Install
$ agentstack add skill-ruesato-agent-skill-floreo-setup ✓ 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
floreo:setup
Embed a floreo auto-invoke rule in the current project's CLAUDE.md. After setup, agents in this project will use floreo automatically for any human-readable output — no explicit /floreo invocation needed.
Steps
- Check whether
CLAUDE.mdexists in the project root. If it doesn't,
note that you'll create it.
- Search the file for any existing floreo rule (grep for
floreo). If one
is already present, show it to the user and stop — no duplicate needed.
- Append the following block to CLAUDE.md (add a blank line before it if
the file doesn't end with one):
## floreo
Use the floreo skill whenever writing: a report, summary, analysis, research
brief, plan, proposal, retrospective, incident report, session-close summary,
or agent brief (when the receiver is human). Floreo turns these into polished
.html reading artifacts — do not write them as Markdown instead.
**Do NOT use floreo for**: any .md file the project or a tool expects
(README.md, CLAUDE.md, AGENTS.md, ONBOARDING.md, ADRs saved as Markdown,
etc.), skill or command definition files (SKILL.md, files in skills/ or
commands/), steering and config files for agents or tools, or content a
downstream agent or tool will parse as plain text.
Invoke the floreo skill before writing the final output file. The floreo skill
file contains the full design system, component library, and Content Plan
templates.
- Tell the user what you added and where. No further action needed — the
rule takes effect in the next session (or immediately, since CLAUDE.md is read at the start of each message).
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ruesato
- Source: ruesato/agent-skill-floreo
- 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.