alexandre-darmon/ai-pm-skills
Evals as evidence: tested Agent Skills for AI product managers in regulated companies
field: AI / ML workflow: Planning & specsPR / code reviewCI/CD & deployTesting & TDDFrontend & design runs claude in CI
stack: Python
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit alexandre-darmon/ai-pm-skills/skills ./rig-ai-pm-skills/skills 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 alexandre-darmon/ai-pm-skills/skills/agent-design-and-tooling .claude/skills/agent-design-and-tooling $ npx degit alexandre-darmon/ai-pm-skills/skills/agent-evals .claude/skills/agent-evals $ npx degit alexandre-darmon/ai-pm-skills/skills/ai-act-classification .claude/skills/ai-act-classification $ npx degit alexandre-darmon/ai-pm-skills/skills/ai-adoption-plan .claude/skills/ai-adoption-plan $ npx degit alexandre-darmon/ai-pm-skills/skills/ai-data-requirements .claude/skills/ai-data-requirements $ npx degit alexandre-darmon/ai-pm-skills/skills/ai-feasibility-spike .claude/skills/ai-feasibility-spike $ npx degit alexandre-darmon/ai-pm-skills/skills/ai-incident-playbook .claude/skills/ai-incident-playbook $ npx degit alexandre-darmon/ai-pm-skills/skills/ai-interaction-patterns .claude/skills/ai-interaction-patterns $ npx degit alexandre-darmon/ai-pm-skills/skills/ai-opportunity-assessment .claude/skills/ai-opportunity-assessment $ npx degit alexandre-darmon/ai-pm-skills/skills/ai-roi-quantification .claude/skills/ai-roi-quantification $ npx degit alexandre-darmon/ai-pm-skills/skills/ai-vendor-evaluation .claude/skills/ai-vendor-evaluation $ npx degit alexandre-darmon/ai-pm-skills/skills/assistant-kpis-cost-per-outcome .claude/skills/assistant-kpis-cost-per-outcome $ npx degit alexandre-darmon/ai-pm-skills/skills/build-evals .claude/skills/build-evals $ npx degit alexandre-darmon/ai-pm-skills/skills/conversation-analysis .claude/skills/conversation-analysis $ npx degit alexandre-darmon/ai-pm-skills/skills/error-analysis .claude/skills/error-analysis $ npx degit alexandre-darmon/ai-pm-skills/skills/llm-feature-prd .claude/skills/llm-feature-prd $ npx degit alexandre-darmon/ai-pm-skills/skills/llm-judge-calibration .claude/skills/llm-judge-calibration $ npx degit alexandre-darmon/ai-pm-skills/skills/model-card-ai-registry .claude/skills/model-card-ai-registry $ npx degit alexandre-darmon/ai-pm-skills/skills/model-selection .claude/skills/model-selection $ npx degit alexandre-darmon/ai-pm-skills/skills/process-ai-redesign .claude/skills/process-ai-redesign $ npx degit alexandre-darmon/ai-pm-skills/skills/production-evals-monitoring .claude/skills/production-evals-monitoring $ npx degit alexandre-darmon/ai-pm-skills/skills/prototype-handover .claude/skills/prototype-handover $ npx degit alexandre-darmon/ai-pm-skills/skills/release-to-production .claude/skills/release-to-production $ npx degit alexandre-darmon/ai-pm-skills/skills/retrieval-evaluation .claude/skills/retrieval-evaluation $ npx degit alexandre-darmon/ai-pm-skills/skills/synthetic-eval-data .claude/skills/synthetic-eval-data $ npx degit alexandre-darmon/ai-pm-skills/skills/system-prompt-and-guardrails .claude/skills/system-prompt-and-guardrails $ npx degit alexandre-darmon/ai-pm-skills/skills/trace-review-tool .claude/skills/trace-review-tool
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 (27)
agent-design-and-toolingagent-evalsai-act-classificationai-adoption-planai-data-requirementsai-feasibility-spikeai-incident-playbookai-interaction-patternsai-opportunity-assessmentai-roi-quantificationai-vendor-evaluationassistant-kpis-cost-per-outcomebuild-evalsconversation-analysiserror-analysisllm-feature-prdllm-judge-calibrationmodel-card-ai-registrymodel-selectionprocess-ai-redesignproduction-evals-monitoringprototype-handoverrelease-to-productionretrieval-evaluationsynthetic-eval-datasystem-prompt-and-guardrailstrace-review-tool
Similar rigs
IamGianluca/dotfiles
Dotfiles for a streamlined developer environment
Pragmatist 3.0k tok · · Q3
haxsd/haxsd-byok
Windows x64 本机模型网关:让 Cursor、Devin、Codex、Claude Code CLI 与 Claude Desktop 使用你自配的模型 API,含模型库、调用记录与 Token 统计。
Pragmatist 1.4k tok · · Q3
olehsvyrydov/AI-development-team
An AI dev team in your editor — ~48 specialist agents and an enforced, proportional workflow with approval gates. Process, not prompts. Open-source, no lock-in; works in Claude Code, Cursor, Kiro & VS Code.
Skill Collector 3.8k tok · · Q0
vTuanpham/dotfiles-with-agency
Agent-first WSL2 dotfiles for Codex, Claude Code, Antigravity and OpenCode. CLI delegation, phone chat, model selection and private previews.
YOLO Cowboy 8.0k tok · · Q5