ethereum

Write consensus tests using repository patterns and fixtures.

Check whether repository guidance and skills are still accurate.

Apply repository conventions when editing GitHub Actions workflows.

Clean up and future-proof a ported static test.

Audit grammar in documentation and code comments.

Implement EIP specification changes using repository conventions.

Run and fix the repository static analysis suite.

Run locally filled fixtures against execution clients with a selected Hive simulator and a network client configuration from hive-tests. Use when testing clients against a devnet or client releases in Hive, or when building a Hive client YAML.

Per-property guidance for the Cryptography property group. Invoke when evaluating, reviewing, or editing notes/values for Verifiability, Post-quantum secure, Number of secrets, or Client-side proving. Cross-cutting rules in scripts/research-prompts.ts still…

Per-property guidance for the Trust / robustness property group (drawn from the schema's Decentralization & Security and Verifiable groups, excluding maturity which lives in property-rules-timing). Invoke when evaluating, reviewing, or editing notes/values…

End-to-end evaluation pipeline for a single protocol — discover sources, run the citations research script, review the output against rules, run an independent second-pass review, and report, applying the qualifying rule-gap improvements to the rule files and…

Per-property guidance for timing-related properties — Time-to-finality, Deposit time, Withdraw time, and Implementation maturity. Invoke when evaluating, reviewing, or editing notes/values for any of these. Cross-cutting rules in scripts/research-prompts.ts…

Per-property guidance for the State property group. Invoke when evaluating, reviewing, or editing notes/values for Private state model, Private Data Storage, Client-side indexing, or Private State Scalability. Cross-cutting rules in…

Find authoritative source URLs for each property of a protocol evaluation using WebSearch/WebFetch, then write the results to scripts/research-cache/{id}.json so the API research script can consume them without spending API credits on web search.

Per-property guidance for the Privacy property group. Invoke when evaluating, reviewing, or editing notes/values for any of Anonymity, Confidentiality, Asset privacy, or Plausible deniability. Loads only the privacy-group rules so the active context stays…

Independent second-pass review of a protocol evaluation. Run AFTER /review-evaluation has produced its first report. This skill spawns a fresh subagent with no exposure to the first review's findings, has it review the same evaluation from scratch against the…

Use when working on the translation pipeline (`src/scripts/intl-pipeline/`), the post-import sanitizer (`intl-sanitizer.ts`), the `intl/pending-*` branches, the `intl-pipeline.yml` GitHub Actions workflow, ETHGlossary integration, or any translation-related…

This skill provides patterns for working with the data-layer module. Use when creating/editing files in src/data-layer/, src/lib/data/, or adding new data sources.

Use when building, refactoring, or styling any UI in the ethereum.org Next.js site (`src/components/`, `app/`, `src/styles/`, `public/content/`, or any `.tsx`/`.mdx`/`.css` change that affects the rendered UI). Provides canonical component choices, design…

Use when reviewing translation imports/PRs (especially against `intl/pending-*` branches), evaluating translation quality across any of the 24 target languages, triaging issues in `.claude/translation-review/`, scoring a locale's translation, running the…

Interview-then-scaffold guide for adding a new page to ethereum.org. Forks first on markdown-backed vs App Router page, then picks the layout and hero, maps the Figma design to existing components, and builds it reuse-first. Invoke with /new-page.

Playwright + Chromatic full-page visual tests for ethereum.org. Trigger on "add a page to the visual suite", "the snapshot keeps changing", "chromatic pages", "chromatic playwright", or edits to `tests/visual/`, `playwright.visual.config.ts`, or the…

Performance patterns and anti-patterns for ethereum.org covering TTFB, LCP, INP, CLS, bundle size, build memory, and RSC payload. Use when diagnosing a perf regression or reviewing proposed code changes for perf landmines.

Adversarial review loop for a built ethereum.org page — spawns copy and design-system reviewer subagents against the Figma source, triages their findings, fixes, and re-reviews until a fresh round comes back clean. Invoke with /review-page.

Convert an EIP proposed for the current fork into forkcast JSON format. Use when adding a new EIP to the tracker.

Draft the laymanDescription, benefits, and tradeoffs fields for an EIP that already exists in src/data/eips/. Use when audit-eips reports missing narrative fields on EIPs that otherwise have complete metadata. For adding a brand-new EIP to the tracker, use…

Propagate a call's fork stage-change decisions into EIP data files. Use when a call's key_decisions.json records EIPs proposed/considered/scheduled/etc. for a fork (e.g. "PFI for Hegota") and the EIP JSONs need their forkRelationships updated to match.

Classify an EIP's client layer (EL or CL) and set the `layer` field on EIPs that are missing it. Use when active fork EIPs lack a layer (e.g. audit-eips reports "missing layer"). Combines a deterministic `requires`-dependency signal with a semantic read of…

Set video/transcript sync offsets for newly synced calls. Use after "sync call assets from eth/pm" commits land on main.

Onboard a brand-new breakout call series across ethereum/pm (trusted list, call series config, issue template, labeler) and Forkcast (via the add-series skill). Use when a new facilitator wants to start running a breakout. Pairs with add-series, which covers…

Register a new protocol call series in Forkcast. Use when a brand-new series type needs to be added to the codebase (not just syncing new calls in an existing series).

Fix transcript/tldr typos for a published Forkcast call AND update the upstream ACDbot vocab so the same typo doesn't recur. Use when a call page on forkcast.org has wrong client/protocol/term names that the pipeline missed.

Run tests and generate reference tests. All testing goes through `make test`, never `pytest` directly. Always load this skill before running tests.

Write specifications. Always load this skill before writing to `specs`.

Review changes. Check that they are correct, consistent with the rest of the specifications, and compliant with the project's conventions. Always load this skill before reviewing changes.

Commit changes and open pull requests. Follow the project's conventions for scope, formatting, and writing style. Always load this skill before committing or opening a pull request.

Prepare for a new release. Perform checks to ensure that the release action can be started. Always load this skill before helping with a release.

Optimize measured finite-field arithmetic bottlenecks in Solidity verifiers using relevant algorithms and papers, explicit coefficient and overflow bounds, independent arithmetic references, and complete verifier validation.

Profile Solidity execution gas with Foundry harnesses, headless flamegraph parsing, and targeted optimized IR builds.

Refresh verifier gas calibration and affected schedule scores after Solidity or cost-model changes. Preserve measurement provenance, verify source fingerprints and receipt inputs, and regenerate reports with the repository's calibration gates.

Analyze optimized Solidity IR and assembly to explain gas regressions, repeated computation, stack spills, and inlining effects. Use when evaluating compiler-sensitive verifier optimizations and their deployed bytecode cost.

Measure verifier transaction gas with Anvil, preserve broadcast receipts, and compare baseline and candidate runs.

Build, adapt, and debug Semaphore V4 applications. Use when a user wants anonymous voting, anonymous feedback, group membership proofs, nullifier-based double-spend prevention, off-chain Semaphore proof generation, on-chain Semaphore group management, or…

Route, build, adapt, and debug Rate-Limiting Nullifier (RLN) applications. Use when a user wants privacy-preserving rate limits, anonymous chat or posting with spam deterrence, nullifier-based abuse detection, RLN registration/signaling/slashing flows, RLN V3…

Build, adapt, and debug TLSNotary agent workflows and TLSNotary Extension plugins. Use when a user wants to prove data from a web service with TLSNotary, create or review a TLSNotary extension plugin, find a JSON API endpoint to notarize, design selective…

Measure verifier transaction gas from Anvil broadcast artifacts.

Profile Solidity gas with Foundry flamegraphs and harness tests.

Batch review of open descriptor pull requests of the ERC-7730 registry. Approves the pending AI Review jobs, verifies every claim of the AI review comments against the descriptor and the tests, and against the contract source when in doubt, approves and…

Guardrail for AI-assisted scientific, mathematical, and formal work. Use when the user is proposing or refining novel theorems, scientific hypotheses, algorithms, or "breakthrough" ideas, especially after long LLM conversations. This skill detects red flags…

Use this skill when a user wants to generate, boot, verify, or extend a state-actor-produced Ethereum database. Covers --client, --spec, --target-size, per-client boot recipes (geth / reth / besu / nethermind / ethrex / erigon / nimbus), and the canonical…

Guides contributors through adding or updating a tool/resource in catalog/resources.json and choosing tags from catalog/taxonomy.json. Use when the user wants to add a new resource, suggest tags, or update an existing resource entry.