AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL unreviewed Apache-2.0 Self-run

Loom

skill-yassimba-loom-loom · by Yassimba

Set up or troubleshoot Yassimba's curated setup through the loom CLI — exact-pinned tools via mise, agent-scoped global or project skills, Pi packages. Use when the user asks to install this collection, add a capability for one or more agents, install a skill globally or in the current project, scaffold AGENTS.md, update or sync the setup, or diagnose installation problems.

↗ Repository
— No reviews yet
0 installs
0 views
— view→install

Install

$ agentstack add skill-yassimba-loom-loom

Open-source listing, not yet scanned by AgentStack. Follow the source repository for install instructions.

Security review

⚠ Flagged

1 finding(s); flagged for manual review. · v0.1.0 How review works →

  • • Prompt-injection patterns
  • • Secret / credential exfiltration
  • • Dangerous shell & filesystem operations
  • • Untrusted network calls
  • • Known-malicious package signatures
  • high Pipes remote content directly into a shell (remote code execution).

What it can access

  • ● Network access Used
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Reliability & compatibility

— Not yet reviewed
0 installs to date
— no reviews yet
● yesterday

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Loom? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Loom

The loom CLI is the single setup interface: it syncs exact-pinned tools through mise, copies skills into Claude, Agents, Codex, Pi, and OpenCode trees itself, and delegates Pi packages to Pi. Every install goes through it — the CLI is the installer.

Start

Check whether the CLI is available:

loom --version

If the command fails or is not found, treat the CLI as not installed: explain that the bootstrap installs mise, syncs the pinned core (node and the loom CLI), and hands off to the guided setup — then ask before running the platform command.

macOS or Linux:

curl -fsSL https://raw.githubusercontent.com/Yassimba/loom/main/install.sh | sh

Windows:

powershell -NoProfile -ExecutionPolicy Bypass -Command "irm https://raw.githubusercontent.com/Yassimba/loom/main/install.ps1 | iex"

Workflows

  • Guided setup (bare loom does the same): loom setup
  • Add capabilities by name: loom add --tool --skill --pi-package
  • Target skill agents: repeat --agent claude|agents|codex|pi|opencode; omit it to use detected agents
  • Choose skill scope: --scope global|project (default: global; project resolves the current Git worktree)
  • Scaffold this project's AGENTS.md + CLAUDE.md: loom init (run inside the project; --python / --rust skip the prompts)
  • Refresh every initialized project's AGENTS.md from the templates: loom sync
  • Update everything — tool pins, Pi package pins, skills, projects, the CLI itself: loom update
  • Check the installation: loom status

Without resource-selection flags, setup and add open a full-screen wizard that needs a real terminal. From an agent, pass resource flags plus any requested --agent and --scope values (inspect loom add --help for the current names), then preview safely with --dry-run.

Before a command that installs or updates, show what will run and ask for confirmation. status and --dry-run are read-only and may run without asking.

Done when: every requested resource is confirmed by the CLI's own output, reported verbatim — a failed or skipped resource is reported as exactly that.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills