Agent skill

Consult Claude

by EpicenterHQ in EpicenterHQ/epicenter

Assign Claude Code a read-only investigation, recommendation, or finished text draft.

Custom licenceAuto-check passedMedia & Creative

Install Consult Claude

skills CLI
$ npx skills add EpicenterHQ/epicenter --skill consult-claude -a claude-code

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

GitHub CLI
$ gh skill install EpicenterHQ/epicenter consult-claude --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/EpicenterHQ/epicenter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/consult-claude .claude/skills/consult-claude && 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
consult-claude
GitHub stars
4.8k
Token cost
~2k tokens
SKILL.md length
1,004 words
Files
4 (incl. scripts, references)
Skills in repo
65
Repo updated
First seen
Licence
Custom licence

At a glance

Assign Claude Code a read-only investigation, recommendation, or finished text draft.

  • Asked to consult Claude
  • SKILL.md covers Define the result, Make the design legible, Send a brief and Adjudicate and continue
  • Runs TypeScript scripts from its folder; calls claude and bun
  • A design-review workflow includes Claude

What it does

Consult Claude is an agent skill from EpicenterHQ/epicenter. Assign Claude Code a read-only investigation, recommendation, or finished text draft. Use when asked to consult Claude or when a design-review workflow includes Claude. Completed edits and executable experiments belong to delegate-claude.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/example-workflow.md`, `scripts/consult-claude.test.ts` and `scripts/consult-claude.ts`).

It sits in Media & Creative, covering Design review and critique. The repository describes itself as: Open-source, local-first apps.

When your agent uses it

  • Asked to consult Claude
  • A design-review workflow includes Claude

Example prompts

  • “/consult-claude”

Requirements

  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit 5b4bb69. 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

    Ships 2 files in scripts/ (TypeScript), which the agent can run.

    Shell commands in SKILL.md call:

    • claude
    • bun

    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):

    • code.claude.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

Consult Claude loads about 2k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 63 tokens; SKILL.md has 1,004 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.9k

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); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,004 words (~1,996 tokens).

“Claude owns a bounded answer: an investigation, recommendation, caller map, API example, migration assessment, or finished text draft. Codex owns the conversation, execution, verification, and integration. Use delegate-claude when Claude should own edits or run an experiment.”

— opening of SKILL.md by EpicenterHQ, Custom licence
name
consult-claude

Read the full SKILL.md on GitHub

Files

SKILL.md and 3 other files (scripts, references) in .agents/skills/consult-claude of EpicenterHQ/epicenter.

  • SKILL.md
  • references/example-workflow.md
  • scripts/consult-claude.test.ts
  • scripts/consult-claude.ts

Open the folder on GitHubat commit 5b4bb69

Compare with similar skills

Consult Claude 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.

Consult Claude compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Consult Claude this skillEpicenterHQ/epicenter4.8k—~2kAutomated safety check: PassCustom licence
System Atlasinkboard/system-atlas430—~2.3kAutomated safety check: PassMIT
Design Image Studiokangarooking/design-image-studio102—~1.5kAutomated safety check: PassMIT
Kicad Reviewmixelpixx/Konnect927—~3.2kAutomated safety check: PassAGPL-3.0
Design AuditUniClipboard/UniClipboard1.9k—~554Automated safety check: PassAGPL-3.0
L1 AI Design ReviewPaperMoonuu/Design-workflow-skills316—~492Automated safety check: PassNone

Similar skills

  • System Atlas

    inkboard/system-atlas

    Build and maintain an explorable, progressively-disclosed isometric "atlas" of a system's architecture — an interactive page (hover to read, click to pin, go inside for steps, moving data packets…

    430 GitHub stars~2.3k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Design Image Studio

    kangarooking/design-image-studio

    Directly generate design-oriented AI images with strong creative direction and prompt engineering.

    102 GitHub stars~1.5k tokensUpdated 5 mo ago
    Media & CreativeAuto-check passed
  • Kicad Review

    mixelpixx/Konnect

    Design review and validation workflow for KiCAD projects via MCP tools.

    927 GitHub stars~3.2k tokensUpdated 4 days ago
    Media & CreativeAuto-check passed
  • Design Audit

    UniClipboard/UniClipboard

    定期审计代码库的工程设计问题(高心智复杂度、单一真相源被破坏、catch-all 胖接口、死代码、散落魔法字面量、泄漏抽象、资源生命周期靠环形缓冲)与可优化点,范围限定为自上次审计以来的 git churn,每条发现都落到 file:line 并对照本项目自己的 VISION.md / 各级 AGENTS.md / memory…

    1.9k GitHub stars~554 tokensUpdated today
    Media & CreativeAuto-check passed
  • L1 AI Design Review

    PaperMoonuu/Design-workflow-skills

    L1 × AI 设计评审:对已完成的单页、局部 UI 设计稿进行小型迭代评审,识别影响面、状态遗漏、文案与一致性风险,并给出 P0/P1/P2 建议和验收清单。用户提供 Figma 链接、截图、前后设计稿或可评审原型,并要求设计走查、风险评审或开发前 UI 检查时使用;不用于设计前方案预检、完整多页面流程或 L2 开发交付。

    316 GitHub stars~492 tokensUpdated 18 days ago
    Media & CreativeAuto-check passed
  • Gpui Kit Design Guides

    StudentWeis/ropy

    The normative Design Guides for GPUI Kit desktop applications.

    194 GitHub starsUsed in 1 repo~1.1k tokens
    Media & CreativeAuto-check passed

More from EpicenterHQ/epicenter

All 65 skills in this repo
  • Agent Instructions

    EpicenterHQ/epicenter

    Write and maintain repository guidance across AGENTS.md, CLAUDE.md, and .agents/skills.

    4.8k GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed
  • Better Auth security hardening: rate limits, secrets, CSRF, trusted origins, cookies, sessions, OAuth tokens, and audit logging.

    4.8k GitHub stars~896 tokensUpdated 2 days ago
    Auto-check passed
  • Cohesion Over Testability

    EpicenterHQ/epicenter

    Collapse test-shaped production boundaries while preserving behavior and coverage.

    4.8k GitHub stars~2k tokensUpdated 2 days ago
    Auto-check passed
  • Collapse Pass

    EpicenterHQ/epicenter

    Remove indirection that does not earn its boundary across a diff or package.

    4.8k GitHub stars~2k tokensUpdated 2 days ago
    Auto-check passed
  • Error Handling

    EpicenterHQ/epicenter

    Apply Wellcrafted Result patterns to fallible operations and preserve failures at boundaries.

    4.8k GitHub stars~1.4k tokensUpdated 2 days ago
    Auto-check passed
  • Factory Function Composition

    EpicenterHQ/epicenter

    Factory function patterns to compose clients and services. An agent skill from EpicenterHQ/epicenter.

    4.8k GitHub stars~3k tokensUpdated 2 days ago
    Auto-check passed

Questions about Consult Claude

What does Consult Claude do?

Assign Claude Code a read-only investigation, recommendation, or finished text draft. Consult Claude is an agent skill from EpicenterHQ/epicenter. Assign Claude Code a read-only investigation, recommendation, or finished text draft.

When should I use Consult Claude?

Consult Claude fits situations like: asked to consult Claude; A design-review workflow includes Claude.

How do I install Consult Claude in Claude Code?

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

How do I install Consult Claude in Codex?

Run `npx skills add EpicenterHQ/epicenter --skill consult-claude -a codex`. Or copy the skill folder (.agents/skills/consult-claude in EpicenterHQ/epicenter) into .agents/skills/consult-claude in your project. Codex loads it when a task matches its description.

Can I use Consult Claude 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 EpicenterHQ/epicenter --skill consult-claude -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/consult-claude, .gemini/skills/consult-claude, .github/skills/consult-claude and .opencode/skills/consult-claude in your project.

What does Consult Claude need to run?

Going by SKILL.md and its folder, Consult Claude needs TypeScript for the scripts in its folder and the command-line tools its instructions call (claude and bun). Our summary lists: Node.js.

Does Consult Claude access the network?

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

Is Consult Claude 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Consult Claude use?

Consult Claude has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Consult Claude use?

About 2k tokens (SKILL.md is roughly 8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.9k tokens, read only when the agent opens those files.

What are the alternatives to Consult Claude?

Skills that share tags, products or a category with Consult Claude: System Atlas (inkboard/system-atlas, 430 stars), Design Image Studio (kangarooking/design-image-studio, 102 stars), Kicad Review (mixelpixx/Konnect, 927 stars) and Design Audit (UniClipboard/UniClipboard, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Consult Claude?

EpicenterHQ (a GitHub organization) maintains it in EpicenterHQ/epicenter, which has 4,822 GitHub stars. The repository holds 65 skills in this directory. The repository was last updated on October 8, 2026.

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