Skip to content
Agentmart
Submit a tool

consult

A question, not a build: answered as an advisor, with nothing created in your workspace.

Skill by jamillazarev

IndexedApache-2.0★ 17
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/jamillazarev-consult

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

A question, not a build: answered as an advisor, with nothing created in your workspace.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/consult

What's inside

Skill name
consult
Description
A question, not a build: answered as an advisor, with nothing created in your workspace.
License
Apache-2.0
Instructions
14 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • name: missing

Files (1)

  • SKILL.md

SKILL.md (first lines)

Load and follow the **multica-ops** skill (`../mops/SKILL.md`), executing its `/multica-ops:consult` flow
(FLOWS.md → Consult). An advisory session: answer the owner's question as an advisor with a
**zero standing footprint** — create nothing that outlives the session, keep answers sourced
and evidence-tiered, spin research (and, on request, validation) sub-agents ephemerally, and
offer to persist or projectize only when the answer leads there.

**Optional addressee** — `/multica-ops:consult [who] <question>`: the contract is a property of the
conversation, so the default is **Mops** but any addressee answers under it. Name a **team agent**
(answers from its own craft), an **expert** (its own voice and sources), or the **theatre**
(personas react — direction-only, 🎭-marked, registered nowhere — but a consulted validated twin
still logs its own use per its consent contract, MODULES → Persona theatre). Route to the **one**
addressee, no fan-out. Args: $ARGUMENTS

From jamillazarev/multica-ops, Apache-2.0.

More from jamillazarev/multica-ops

Signals

Stars
17
Forks
1
Open issues
2
Last commit (this folder)
Sep 24, 2026 (1 month ago)
Last release
Sep 25, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
Repository
github.com/jamillazarev/multica-ops
Website
ai.jamillazarev.com/skills/multica-ops
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from jamillazarev

Cite this page

consult skill. Agent Mart. https://agentmart.dev/skills/jamillazarev-consult (last updated 2026-10-24)