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

Consult

by raine in raine/consult-llm

Consult an external LLM with the user's query. An agent skill from raine/consult-llm.

MITAuto-check: notesAgent Workflows

Install Consult

skills CLI
$ npx skills add raine/consult-llm --skill consult -a claude-code

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

GitHub CLI
$ gh skill install raine/consult-llm consult --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/raine/consult-llm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/consult .claude/skills/consult && 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
GitHub stars
139
Token cost
~963 tokens
SKILL.md length
530 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Consult an external LLM with the user's query. An agent skill from raine/consult-llm.

  • Works in 5 steps: Load consult-llm skill → Gather context → Invoke → …
  • Agent Workflows work in your project
  • SKILL.md covers Available models, Argument handling, Workflow and Critical rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Consult is an agent skill from raine/consult-llm. Consult an external LLM with the user's query.

Its SKILL.md is about 960 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows. The repository describes itself as: Get a second opinion from another AI model. The licence is MIT.

When your agent uses it

  • Agent Workflows work in your project

Example prompts

  • “/consult”

Requirements

  • Pre-approved tools (allowed-tools): Bash, Glob, Grep, Read

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Load consult-llm skill
  2. Gather context
  3. Invoke
  4. Resolve context requests
  5. Present results

What it can do on your machine

Read from SKILL.md and the folder at commit 69e3ecb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Glob
    • Grep
    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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 loads about 963 tokens when it runs. Until then it costs about 14 tokens; SKILL.md has 530 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~14
When it runs · the whole SKILL.md, loaded when a task matches
~963

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Glob, Grep, Read

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 raine/consult-llm at commit 69e3ecb, republished under its MIT licence (© raine). 530 words, ~963 tokens.

Download SKILL.mdSave it as .claude/skills/consult/SKILL.md (or your agent's skills folder).
name
consult
description
Consult an external LLM with the user's query.
allowed-tools
Bash, Glob, Grep, Read

Consult an external LLM with the user's query via the consult-llm CLI.

Load the consult-llm skill before invoking — it defines the invocation contract (stdin heredoc, flags, output format, multi-turn). Do not call the CLI without loading it first.

Available models

Selectors resolvable in this environment (depends on configured API keys):

!`consult-llm models`

Argument handling

Arguments: $ARGUMENTS

Check $ARGUMENTS for flags:

Model flags: any --<selector> from the Models block above selects that model (e.g. --gemini, --openai, --deepseek, --minimax). Repeat for multiple models — they run in parallel.

Translate model flags according to the loaded consult-llm skill's model-selection rules.

Mode flags:

  • --browser → use web mode (--web, copies prompt to clipboard)
  • --background → run the Bash call in background mode (run_in_background)

Strip all flags from the arguments to get the user query.

Workflow

0. Load consult-llm skill

Load it now. Follow its invocation contract for all CLI calls in this workflow.

1. Gather context
  • Use Glob/Grep to find relevant files.
  • Read key files to confirm relevance.
  • Do enough research to understand how the requested behavior actually works. Before starting, think about what resources would be useful to obtain first: relevant source files, tests, logs, generated files, config, examples, command output, external docs, or authoritative upstream source. Gather the cheapest useful evidence before consulting.
  • Do not stop at the first plausible file, definition, setting, or example. Follow references, callers, related tests, and runtime usage until you can explain the current behavior and the likely impact of changing it.
  • Select files that let reviewers understand the behavior being discussed and verify your assumptions.
2. Invoke

One or more --<selector> flags — single call with one -m <selector> per flag, plus -f <path> for each relevant file. Multiple selectors run in parallel and the CLI returns a combined response with per-model sections.

No model flag (default) — use the loaded consult-llm skill's default model-selection rules, plus -f <path> for each relevant file.

--browser — single call with --web (model flags are ignored in web mode).

Show full SKILL.md (208 more words)Show less
3. Resolve context requests

Before using the response, apply the loaded consult-llm skill's context request loop. If an answer ends with a context request, resume that model independently with the requested evidence and treat its revised answer as the consultation result.

4. Present results
  • Normal mode (single model): summarize key insights, recommendations, and considerations.
  • Normal mode (multiple models): the CLI output already contains labeled per-model sections. Synthesize by highlighting agreements, noting disagreements, and presenting a unified takeaway.
  • Web mode: inform the user the prompt was copied to clipboard and ask them to paste it into their browser-based LLM and share the response back.

Critical rules

  • ALWAYS gather file context before consulting.
  • Pass through the user's query faithfully — do NOT add your own theories, suspects, analysis, or suggested solutions to the prompt. The user's intent is the prompt. Rephrase as needed so the prompt reads as a direct question to the LLM, not a meta-instruction to you. You may add brief factual context (e.g. "we recently changed X to Y"), but never inject your own diagnostic opinions or hypotheses. Do not pass the user's query verbatim if it is phrased as an instruction to you rather than a question for the LLM.
  • Provide focused, relevant files (quality over quantity).

© raine, MIT. 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 skills/consult of raine/consult-llm.

Open the folder on GitHubat commit 69e3ecb

Compare with similar skills

Consult 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Consult this skillraine/consult-llm139—~963Automated safety check: NotesMIT
MCP Server Builderanthropics/skills180k64 repos~2.3kAutomated safety check: PassApache-2.0
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official38k11 repos~4.1kAutomated safety check: NotesApache-2.0
Using Superpowersfarm-fe/farm5.6k35 repos~1.4kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers296k2 repos~5.1kAutomated safety check: PassMIT
Claude Code Agent Developmentanthropics/claude-plugins-official38k8 repos~2.8kAutomated safety check: PassApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 64 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • Hook Development for Claude Code Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.

    38k GitHub starsUsed in 11 repos~4.1k tokens
    Agent WorkflowsAuto-check: notes

  • Using Superpowers

    farm-fe/farm

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    5.6k GitHub starsUsed in 35 repos~1.4k tokens
    Agent WorkflowsAuto-check passed

  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    296k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 8 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    795 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed

More from raine/consult-llm

All 12 skills in this repo

  • Implement

    raine/consult-llm

    Explicit workflow for one bounded implementation using source-grounded discovery, a walking slice, evidence-gated review, validation, and commit.

    139 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check: notes

  • Collab

    raine/consult-llm

    Multiple LLMs collaboratively brainstorm solutions, building on each other's ideas across rounds.

    139 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed

  • Collab Vs

    raine/consult-llm

    The agent brainstorms with a partner LLM in alternating turns, building on each other's ideas.

    139 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed

  • Consult LLM

    raine/consult-llm

    How to invoke the consult-llm CLI. An agent skill from raine/consult-llm.

    139 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check: notes

  • Debate

    raine/consult-llm

    LLMs propose and critique approaches, agent moderates the debate and synthesizes the best solution, then implements.

    139 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed

  • Debate Vs

    raine/consult-llm

    The agent debates an opponent LLM through a multi-turn conversation, then synthesizes the best approach and implements.

    139 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Consult

What does Consult do?

Consult an external LLM with the user's query. An agent skill from raine/consult-llm. Consult is an agent skill from raine/consult-llm. Consult an external LLM with the user's query.

When should I use Consult?

Consult fits situations like: agent Workflows work in your project.

How do I install Consult in Claude Code?

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

How do I install Consult in Codex?

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

Can I use Consult 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 raine/consult-llm --skill consult -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, .gemini/skills/consult, .github/skills/consult and .opencode/skills/consult in your project.

What does Consult need to run?

SKILL.md names no scripts, command-line tools or credentials: Consult is instructions for the agent only. Its frontmatter pre-approves these tools: Bash, Glob, Grep, Read.

Does Consult access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Consult safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Consult use?

Consult is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Consult use?

About 963 tokens (SKILL.md is roughly 3.9k 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 Consult?

Skills that share tags, products or a category with Consult: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 296k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Consult?

raine (a GitHub user) maintains it in raine/consult-llm, which has 139 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 7, 2026.

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