Ludovic33Fr/product-ai-toolbox
A curated repository of agents and skills designed for Product Managers. It provides practical templates, workflows, and best practices to leverage AI effectively across discovery, delivery, and decision-making.
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 Ludovic33Fr/product-ai-toolbox/agents ./rig-product-ai-toolbox/agents $ npx degit Ludovic33Fr/product-ai-toolbox/skills ./rig-product-ai-toolbox/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 Ludovic33Fr/product-ai-toolbox/skills/committee-prep .claude/skills/committee-prep $ npx degit Ludovic33Fr/product-ai-toolbox/skills/devils-advocate .claude/skills/devils-advocate $ npx degit Ludovic33Fr/product-ai-toolbox/skills/discovery-cadrage .claude/skills/discovery-cadrage $ npx degit Ludovic33Fr/product-ai-toolbox/skills/feature-ethics-audit .claude/skills/feature-ethics-audit $ npx degit Ludovic33Fr/product-ai-toolbox/skills/four-indicators-measure .claude/skills/four-indicators-measure $ npx degit Ludovic33Fr/product-ai-toolbox/skills/multi-stakeholder-comm .claude/skills/multi-stakeholder-comm $ npx degit Ludovic33Fr/product-ai-toolbox/skills/onboarding-pm .claude/skills/onboarding-pm $ npx degit Ludovic33Fr/product-ai-toolbox/skills/quality-review-tickets .claude/skills/quality-review-tickets $ npx degit Ludovic33Fr/product-ai-toolbox/skills/quarterly-review-pm .claude/skills/quarterly-review-pm $ npx degit Ludovic33Fr/product-ai-toolbox/skills/roadmap-variants .claude/skills/roadmap-variants $ npx degit Ludovic33Fr/product-ai-toolbox/skills/spec-from-brief .claude/skills/spec-from-brief $ npx degit Ludovic33Fr/product-ai-toolbox/skills/weak-signals-weekly .claude/skills/weak-signals-weekly
$ curl -fsSL --create-dirs -o .claude/agents/backlog-triage-agent.md https://raw.githubusercontent.com/Ludovic33Fr/product-ai-toolbox/main/agents/backlog-triage-agent.md $ curl -fsSL --create-dirs -o .claude/agents/competitive-watcher.md https://raw.githubusercontent.com/Ludovic33Fr/product-ai-toolbox/main/agents/competitive-watcher.md $ curl -fsSL --create-dirs -o .claude/agents/decision-journal-keeper.md https://raw.githubusercontent.com/Ludovic33Fr/product-ai-toolbox/main/agents/decision-journal-keeper.md $ curl -fsSL --create-dirs -o .claude/agents/roadmap-pilot-agent.md https://raw.githubusercontent.com/Ludovic33Fr/product-ai-toolbox/main/agents/roadmap-pilot-agent.md $ curl -fsSL --create-dirs -o .claude/agents/stakeholder-digest-agent.md https://raw.githubusercontent.com/Ludovic33Fr/product-ai-toolbox/main/agents/stakeholder-digest-agent.md $ curl -fsSL --create-dirs -o .claude/agents/weak-signals-watcher.md https://raw.githubusercontent.com/Ludovic33Fr/product-ai-toolbox/main/agents/weak-signals-watcher.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(~/.aws/**)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(.env)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/.env.*)",
"Read(**/*.key)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(npm publish:*)",
"Bash(wget *)",
"Bash(git rebase *)",
"Bash(gh pr merge *)",
"Bash(git commit *)"
]
}
} Skills (12)
committee-prepdevils-advocatediscovery-cadragefeature-ethics-auditfour-indicators-measuremulti-stakeholder-commonboarding-pmquality-review-ticketsquarterly-review-pmroadmap-variantsspec-from-briefweak-signals-weekly
Subagents (6)
| backlog-triage-agent | Utiliser pour pré-trier les tickets entrants et préparer la décision humaine sans s'y substituer. Détecte les doublons probables, signale les incohérences entre criticité déclarée et impact mesuré, et |
| competitive-watcher | Utiliser pour la veille concurrentielle continue. Surveille une liste fermée de sources externes (sites, blogs produit, communiqués, comptes sociaux), produit une note de pilotage hebdomadaire de cinq |
| decision-journal-keeper | Utiliser pour maintenir le journal de décision du PM à jour sans saisie manuelle systématique. Détecte les décisions dans les notes ingérées, propose une formulation, n'écrit qu'après validation expli |
| roadmap-pilot-agent | Utiliser pour comparer en continu l'avancement effectif de la roadmap à la trajectoire prévue. Produit une note de pilotage hebdomadaire avec maximum trois alertes classées par enjeu décisionnel, et d |
| stakeholder-digest-agent | Utiliser pour produire chaque jeudi un digest hebdomadaire personnalisé par stakeholder, à partir des sorties consolidées des autres agents. Production de brouillons uniquement, jamais d'envoi automat |
| weak-signals-watcher | Utiliser pour détecter en continu les signaux faibles utilisateurs (verbatims, support, mentions externes) et alimenter le journal de discovery, avec une synthèse hebdomadaire au format du skill weak- |
Similar rigs
DD-Gits/CoreVault
An Obsidian vault scaffold for AI-assisted development. Persistent project context, durable AI memory, and a kickoff/wrap-up session protocol that works across Claude Code, Codex, Cursor, and other AGENTS.md-aware agents.
Pragmatist 4.1k tok ·
kato-yoshiharu/dotfiles
—
Skill Collector 681 tok ·
ccomunello/cursor-my-workflow
A ready-to-fork Cursor template for academics using LaTeX/Beamer + R based on claude-code-my-workflow. Multi-agent review, quality gates, adversarial QA, and replication protocols.
Skill Collector 8.6k tok ·
l-lin/dotfiles
:octocat:
Skill Collector 11.4k tok ·