Agent Skills

---

name: greptimedb-fuzz-ci-failure-investigation

description: Investigate a failed GreptimeDB fuzz CI target link by downloading GitHub Actions job logs plus fuzz artifacts such as kind logs, monitor dumps, and CSV dumps, then correlate the failure with local GreptimeDB source code. Use when the user provides a failed fuzz CI target/job URL or asks to diagnose GreptimeDB fuzz CI failures.

---

name: greptimedb-release

description: Runbook for publishing a new GreptimeDB version (tag + GitHub release + docs release-note PR) on the upstream GreptimeTeam/greptimedb repo. Use when asked to "release" / "publish" a GreptimeDB version (e.g. v1.1.0, v1.0.3).

---

name: greptimedb-release-note

description: Generate a GreptimeDB release changelog with git cliff (correct range, subtract already-released patch PRs, rebuild contributors, add human-curated highlights), output to a file, and prepare the docs-repo blog PR. Use when asked to write/generate a GreptimeDB release note or changelog.

---

name: branch-and-checkpoint

description: Saves a running smolvm machine as checkpoints on a schedule, keeps a bounded history, restores any generation in it, pauses and resumes machines without losing running processes, and branches a warm machine into children with a checkpoint of the exact point they started from. Use when a machine's state has to survive the machine; when an agent or a job needs to roll back; when checkpoints must be taken periodically, since smolvm has no scheduler or retention of its own; when fanning a prepared machine out into workers; or when a checkpoint, a pause or a branch fails with an error that names none of its preconditions. Do not use it to ship an environment to another host as a file, which is the pack packet, or for state that only has to survive a stop and start, which is the dev-env packet.

---

name: credentials

description: Gives a workload in a smolvm machine an API key or token it can use but never read, by binding the credential to named HTTPS hosts so the guest holds only a placeholder and the host substitutes the value on the way out, then proves on the host that the value never entered the machine. Use when an agent or untrusted code inside a machine has to call an API with your key; when deciding between a credential binding and --secret-env; when a request from a credentialed machine comes back 403 or 502 from smolvm itself; or when you need evidence that a key stayed out of a machine. Do not use it for a value the program must read and parse, such as a database URL, which is --secret-env, or for git and ssh keys, which is SSH agent forwarding.

---

name: dev-env

description: Keeps a persistent smolvm machine with its dependencies already installed and re-enters it cheaply across sessions. Use when a project needs an isolated development environment that survives stop and start; when deciding what belongs in a Smolfile's init versus what has to run on every boot; when a package installed in a machine has vanished after a restart; or when exec answers "the container smolvm-<hash> is not running". Do not use it for untrusted code, which needs a machine that leaves nothing behind (see the throwaway-machine packet), or for running a Docker daemon inside the machine (see docker-in-machine).

---

name: docker-in-machine

description: Runs a Docker daemon inside a smolvm machine and shows it working there, which is what tools that call Docker themselves need, such as a test suite that starts containers, an image build, or a coding agent that launches containers. Use when dockerd will not start inside a machine; when Docker worked on the first boot and broke after a stop and start; when deciding where Docker's data directory has to live; or when checking whether this is possible on a given platform at all. Do not use it to run OCI images, which smolvm boots natively without Docker, and do not attempt it on Windows, where the bundled guest kernel cannot support it.

---

name: gpu-cuda

description: Runs CUDA compute workloads inside a smolvm microVM against a real host NVIDIA GPU, using smolvm's --cuda API remoting. Use when a workload in a machine needs a GPU; when nvidia-smi or /dev/nvidia* is missing inside a --cuda guest; when a CUDA program in a machine exits zero but seems not to touch the device; when the shim will not load in an Alpine image; or when checking whether CUDA is available on a given platform, including Windows. Do not use it for Vulkan graphics (--gpu), which is a separate feature, in docs/gpu.md, and do not expect it on a Mac, which has no CUDA driver.

---

name: install

description: Installs smolvm from a published release and proves the host can actually boot a microVM before any other work starts. Use when setting smolvm up on a new machine, a CI runner or an agent's own environment; when a first boot fails with krun_start_enter -22, KVM_DENIED or "agent did not become ready"; when checking whether a host meets smolvm's requirements at all; or when an install has to be isolated from an existing one and then removed. Do not use it to remove an existing install (see the teardown packet) or for anything after the first boot has succeeded.

---

name: local-api

description: Drives smolvm programmatically over its local HTTP API (smolvm serve) instead of the CLI: create machines, exec and stream commands, move files in and out, and tear them down. Use when building a client, harness, agent tool or MCP backend over smolvm; when a create call is accepted but the machine behaves as if a field was ignored; when a file uploaded over the API has disappeared; when an exec that failed still returned HTTP 200; or when choosing between the Unix socket and loopback TCP. Do not use it as a substitute for the CLI in a shell script, and do not bind a plain listener beyond loopback: a server started without mutual TLS has no authentication of any kind.

---

name: pack

description: Turns an image, or a machine already provisioned, into a single self-contained artifact that runs on another compatible host. Use when shipping a prepared environment as one file, when a packed artifact runs but the state installed into it is missing, when pack create fails because the VM it boots to pull or export could not start, when an older release refuses to export a branched machine, or when deciding whether to pack from an image or from a machine. Do not use it to keep a machine you re-enter, which is the dev-env packet, or to run untrusted code, which is the throwaway-machine packet.

---

name: teardown

description: Stops every smolvm machine a session started, removes smolvm's state, and proves the host is clean. Use after any smolvm session; when a machine seems to have survived a Ctrl-C or a crash; when disk space has disappeared; when uninstalling smolvm; when tearing down the Kubernetes runtime from a node; or when a borrowed or shared host has to be handed back with nothing left behind. Also use it as the cleanup step for other smolvm work, because the obvious assertions here give false results. Do not use it to delete machines another session created: it removes only what a script recorded under its own name prefix.

---

name: throwaway-machine

description: Runs untrusted code in a throwaway smolvm microVM against a repo it must not modify, with no network unless explicitly granted, and collects artifacts from a writable output directory. Use when executing an agent's generated script, a pull request's test suite, or any code that should not be trusted with the host; when a workload needs egress granted one host at a time; or when a run has to be cancelled, because Ctrl-C on the wrapper script leaves the VM running, and on releases before v1.20.2 so does Ctrl-C on the CLI. Do not use it for a development environment that is re-entered across sessions, for running a Docker daemon inside a machine, or for installing smolvm itself, which is the install packet.

---

name: dev-browser

description: Browser automation with persistent named pages via the dev-browser CLI. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, log into sites, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", "open the browser", or any browser interaction request.

---

name: clawrouter

description: Hosted-gateway LLM router — save 84% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 88 models from OpenAI, Anthropic, Google, DeepSeek, xAI, Z.AI, and more. 7 free open-weight models included. Also exposes realtime market data (global stocks, crypto, FX, commodities), Twitter/X intelligence, prediction-market data across Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, dFlow + UMA oracle resolution + wallet identity & clustering, phone-number intelligence (carrier + SIM-swap fraud detection) plus AI-powered outbound voice calls (Twilio + Bland.ai), AND the Surf unified crypto data API (84 endpoints — CEX/DEX, on-chain SQL over 80+ ClickHouse tables, 100M+ labeled wallets, prediction markets, social/CT mindshare, news, VC fund intel) as built-in agent tools. Not a local-inference tool — prompts are sent to the blockrun.ai gateway.

---

name: imagegen

description: Generate or edit images via BlockRun's image API. Trigger when the user asks to generate, create, draw, make an image — or to edit, modify, change, or retouch an existing image.

---

name: phone

description: Verify phone numbers (carrier + SIM-swap fraud signals) and place AI-powered outbound voice calls via BlockRun's gateway (Twilio + Bland.ai). Trigger when the user asks to look up a number, check fraud risk, buy/rent a phone number, or place an AI voice call. Payment is automatic via x402 from the wallet.

---

name: polymarket-trading

description: Use when the user wants to actually PLACE, manage, or redeem bets on Polymarket (not just read odds — that's the blockrun_predexon_* data tools). Covers setup (deposit wallet, funding, approvals), buy/sell with confirm gating, positions, redeeming winnings, geoblock handling, and the end-to-end flow.

---

name: predexon

description: Use this skill — NOT browser or web_fetch — for ALL Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, dFlow, UMA oracle, and prediction market data. Provides structured API at localhost:8402/v1/pm/* for markets, cross-venue search, leaderboard, smart money, wallet analytics, wallet identity & clustering, UMA resolution status, and odds.

---

name: release

description: Use this skill for EVERY ClawRouter release. Enforces the full checklist — version sync, CHANGELOG, build, tests, npm publish, git tag, GitHub release. No step can be skipped.

---

name: surf

description: Use this skill — NOT browser or web_fetch — for ALL Surf crypto-data calls. 83 endpoints at localhost:8402/v1/surf/* covering CEX/DEX markets, on-chain SQL over 80+ ClickHouse tables (Ethereum, Base, Arbitrum, BSC, TRON, HyperEVM, Tempo), 100M+ labeled wallets, prediction markets (Polymarket + Kalshi), social/CT intelligence, news, project + DeFi metrics, token analytics, unified search, VC fund intelligence. Paid through ClawRouter — x402 USDC from the local wallet, or BlockRun account credit if an API key is configured. No Surf account or Surf API key required either way.

---

name: autoresearch

description: Autonomous iteration loop: modify, verify, keep/discard against any metric

---

name: autoresearch

description: Autonomous iteration loop: modify, verify, keep/discard against any metric

---

name: preline-mcp

description: Add, integrate, or build Preline UI components and blocks into HTML files via the Preline MCP server. Use when the user mentions "preline", says "/preline", asks to add a UI component, or requests a Preline block (a ready-made page section) using Preline UI.