. Triggers: verify goal,con firm success, did I achieve this.

Pauses high-risk actions for explicit human approval. Use before WhatsApp se nds, deployments, deletions, credential changes, or financial actions. Trigg ers:approve this, hitl check, human review needed. Use when the user needs t his capability.

Browses web with human-like patterns to reduce bot detection. Use for scrapi ngfragile sites or user says stealth browse, human-like browsing. Use when t heuser needs this capability. Triggers: stealth browse, human-like browsing, avoid bot detection.

Stress-tests skills with edge-case prompts and scoring rubric. Use before pu blishing skills or user says test skill, hyper test. Use when the user needs this capability. Triggers: test skill, hyper test, skill QA, audit skill qu ality.

Generates visual assets via image generation tools. Use when user needs icon s,mockups, illustrations, or says generate image, create asset. Triggers: ge nerate image, create asset, make icon, design mockup.

Synthesizes findings from multiple sources into actionable insights. Use aft erresearch or user says synthesize, key takeaways, summarize findings. Use w henthe user needs this capability. Triggers: synthesize, key takeaways, summ arize findings, insight report.

Ensures web access is used effectively for live information. Use when facts may be stale or user says search web, need internet, look up online. Trigger s: search web, need internet, look up online, current info.

Builds structured knowledge graphs from text and sessions. Use when organizi ngentities and relations or user says knowledge graph, map entities. Trigger s:knowledge graph, map entities, build graph, entity map.

Discovers MCP servers and reads tool schemas before calling MCP tools. Use b efore MCP invocations or when user says what MCP tools, check MCP schema. Re ad-only filesystem inspection of MCP descriptors. Triggers: mcp tools, MCP s chema,discover MCP. Use when the user needs this capability.

Manages large context windows via chunking, summarization, and retrieval. Us efor long documents or user says manage context, too much context. Use when theuser needs this capability. Triggers: manage context, too much context, c hunkdocument, context budget.

Scores and filters retrieved memory against trust and poisoning risk. Use be fore citing prior context, or when user says sanitize memory, trust score re trieval, clean knowledge graph. Use when the user needs this capability. Tri ggers:sanitize memory, trust score retrieval, clean knowledge graph.

Coordinates multiple agents with role assignment and handoffs. Use for paral lel work or user says coordinate agents, multi agent team. Use when the user needs this capability. Triggers: coordinate agents, multi agent team, agent roles, delegate agents.

Orchestrates complex multi-agent pipelines with DAG execution. Use for large projects or user says orchestrate agents, agent pipeline. Use when the user needs this capability. Triggers: orchestrate agents, agent pipeline, multi step agents.

Unifies WhatsApp, Telegram, and future channels with shared memory and ratin g.Use when user says bridge messengers or unified chat memory. One rater, on e auto-responder policy across platforms. Triggers: bridge messengers, unifi ed chat memory, cross-platform reply.

Converts natural language descriptions into SKILL.md drafts. Use when user d escribes a new capability or says create skill from description. Triggers: c reate skill from description, NL to skill, skill from prompt.

Verifies local LLM services (e.g. Ollama) are bound to localhost only. Usewh en checking Ollama security or user says is ollama exposed, secure localLLM. Read-only network and config checks. Triggers: ollama security, localhostLL M, secure ollama.

Helps maintain open-source repos: README accuracy, version consistency, andp re-release checklists. Use when syncing docs with repo reality or user saysf ix README, prep release, repo maintenance. Triggers: fix README, preprelease , repo maintenance, sync docs.