Install
$ agentstack add skill-bloomlabsinc-agent-skills-bloom ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Bloom
Bloom is a canvas of live React frames backed by a full app (a sandbox codebase + Convex backend). You reach it through the Bloom MCP (or the bloom CLI). Two things are true and easy to get wrong:
- Frames are not your repo. Canvas frames live at
@bloom-frame/and are React TSX rendered on the canvas.@/is the Bloom project's sandbox, not the repo your editor has open. - You don't write the plan in prose — you build it as a frame. Designing and planning happen on the canvas.
Orient first
Before any read/write, ground yourself with three calls (details in [bloom-mcp](../bloom-mcp/SKILL.md)):
whoami— token works? what can it reach?list_projects→list_branches→list_canvas_pages— pick the project, branch, and page you're working in.
If a step returns nothing or errors, stop and fix access before writing — don't guess IDs.
Which skill
- Calling MCP tools (
write_files,edit_files,code_search,trigger_agent, …) → [bloom-mcp](../bloom-mcp/SKILL.md): the tool model, guardrails, and the full catalog. - Planning a feature or iterating on a design → [
bloom-visual-planning](../bloom-visual-planning/SKILL.md): build the plan as a canvas frame and iterate visually with the user.
Install these skills
bunx skills add BloomLabsInc/agent-skills
Cross-agent (Claude Code, Cursor, Codex, …). The bloom CLI runs this for you on bloom init.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: BloomLabsInc
- Source: BloomLabsInc/agent-skills
- License: MIT
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.