skills/local/cali-product-workflow/skills-workflow/cali-shape-up/SKILL.md
[Cali] Shape Up product planning skill. Use when the user wants to shape a product proposal using the Shape Up method. Produces a shaped proposal with problem, solution, scope (IN/OUT), and risks. Part of the cali-product-workflow but can be used standalone.
npx skillsauth add renatocaliari/agent-sync-public-skills cali-shape-upInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Tools: See
references/cli-tools/subagents.mdfor subagent patterns.
This skill executes the Shape Up planning phase. It can be run:
/skill:cali-shape-up — for quick shaping sessions/skill:cali-product-workflowBefore shaping, launch subagent to map context:
subagent({
tasks: [
{
agent: "scout",
task: `Map the current code state related to: [description].
Identify relevant files, existing flows, and impact points.`,
output: ".cali-product-workflow/{YYYY-MM-DD}/{_dir}/context/current-state.md",
context: "fresh"
},
{
agent: "scout",
task: `Map technical risks, external dependencies, and
constraints for: [description].`,
output: ".cali-product-workflow/{YYYY-MM-DD}/{_dir}/context/risks.md",
context: "fresh"
}
],
concurrency: 2
})
Read the outputs before proceeding.
Read the references/ files to guide the process:
| File | Covers |
|---|---|
| references/shaping-complete.md | Context, clarification, responsibilities |
| references/shaping-principles.md | Core shaping principles |
| references/risk-analysis.md | Risk analysis and strategic alternatives |
| references/execution-guide.md | Sequencing, persistence, cross-domain adaptation |
| references/proposal-structure.md | Output structure for the shaped proposal |
| references/output-expectations.md | Strong vs weak output criteria |
Use ask_user_question for strategic questions when needed.
After shaping:
.cali-product-workflow/{YYYY-MM-DD}/{_dir}/plans/spec-product_{v}.mdAfter Shape Up, the workflow proceeds:
Shape Up
↓
Plan Critique (pre-flight check)
↓
Plannotator (Gate — visual approval)
↓
Scope Adjustment (ask) ← HERE scope happens
↓
Interface Brainstorming (if selected)
Note: Scope Adjustment comes AFTER Gate approval, not before.
This section executes after Plannotator Gate approval (not immediately after shaping).
When triggered by the orchestrator:
Show the IN/OUT scope table. Ask:
ask_user_question multiSelect with current IN scopesask_user_question multiSelect with OUT scope itemsask_user_question({
questions: [
{
question: "What should be REMOVED from IN scope? (select none to keep current)",
header: "Remove IN",
multiSelect: true,
options: [
{ label: "{IN scope item 1}", description: "{description}" },
{ label: "{IN scope item 2}", description: "{description}" }
]
},
{
question: "What should be ADDED to IN scope? (select none to keep current)",
header: "Add to IN",
multiSelect: true,
options: [
{ label: "{OUT scope item 1}", description: "{description}" },
{ label: "{OUT scope item 2}", description: "{description}" }
]
}
]
})
If user removes items: update spec
If user adds items: create spec-product_{v+1}.md (user is aware)
If user selects nothing: proceed without changes
Note: No Plannotator re-run — ask tool already confirms selections.
The shaped proposal is saved to:
.cali-product-workflow/{YYYY-MM-DD}/{_dir}/plans/spec-product_{v}.md
See references/proposal-structure.md for the expected output format.
If a tool is unavailable, check:
../../../cali-product-workflow/references/cli-tools/
development
PocketBase v0.39+ development - API rules, auth, collections, SDK, realtime, files, Go/JS extending, deployment, production tuning.
tools
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.
testing
[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".
tools
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.