aws-samples/sample-kiro-cli-prompts-for-product-teams
No description.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit aws-samples/sample-kiro-cli-prompts-for-product-teams/.claude ./rig-sample-kiro-cli-prompts-for-product-teams # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit aws-samples/sample-kiro-cli-prompts-for-product-teams/.claude/skills/product-ai-framing .claude/skills/product-ai-framing $ npx degit aws-samples/sample-kiro-cli-prompts-for-product-teams/.claude/skills/product-prd .claude/skills/product-prd $ npx degit aws-samples/sample-kiro-cli-prompts-for-product-teams/.claude/skills/product-prfaq .claude/skills/product-prfaq $ npx degit aws-samples/sample-kiro-cli-prompts-for-product-teams/.claude/skills/product-prototype .claude/skills/product-prototype $ npx degit aws-samples/sample-kiro-cli-prompts-for-product-teams/.claude/skills/product-research .claude/skills/product-research $ npx degit aws-samples/sample-kiro-cli-prompts-for-product-teams/.claude/skills/regenerate-screen-index .claude/skills/regenerate-screen-index
$ curl -fsSL --create-dirs -o .claude/agents/ai-framing.md https://raw.githubusercontent.com/aws-samples/sample-kiro-cli-prompts-for-product-teams/main/.claude/agents/ai-framing.md $ curl -fsSL --create-dirs -o .claude/agents/deep-research.md https://raw.githubusercontent.com/aws-samples/sample-kiro-cli-prompts-for-product-teams/main/.claude/agents/deep-research.md $ curl -fsSL --create-dirs -o .claude/agents/design-system.md https://raw.githubusercontent.com/aws-samples/sample-kiro-cli-prompts-for-product-teams/main/.claude/agents/design-system.md $ curl -fsSL --create-dirs -o .claude/agents/prd.md https://raw.githubusercontent.com/aws-samples/sample-kiro-cli-prompts-for-product-teams/main/.claude/agents/prd.md $ curl -fsSL --create-dirs -o .claude/agents/prfaq.md https://raw.githubusercontent.com/aws-samples/sample-kiro-cli-prompts-for-product-teams/main/.claude/agents/prfaq.md $ curl -fsSL --create-dirs -o .claude/agents/product-reviewer.md https://raw.githubusercontent.com/aws-samples/sample-kiro-cli-prompts-for-product-teams/main/.claude/agents/product-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/screen-builder.md https://raw.githubusercontent.com/aws-samples/sample-kiro-cli-prompts-for-product-teams/main/.claude/agents/screen-builder.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (6)
Subagents (7)
| ai-framing model: inherit | Use for the AI Framing phase (AI/ML products ONLY) — ML problem framing, input/output schemas, evaluation metrics with thresholds, and data strategy. Dispatch after Deep Market Research is approved an |
| deep-research model: inherit | Use for the Deep Market Research phase — 6 parallel research dimensions, competitor/persona/tech-radar analysis, source validation, and the MarketResearch_*.html brief. Dispatch when starting product |
| design-system model: inherit | Use at the START of the Prototype phase to create the shared [product-slug].css and DesignSystem_*.html visual reference, and to extract the Design Token Contract — BEFORE any Screen_*.html is built. |
| prd model: inherit | Use for the PRD phase — EARS-syntax requirements, personas with dashboard widgets, success metrics, AWS-native technical architecture WITH an inline SVG diagram, and current-year technology research. |
| prfaq model: inherit | Use for the PRFAQ phase — Amazon Working Backwards press release + skeptical FAQ, grounded in the market research brief. Dispatch after research is approved and the user wants the PRFAQ. |
| product-reviewer model: inherit | Use to run a review lens over completed artifacts — accessibility (WCAG AA), full-interactivity/link audit, risk analysis, or competitive response. Dispatch when the user asks to audit, stress-test, o |
| screen-builder model: inherit | Use to build ONE prototype screen file (Screen_*.html) from a screen-builder contract during the Prototype phase. The Orchestrator dispatches one per screen, in parallel. Each invocation builds exactl |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| PostToolUse | Write|Edit | f=$(perl -ne 'print "$1" if /"file_path"\s*:\s*"((?:[^"\\]|\\.)+)"/'); t="/tmp/__pmpm_hk.$$"; jschk(){ if command -v osascript >/dev/null 2>&1; then osascript -l JavaScript -e 'function run(a){ObjC.import("Foundation");var s=$.NSString.stri |
Kiro (13 steering)
design-standards · always · 1.3k tokmarket-research · manualprd-guide · manualprfaq-guide · manualproduct-workflow · always · 10.4k tokprototype-guide · manualprototype-spec-guide · manualspecialist-design-system · filematchspecialist-market-research · filematchspecialist-prd · filematchspecialist-prfaq · filematchspecialist-prototype-spec · filematchspecialist-prototype · filematch
How Kiro files are scored: methodology.
Similar rigs
amit-mizrachi/claude-amit-mizrachi
Claude Code skills for unattended work: hand a session off (next-prompt), take a feature through the night as one PR (night-sprint), chart a wayfinder map (mywayfinder). Plus a sliding 8h macOS caffeinate hook.
Pragmatist 3.1k tok · · Q0
SuShuheng/making-things
Production-grade Electron full-stack AI coding workflow plugin for Codex, ZCode, and Claude Code. Persisted, evidence-gated lifecycle from PRD to post-release. Dual-agent orchestration.
Skill Collector 1.6k tok · · Q3
NeverGET/superclaude-spec-workflow
Supercharge Claude Code with 19 AI agents, spec-driven workflows, and Gemini's 2M token capacity. Phase-gated development (Requirements → Design → Tasks → Code) with validation at every step. 9 MCP servers integrated. One-command setup via
Orchestrator 3.0k tok · · Q0
Bosh-Kuo/awesome-agent-toolkit
My personal collection of essential MCP configs, agent skills, and prompts, accumulated from daily dev work and the open-source community. Optimized for any AI coding tool.
MCP Hoarder 39.7k tok · · Q15