查找技能

First step of deploying a new warp route (steps 1–9). Reads a Linear ticket to extract token details and chain configuration, looks up mailbox addresses from the local registry, generates the deploy.yaml, runs the deploy, and optionally runs a send test. Follow up with /warp-deploy-update-owners.

中文简介正在准备中。当前显示原文说明。

Add a new warp route to the Nexus UI whitelist. Checks out the nexus branch of hyperlane-warp-ui-template, adds the warp route ID to warpRouteWhitelist.ts, and opens a PR targeting the nexus branch.

中文简介正在准备中。当前显示原文说明。

Post-registry-merge steps for a new warp route deployment. Adds the warp route ID to warpIds.ts, updates .registryrc to latest registry commit, runs update-agent-config, then guides the user through warp monitor deployment and PR creation.

中文简介正在准备中。当前显示原文说明。

Preflight that resolves which private key(s) to use for the warp-deploy chain across every protocol in the route (EVM / Sealevel / Cosmos / Starknet / Tron). For each protocol the user supplies either a specific key spec (GCP secret name, env var, or keystore path) or a candidate list of GCP secret names for the agent to surface and the user to pick. The agent never enumerates GCP secrets on its own and never reads secret values without an explicit user-approved pick. Persists the resolution to `~/.hyperlane/key-contexts/ticket-id.yaml` for downstream warp-deploy skills to auto-load.

中文简介正在准备中。当前显示原文说明。

Post-deployment ownership transfer and registry PR for a warp route. Transfers ownership from the temporary deployer address to real owners, adds CoinGecko ID, commits, and opens a registry PR. Run after warp-deploy-init completes deployment.

中文简介正在准备中。当前显示原文说明。

Ownership-validation preflight for a warp route. For each chain in the route, determine the owner type (ICA / Safe / Squads / other multisig), confirm it exists on chain (or deploy if missing for ICAs), and reject EOAs. Run before /warp-deploy-init-route generates the deploy.yaml so the deployment never proceeds against an invalid owner set.

中文简介正在准备中。当前显示原文说明。

Generic update orchestrator for an already-deployed warp route. Reads a Linear ticket describing any combination of warp-fee changes / ISM changes / hook changes / owner-address changes / additional-collateral-chain additions, edits the registry deploy.yaml accordingly, builds a per-chain strategy file from the artifact-context owner classifications, runs `hyperlane warp apply`, fork-simulates the resulting receipts via `/warp-route-check`, and hands off to `/warp-update-propose` to land the proposals. Chain extension (adding a brand-new chain with new on-chain contracts) is a separate skill — see `/warp-update-extend`.

中文简介正在准备中。当前显示原文说明。

Pre-flight gas and balance check before deploying a warp route. Reads a Linear ticket, checks deployer wallet native gas balances per chain (warn if less than $10), and checks collateral token balance (need ~$1 for testing).

中文简介正在准备中。当前显示原文说明。

Add a new chain to an existing warp route owned by a customer. Reads a Linear ticket, adds the new chain to the deploy.yaml, builds a customer-specific strategy file for existing chains, runs warp apply, and outputs transaction files for the customer to sign via their multisig.

中文简介正在准备中。当前显示原文说明。

Read and manage Linear issues, projects, cycles, teams, comments, and labels. Use this whenever the user wants to list their issues, search issues, create or update an issue, move an issue between states, add a comment, check a project or cycle, look up a team, or ask "what's on my plate in Linear" — even if they don't say "API" or "GraphQL". Also use it for any linear.app URL or an issue identifier like "ENG-123". Always start from this skill when interacting with this service — its bundled scripts and recipes are the fastest path.

中文简介正在准备中。当前显示原文说明。

Execute Anarlog work immediately while recording issues, decisions, progress, and lessons in Linear. Use for Anarlog repository or Anarlog desktop, web, mobile, and API work, including related worktrees and ANLG issues. Explicit brainstorming stays discussion-first. Do not use for unrelated repositories or meeting-data queries.

中文简介正在准备中。当前显示原文说明。

Interact with Linear.app for issue tracking. Use when working with Linear tickets (format ABC-123), creating issues, updating status, or downloading attachments. Triggers on ticket references, issue management, or when user mentions Linear.

中文简介正在准备中。当前显示原文说明。

Use when the user supplies or imports existing security findings, vulnerability reports, or security/vulnerability Jira/Linear tickets from scanners, advisories, GitHub, Atlassian Rovo, Linear, or similar backlog sources and wants static repo-impact triage. Do not use for discovery, duplicate-bug triage, validation, or fixes.

中文简介正在准备中。当前显示原文说明。

Implement features, fix bugs, and keep the codebase healthy and maintainable. Works from a defined PBI, issue, or task description.

中文简介正在准备中。当前显示原文说明。

Pick a Linear PBI, spec it, assemble it, then hold at the gate with a Boeing list for HITL clearance. Does NOT ship.

中文简介正在准备中。当前显示原文说明。

Dev-Critic loop: implement, review, fix — repeat until clean

中文简介正在准备中。当前显示原文说明。

Produce written specs and atomic PBIs that an implementation agent can execute independently. Authors specs and Linear issues.

中文简介正在准备中。当前显示原文说明。

Linear project management - issues, projects, cycles, and roadmaps. Use for Linear-related tasks like managing issues, tracking sprints, and organizing projects.

中文简介正在准备中。当前显示原文说明。

Use when asked to create or update a PR, revise its description, or link issue references to its body. Not for multi-PR stacks: use gate-and-merge. Not for releases: use git-workflow-and-versioning.

中文简介正在准备中。当前显示原文说明。

Perform actions in Linear (read, create, update, search issues, projects, comments, teams, cycles, labels, etc.) by writing and running small Node scripts against the official @linear/sdk TypeScript SDK with a personal API key. Use this when the user wants to do Linear work from the terminal without the Linear MCP server, or asks to list/open/create/update/close Linear issues, leave comments, or query teams, projects, users, or workflow states.

中文简介正在准备中。当前显示原文说明。

Perform actions in Linear (read, create, update, search issues, projects, comments, teams, cycles, labels, etc.) by writing and running small Node scripts against the official @linear/sdk TypeScript SDK with a personal API key. Use this when the user wants to do Linear work from the terminal without the Linear MCP server, or asks to list/open/create/update/close Linear issues, leave comments, or query teams, projects, users, or workflow states.

中文简介正在准备中。当前显示原文说明。

Fires after fixing any non-trivial bug or regression. Asks: could the graph have caught this as a guarantee? Pairs with reflection-in-and-on-action — picks up after "earliest catchable signal" and asks the next question: was that signal expressible in graph? Triggers: (1) after any non-trivial bug fix is verified working, (2) after a regression report (something used to work, broke), (3) during step 6 (knowledge extraction) of the workflow, (4) when reflection-on-action surfaces a "would have been catchable" signal. Outcome is a triage decision (graph-reachable? rule expressible? rule sound?) and either a draft Linear issue + guarantee proposal, or a recorded "graph capability gap" note. Never auto-creates guarantees.

中文简介正在准备中。当前显示原文说明。

Cyclical dogfooding loop: test AI-AGENT-STORIES.md against the live graph, discover new stories, analyze gaps, fix root causes, re-test, write report. Use when: (1) user says "/gap-loop", (2) periodic dogfooding session, (3) after a release or major feature to re-validate stories, (4) before sprint planning to prioritize product gaps.

中文简介正在准备中。当前显示原文说明。

Use when setting up a Shipfox workflow from a template.

中文简介正在准备中。当前显示原文说明。