setup
Set up or inspect a Multica workspace memory instance and its local binding.
Skill by junjiezhou1122
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/junjiezhou1122-setup
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.
About
Use cases: productivity
Reviews
Write a reviewNo 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. 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/setup
What's inside
- Skill name
setup- Description
- Set up or inspect a Multica workspace memory instance and its local binding. Use when onboarding an existing team to Multica Team; does not start task runs or enable automatic capture.
- License
- MIT
- Instructions
- 15 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Follow the [runtime guide](../../docs/runtimes.md) for client invocation, tool equivalents, and hook limits. # Set up workspace memory 1. Follow [company binding discovery](../../docs/multica-integration.md#discover-a-company-binding) to find an existing instance before preparing one. Resolve the target Multica server and full workspace UUID from the user or an existing binding. Inspect live CLI help and read workspace/project/agent state using explicit `--workspace-id`. If the user selects another company, respect that selection. Stop on ambiguous identity rather than using a switchable CLI default. 2. Read [the specification](../../SPEC.md) and [integration instructions](../../docs/multica-integration.md). Locate an existing instance first. Choose a persistent directory outside plugin code, contribution repos, and task checkouts. Verify runtime access. A remote runtime cannot use a console-only local path. 3. Prepare local operational binding from [the example](../../templates/binding.example.json). Place it outside the memory repository. Map actual agent/project IDs to stable safe keys. Resolve the maintainer. Preserve existing grants; default to local storage, explicit capture, preview feedback, and manual dreams. Public hosting or pushing needs an explicit target and grant. Do not put credentials in the binding. 4. Inspect the destination. For a nonexistent or empty directory, copy [the memory template](../../templates/memory), adjust member/project keys and indexes, initialize a separate Git repository, inspect the changes, and make an initial local commit. Reuse a clean existing repository whose Git top-level is exactly the destination and contains MEMORY.md. For any other nonempty destination, stop without overwriting. Do not set global Git identity. 5. Follow [actual instance validation](../../docs/instance-validation.md) to validate memory links and the binding. Confirm the workspace mapping and intended files. Report paths, grants, reachable runtimes, and remaining setup gaps. Installing these skills for Multica workers is a separate step under the user's authorization; use current `skill` and `agent skills` help, retain existing assignments, and read back attachments. When Team Ops company registration is part of the authorized setup, discover its existing entry and registry record first. Offer `memory_binding_path` in that local registration or entry, resolving relative paths from the entry directory. Verify the registration, entry, and binding identify the same server/workspace; preserve defaults, unrelated records, and existing grants. Use installed `/multica-team:mops` company discovery or an explicitly configured accessible Team Ops source, without assuming sibling plugin roots. Report an unwired company pointer as a setup gap. Completed setup means an identifiable instance and valid binding, not automatic reads in new sessions. Add a persistent instruction pointer to the binding for each authorized worker. Do not schedule dreams or run evaluation sessions during setup.
From junjiezhou1122/multica-team, MIT.
More from junjiezhou1122/multica-team
- 0.554score
dreaming
junjiezhou1122
Consolidate a Multica team's existing memory using specified task evidence.
SkillAFreshness: A★ 2Claude Code +9 - 0.552score
feedback
junjiezhou1122
Triage feedback about Multica Team, preview an upstream issue, or submit an authorized issue or reviewed fix PR.
SkillAFreshness: A★ 2Claude Code +9 - 0.532score
mops
junjiezhou1122
Use when the user wants to build, bootstrap, join, or operate an autonomous team of AI agents on Multica — you act as their Team Advisor (Executive Advisor)…
SkillAFreshness: A★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 7, 2026 (22 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/junjiezhou1122/multica-team
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from junjiezhou1122
- 0.580score
check
junjiezhou1122
Run the standalone offline validator for a native IdeaScientist run's artifacts, evidence receipts and stage dependencies.
SkillAFreshness: A★ 47Claude Code +9 - 0.580score
ideate
junjiezhou1122
Start a bounded native IdeaScientist run for a research problem, grounded gaps, one intuition and an independently reviewed proposal.
SkillAFreshness: A★ 47Claude Code +9 - 0.580score
evaluate
junjiezhou1122
Independently evaluate a native proposal with explained quality scores, coverage-limited novelty and a previously frozen blind baseline.
SkillAFreshness: A★ 47Claude Code +9 - 0.580score
resume
junjiezhou1122
Validate a saved native IdeaScientist run and continue its next admissible stage without resetting budgets or overwriting outputs.
SkillAFreshness: A★ 47Claude Code +9 - 0.574score
ideascientist-ideate
junjiezhou1122
Start automatic grounded scientific ideation for a research problem.
SkillAFreshness: A★ 47Claude Code +9 - 0.574score
ideascientist-check
junjiezhou1122
Check saved IdeaScientist artifacts using the canonical offline validator.
SkillAFreshness: A★ 47Claude Code +9
Cite this page
setup skill. Agent Mart. https://agentmart.dev/skills/junjiezhou1122-setup (last updated 2026-10-24)