New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Consume Hive

by ethereum in ethereum/execution-specs

Run locally filled fixtures against execution clients with a selected Hive simulator and a network client configuration from hive-tests.

CC0-1.0Auto-check passed

Install Consume Hive

skills CLI
$ npx skills add ethereum/execution-specs --skill consume-hive -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ethereum/execution-specs consume-hive --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ethereum/execution-specs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/consume-hive .claude/skills/consume-hive && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
consume-hive
GitHub stars
1.2k
Token cost
~1.7k tokens
SKILL.md length
692 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
CC0-1.0

At a glance

Run locally filled fixtures against execution clients with a selected Hive simulator and a network client configuration from hive-tests.

  • Testing clients against a devnet
  • SKILL.md covers Resolve inputs, Create a client YAML, Start Hive and Consume fixtures
  • Calls gh, uv and docker
  • Client releases in Hive

What it does

Consume Hive is an agent skill from ethereum/execution-specs. 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.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Specification for the Execution Layer. Tracking network upgrades. The licence is CC0-1.0.

When your agent uses it

  • Testing clients against a devnet
  • Client releases in Hive
  • Building a Hive client YAML

Example prompts

  • “/consume-hive”

Requirements

  • Docker

What it can do on your machine

Read from SKILL.md and the folder at commit 64cbead. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • uv
    • docker
    • bash

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Consume Hive loads about 1.7k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 692 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ethereum/execution-specs at commit 64cbead, republished under its CC0-1.0 licence (© ethereum). 692 words, ~1,693 tokens.

Download SKILL.mdSave it as .claude/skills/consume-hive/SKILL.md (or your agent's skills folder).
name
consume-hive
description
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.

Consume Hive

Usage:

/consume-hive <fixtures> <network|client.yaml|releases> <engine|enginex|rlp|sync>

Require all three inputs; ask for missing ones. Run only the selected simulator, with no simulator default. execute hive is intentionally left for a separate skill.

Resolve inputs

  • Fixtures: resolve the local fixture root, preserving its .meta data. Check that it contains fixtures for the selected simulator: engine uses blockchain_tests_engine, enginex uses blockchain_tests_engine_x, rlp uses blockchain_tests, and sync uses blockchain_tests_sync (generated by tests marked verify_sync). Report missing formats or an empty selection; do not substitute released fixtures. If filling is needed, use /fill-tests.

  • Network/client YAML: fetch a snapshot from the default branch of ethpandaops/hive-tests, pinned to its current commit; no clone is needed. The upstream files are usable as-is:

    bash
    REPO=repos/ethpandaops/hive-tests
REV=$(gh api "$REPO/commits/master" --jq .sha)
CONFIGS="$REPO/contents/.github/configs/hive"
gh api "$CONFIGS?ref=$REV" --jq '.[].name'
gh api "$CONFIGS/$NAME?ref=$REV" -H 'Accept: application/vnd.github.raw' \
  > "$RUN_DIR/client.yaml"

    For mainnet or generic, inspect .github/workflows/generic.yaml at $REV and use its default client_file (currently master.yaml, not generic.yaml). Otherwise, resolve the specified network name or YAML path against the listing above. If absent or ambiguous, show the available choices and ask; do not silently substitute another devnet. Record $REV with the saved YAML. Preserve its client list, image tags, and build arguments.

  • Client releases: hive-tests has no file for client release images. When the user asks for releases or a public network (for example Sepolia or mainnet releases), create a client YAML instead.

Create a client YAML

For the file format, see Client configuration. Unless the user names other clients, use the clients in hive-tests' master.yaml. Write the file to $RUN_DIR/client.yaml with one entry per client, nametag: release, and build_args set to the release image:

yaml
- client: go-ethereum
  nametag: release
  build_args:
    baseimage: ethereum/client-go
    tag: <release-tag>
ClientRelease repositoryImageTag format
besubesu-eth/besuhyperledger/besurelease tag
erigonerigontech/erigonerigontech/erigonrelease tag
ethrexlambdaclass/ethrexghcr.io/lambdaclass/ethrexno v prefix
go-ethereumethereum/go-ethereumethereum/client-gorelease tag
nethermindNethermindEth/nethermindnethermind/nethermindrelease tag
nimbus-elstatus-im/nimbus-eth1statusim/nimbus-eth1release tag
rethparadigmxyz/rethghcr.io/paradigmxyz/rethrelease tag

Resolve each tag with gh api repos/<release-repository>/releases/latest --jq .tag_name, then check the image exists with docker buildx imagetools inspect <image>:<tag> before starting Hive. If a check fails, stop and report it; do not fall back to another tag.

  • Always set build_args. Hive's default Dockerfiles mostly build development branches (for example Besu develop, Nethermind master), so an entry without them does not test a release.
  • Never use latest or another moving tag.
  • Report the file as generated locally, not from hive-tests, list each client's release tag, and offer to upstream it to hive-tests.
Show full SKILL.md (308 more words)Show less

Start Hive

Use a built ethereum/hive checkout and a fresh run directory for logs and reports. For environment and platform setup, see Hive dev mode.

From the Hive root, start a dedicated server on an unused localhost port:

bash
./hive --dev --dev.addr "127.0.0.1:$HIVE_PORT" \
  --client-file "$CLIENT_YAML" \
  --docker.pull --docker.nocache '^hive/clients/' --docker.buildoutput \
  --results-root "$RUN_DIR/hive-results"

Always enable --docker.pull to refresh base images; --docker.nocache also rebuilds client wrappers. The rebuild runs for every client on each start, so expect a slow start with a large YAML. A failed pull is not permission to use stale images. Do not add a client filter unless requested. Record the server PID, wait for its API, and verify /clients contains the YAML's clients. Capture build logs and image IDs/digests: mutable tags alone do not identify what was tested.

Consume fixtures

Run from execution-specs with HIVE_SIMULATOR pointing to this server. Choose worker count for the host (four is a reasonable start). Set these options:

SimulatorAdditional consume options
engine--disable-strict-exception-matching=nimbus-el
enginex--disable-strict-exception-matching=nimbus-el
rlpNone
syncNone

The Nimbus exception matches the Engine/EngineX Dockerfile defaults tracked in issue #3603. Native commands do not inherit those defaults. Keep invalid-payload rejection checks enabled and other clients' exception matching strict; do not skip negative tests. RLP import does not verify Engine API rejection messages.

sync parametrizes both source and syncing clients from the YAML, running client pairs. Account for the extra containers when choosing workers and report results per pair.

Put the selected options above in a Bash array SIMULATOR_ARGS, then run the commands below with Bash. If the shell is not Bash (for example fish), wrap them in bash -c:

bash
export HIVE_SIMULATOR="http://127.0.0.1:$HIVE_PORT"
uv run consume "$SIMULATOR" --input "$FIXTURES" \
  "${SIMULATOR_ARGS[@]}" -n "$WORKERS" --timing-data \
  --html "$RUN_DIR/report.html" --junitxml "$RUN_DIR/report.xml"

Preserve command output, exit status, and Hive logs. Report per-client pass/fail/skip/error counts, fixture scope, commands, repository revisions, client versions/images, and report paths. Distinguish infrastructure failures from test failures; an empty run is not a pass. Diagnose failures without weakening fixture expectations. Stop only the Hive process started for this run and retain its evidence.

© ethereum, CC0-1.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/consume-hive of ethereum/execution-specs.

Open the folder on GitHubat commit 64cbead

Compare with similar skills

Consume Hive next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Consume Hive compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Consume Hive this skillethereum/execution-specs1.2k—~1.7kAutomated safety check: PassCC0-1.0
Consuming Endpoints From Client CodePostHog/posthog40k—~3.3kAutomated safety check: PassCustom licence
LocalizeDonchitos/Claude-Code-Game-Studios26k—~5.2kAutomated safety check: NotesMIT
SEO LocalAgriciDaniel/claude-seo19k—~4.5kAutomated safety check: PassMIT
Local Legal SEO Auditsickn33/agentic-awesome-skills47k2 repos~3.2kAutomated safety check: PassMIT
Translating LocalesTriliumNext/Trilium38k—~3kAutomated safety check: PassAGPL-3.0

Similar skills

  • Consuming Endpoints From Client Code

    PostHog/posthog

    Official

    Wire a PostHog endpoint into a client app or SDK. An agent skill from PostHog/posthog.

    40k GitHub stars~3.3k tokensUpdated today
    Backend & APIsAuto-check passed

  • Localize

    Donchitos/Claude-Code-Game-Studios

    Localization pipeline — find hardcoded strings, extract string tables, cultural review, VO, RTL, enforce string freeze.

    26k GitHub stars~5.2k tokensUpdated 2 days ago
    Frontend & DesignAuto-check: notes

  • SEO Local

    AgriciDaniel/claude-seo

    Audit local SEO, including Google Business Profile, NAP consistency, citations, reviews, local schema, location pages, and multi-location structure.

    19k GitHub stars~4.5k tokensUpdated 5 days ago
    Marketing & SEOAuto-check passed

  • Local Legal SEO Audit

    sickn33/agentic-awesome-skills

    Audit and improve local SEO for law firms, attorneys, forensic experts and legal/professional services sites with local presence, focusing on GBP, directories, E-E-A-T and practice/location pages.

    47k GitHub starsUsed in 2 repos~3.2k tokens
    Marketing & SEOAuto-check passed

  • Translating Locales

    TriliumNext/Trilium

    A skill your agent uses when filling in or improving a lagging UI translation locale in Trilium (e.g.

    38k GitHub stars~3k tokensUpdated today
    Writing & ContentAuto-check passed

  • Local LLM Expert

    sickn33/agentic-awesome-skills

    Master local LLM inference, model selection, VRAM optimization, and local deployment using Ollama, llama.cpp, vLLM, and LM Studio.

    47k GitHub starsUsed in 2 repos~1.6k tokens
    AI & LLM EngineeringAuto-check passed

More from ethereum/execution-specs

All 13 skills in this repo

  • Eip Checklist

    ethereum/execution-specs

    Track EIP test coverage with the repository checklist system.

    1.2k GitHub stars~804 tokensUpdated today
    Auto-check passed

  • Fill Tests

    ethereum/execution-specs

    Fill test fixtures with the repository fill command. An agent skill from ethereum/execution-specs.

    1.2k GitHub stars~793 tokensUpdated today
    Auto-check passed

  • Grammar Check

    ethereum/execution-specs

    Audit grammar in documentation and code comments. An agent skill from ethereum/execution-specs.

    1.2k GitHub stars~424 tokensUpdated today
    Auto-check passed

  • Implement Eip

    ethereum/execution-specs

    Implement EIP specification changes using repository conventions.

    1.2k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Pytester

    ethereum/execution-specs

    Write and run isolated pytester-based plugin tests. An agent skill from ethereum/execution-specs.

    1.2k GitHub stars~403 tokensUpdated today
    Auto-check passed

  • Write Docstring

    ethereum/execution-specs

    Write specification docstrings using repository conventions.

    1.2k GitHub stars~2.6k tokensUpdated today
    Auto-check passed

Questions about Consume Hive

What does Consume Hive do?

Run locally filled fixtures against execution clients with a selected Hive simulator and a network client configuration from hive-tests. Consume Hive is an agent skill from ethereum/execution-specs. Run locally filled fixtures against execution clients with a selected Hive simulator and a network client configuration from hive-tests.

When should I use Consume Hive?

Consume Hive fits situations like: testing clients against a devnet; client releases in Hive; building a Hive client YAML.

How do I install Consume Hive in Claude Code?

Run `npx skills add ethereum/execution-specs --skill consume-hive -a claude-code`. Or copy the skill folder (.agents/skills/consume-hive in ethereum/execution-specs) into .claude/skills/consume-hive in your project. Claude Code loads it when a task matches its description.

How do I install Consume Hive in Codex?

Run `npx skills add ethereum/execution-specs --skill consume-hive -a codex`. Or copy the skill folder (.agents/skills/consume-hive in ethereum/execution-specs) into .agents/skills/consume-hive in your project. Codex loads it when a task matches its description.

Can I use Consume Hive in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ethereum/execution-specs --skill consume-hive -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/consume-hive, .gemini/skills/consume-hive, .github/skills/consume-hive and .opencode/skills/consume-hive in your project.

What does Consume Hive need to run?

Going by SKILL.md and its folder, Consume Hive needs the command-line tools its instructions call (gh, uv, docker and bash). Our summary lists: Docker.

Does Consume Hive access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Consume Hive safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Consume Hive use?

Consume Hive is published under the CC0-1.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Consume Hive use?

About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Consume Hive?

Skills that share tags, products or a category with Consume Hive: Consuming Endpoints From Client Code (PostHog/posthog, 40k stars), Localize (Donchitos/Claude-Code-Game-Studios, 26k stars), SEO Local (AgriciDaniel/claude-seo, 19k stars) and Local Legal SEO Audit (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Consume Hive?

ethereum (a GitHub organization) maintains it in ethereum/execution-specs, which has 1,196 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 10, 2026.

Source: ethereum/execution-specs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.