renatocaliari/cali-interface-brainstorm
skills/renatocaliari/pi-product-workflow/cali-product-workflow/skills-workflow/cali-interface-brainstorm/SKILL.md
[Cali] Interface brainstorming skill. Use when generating interface proposals using the 5 archetypes method. Produces 5 independent proposals + hybrid recommendation. Part of cali-product-workflow but can be used standalone.
$ install --global
skillsauthnpx skillsauth add renatocaliari/agent-sync-public-skills cali-interface-brainstormInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 25, 2026, 4:22 AM276.6s7 files scanned
SKILL.md
- name:
- cali-interface-brainstorm
- description:
- >
Interface Brainstorming
Tools: See
references/cli-tools/subagents.mdfor subagent patterns.
Overview
This skill executes the Interface Brainstorming phase.
How to Load
This skill is bundled with cali-product-workflow — there is no standalone /skill: command.
Via Orchestrator (recommended)
The orchestrator reads this file directly when needed.
Standalone
To run standalone, see skills-workflow/cali-interface-brainstorm/SKILL.md for instructions and follow the instructions inline.
Process
Step 1: Read the references/ files to guide the process:
| File | Covers | When to read |
|---|---|---|
| references/interface-context.md | Progressive Clarification, when to use, system equivalents | Before starting |
| references/interface-reconstruction.md | Context reconstruction, hidden job extraction | Before generating |
| references/interface-rules.md | Separation Rule, Forced Trade-Off Rule, output quality | Before generating |
| references/archetypes.md | 5 archetypes with descriptions | During generation |
| references/hybrid-recommendation.md | Hybrid recommendation strategy | Step 3 only |
Generate Proposals (Step 1-2)
Step 1: Generate 5 proposals in parallel (5 independent workers):
subagent({
tasks: [
{ agent: "worker", task: `Generate Proposal A (Archetype A — Conventional Standard) for [product context]. Full format per references/output-format.md.` },
{ agent: "worker", task: `Generate Proposal B (Archetype B — Interaction Paradigm Shift) for [product context]. Full format per references/output-format.md.` },
{ agent: "worker", task: `Generate Proposal C (Archetype C — Technological Vanguard) for [product context]. Full format per references/output-format.md.` },
{ agent: "worker", task: `Generate Proposal D (Archetype D — Radical Simplicity) for [product context]. Full format per references/output-format.md.` },
{ agent: "worker", task: `Generate Proposal E (Archetype E — Expert/Command-First) for [product context]. Full format per references/output-format.md.` },
],
concurrency: 5,
context: "fork"
})
- Each worker generates one proposal (independent, no cross-contamination)
- Combined output:
.cali-product-workflow/{YYYY-MM-DD}/{_dir}/interfaces/interfaces_{v}.md
Step 2: see references/output-format.md for instructions to format and concatenate all proposals.
Generate Hybrid (Step 3 — AFTER proposals complete)
CRITICAL: Hybrid is generated AFTER all 5 proposals are complete to avoid bias.
agent parameter is REQUIRED — always use "worker":
subagent({
agent: "worker",
task: `Read the 5 proposals (A-E) from .cali-product-workflow/{YYYY-MM-DD}/{_dir}/interfaces/interfaces_{v}.md.
Then generate a **Hybrid Proposal** that combines the strongest elements from 2 or more archetypes.
Follow references/hybrid-recommendation.md for the strategy.
Append to the interfaces file.`,
reads: [`.cali-product-workflow/{YYYY-MM-DD}/{_dir}/interfaces/interfaces_{v}.md`]
})
Visual Review (Phase 8 Gate — Automatic)
After all proposals + Hybrid, use the Plannotator gate command (see references/cli-tools/plannotator.md for the correct CLI command). Execute it directly — do NOT describe it to the user.
Wait for the --gate result. If approved, automatically advance to Phase 9 (Interface Selection) — use Pattern 2 from references/cli-tools/structured-question.md to let the user pick one proposal. Do NOT just describe what comes next — execute it.
User Selection (Phase 9)
After visual review and approval, use Pattern 2 from ../../phases/ask-patterns.md to ask the user which proposal to follow.
Output
Interface proposals are saved to:
.cali-product-workflow/{YYYY-MM-DD}/{_dir}/interfaces/interfaces_{v}.md
Related Skills
- cali-shape-up: Produces the shaped proposal that feeds this phase
- cali-product-workflow (orchestrator): Coordinates this skill with other phases
Environment Adaptation
If a tool is unavailable, check:
../../../cali-product-workflow/references/cli-tools/
Related Skills
renatocaliari/cali-lat-md-seed
tools
VerifiedTrustedCommunity
Auto-initialize structured documentation for any project using lat.md (knowledge graph of markdown files with [[wiki links]], // @lat: code refs, and semantic search). Detects cali-product-workflow artifacts (spec-product.md, spec-tech.md, critiques) and uses them as seed material. Falls back to extracting business rules, architecture, and design decisions directly from the codebase. Use when a project lacks structured documentation or when lat.md/ is missing. After seeding, lat.md extension hooks keep documentation alive automatically.
1SKILL.mdUpdated Jun 2, 2026
renatocaliari/cali-ops-server-security
testing
VerifiedTrustedCommunity
[Cali] Server security audit and hardening for private servers behind Tailscale. Use when: auditing server security, hardening SSH/firewall/Docker, checking for vulnerabilities, setting up fail2ban, reviewing port exposure, or responding to security alerts. Covers 6 layers: CloudFlare, UFW, Tailscale, SSH, Docker, Application. Triggers: "server security", "security audit", "harden server", "SSH hardening", "firewall rules", "UFW config", "fail2ban", "port security", "Docker security", "vulnerability check", "security review".
1SKILL.mdUpdated May 30, 2026
renatocaliari/cali-ops-package-audit
tools
VerifiedTrustedCommunity
Run supply chain security scans before installing packages or before releases. Triggers when: user installs a package (npm, pip, go get, brew), user asks to 'scan dependencies', 'check vulnerabilities', 'supply chain', 'security audit', 'run trivy', 'run socket', or before any release/deployment. Also triggers on mentions of: socket.dev, trivy, OSV-scanner, dotenvx, CVE, dependency audit. Covers all four tools with concrete commands.
1SKILL.mdUpdated May 30, 2026
renatocaliari/cali-ops-docker-server-dashboard
tools
VerifiedTrustedCommunity
[Cali] - INTERACTIVE SKILL: Discover servers from ~/.ssh/config, auto-detect hosts (filtering out non-server entries like github.com), prompt user to pick one via question tool, then SSH into the chosen server and render a real-time ASCII dashboard with Docker containers, images, volumes, routes, cron, orphaned resources, and cleanup suggestions. REQUIRES question tool, SSH config parsing, and shell execution.
1SKILL.mdUpdated May 30, 2026