knowledge-work-plugins

Analyzes weight file diffs after benchmarks to flag significant regressions in ref_time, proof_size, and DB reads. Use when updating weights, running benchmarks, or reviewing weight changes.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when executing implementation plans with independent tasks in the current session

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

QA cherry-pick tracking documents for polkadot-sdk fork upgrades. Use when auditing, verifying, or updating cherry-pick tables in docs/cherry-picks/, when upgrading to a new polkadot-sdk stable branch, or when checking if a cherry-pick was applied.

Use when creating, reviewing, backfilling, superseding, or organizing architecture decision records (ADRs/MADR) for significant technical decisions; avoid trivial implementation notes and broad design documents

Use when converting a meeting transcript, recording transcript, or auto-generated notes (Gemini, Granola, Otter, Fireflies, Zoom) into a structured summary. Not for behavioral analysis, filler-word counts, or facilitation critique.

Use when creating new skills, editing existing skills, or verifying skills work before deployment

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when identifying project risks, creating risk registers, building mitigation plans, or assessing impact and likelihood of threats to delivery

Maintains bridge infrastructure for Moonbeam including substrate-relay updates, zombienet chain spec generation, and bridge integration testing. Use when upgrading polkadot-sdk stable versions, updating the substrate-relay binary, regenerating relay chain specs, or debugging bridge relayer issues.

Use when you have a spec or requirements for a multi-step task, before touching code

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Write pull request descriptions from local git changes. Use when asked to summarize a branch diff into PR-ready markdown, including goal discovery, breaking-change detection, and template-based formatting. Select base branch as `main`/`master` by default, or `moonbeam-polkadot-stableNNNN` when the user provides a 4-digit release number.

Use when creating a new plugin for agentic AI assistants, scaffolding plugin directory structures, starting a new plugin project from scratch, or porting existing skills from another repository

Use when auditing or refactoring a reusable agent artifact such as a `SKILL.md` bundle or standalone agent definition for trigger quality, bundle structure, metadata parity, progressive disclosure, or reusable capability fit.

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Use when installing or configuring a distributable plugin that contains ~~placeholder references needing replacement with organization-specific tool names

Creates and integrates new FRAME pallets into the Moonbeam runtime. Use when adding on-chain functionality, implementing Substrate-native features, creating new storage and extrinsics, or extending runtime capabilities.

Creates and integrates EVM precompiled contracts that expose Substrate functionality to the EVM. Use when exposing pallet functionality to Solidity contracts, creating Ethereum-compatible interfaces, implementing standard Ethereum precompiles, or bridging EVM and Substrate state.

Creates and runs benchmarks for pallets and precompiles to generate accurate weight functions for the Moonbeam runtime. Use when adding new extrinsics, creating precompiles, optimizing functionality, updating weights after logic changes, or validating weight accuracy.

Debugs issues in the Moonbeam parachain including runtime panics, EVM execution failures, XCM message delivery problems, and client-side errors. Use when encountering transaction failures, unexpected behavior, state inconsistencies, block production issues, or RPC errors.

Develops and extends RPC methods for the Moonbeam node including Ethereum-compatible RPCs and custom Moonbeam RPCs. Use when adding RPC endpoints, implementing Ethereum RPC compatibility, debugging RPC issues, extending existing methods, or adding tracing/debug capabilities.

Develops and modifies the Moonbeam runtime using general patterns and best practices. Use when modifying runtime configuration, adding pallets to the runtime, implementing migrations, updating runtime APIs, or managing runtime versioning.

Develops XCM (Cross-Consensus Messaging) functionality for cross-chain communication between Moonbeam and other parachains/relay chains. Use when implementing cross-chain asset transfers, adding support for remote chains, debugging XCM message failures, configuring XCM fees, or registering foreign assets.

Implements Ethereum Improvement Proposals (EIPs) in the Moonbeam runtime to maintain Ethereum compatibility. Use when adding support for new opcodes, implementing precompile standards, supporting new transaction types, updating gas costs per EIP specs, or implementing account abstraction features.

Manages Moonbeam's parachain staking system including collator selection, delegation, and rewards. Use when modifying staking parameters, debugging delegation issues, implementing staking features, understanding collator selection, or working with staking rewards.

Patches Cargo dependencies to use local checkouts or different branches. Use when testing changes across multiple repositories, debugging dependency issues, or developing against local polkadot-sdk/frontier/moonkit forks.

Runs and writes tests for the Moonbeam parachain including Rust unit tests, TypeScript integration tests, smoke tests, and multi-chain tests. Use when verifying changes, writing tests for new features, debugging test failures, running specific test suites, or creating test fixtures.

Writes and tests runtime migrations for state transitions in Moonbeam. Use when handling storage layout changes, renaming or removing storage items, data format changes, pallet index changes, or storage key modifications.