Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Ludovic33Fr/product-ai-toolbox --skill quarterly-review-pmgit clone --depth 1 https://github.com/Ludovic33Fr/product-ai-toolboxWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ludovic33fr/product-ai-toolbox/quarterly-review-pm)<a href="https://agentmods.dev/skills/ludovic33fr/product-ai-toolbox/quarterly-review-pm"><img src="https://agentmods.dev/badge/skills/ludovic33fr/product-ai-toolbox/quarterly-review-pm/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ludovic33fr/product-ai-toolbox/quarterly-review-pm"><img src="https://agentmods.dev/badge/skills/ludovic33fr/product-ai-toolbox/quarterly-review-pm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.02011 |
| Opus 5 | $0.00034 | $0.01006 |
| Sonnet 5 | $0.00013 | $0.00402 |
| Haiku 4.5 | $0.00007 | $0.00201 |
Grade A, and why
quarterly-review-pm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
quarterly-review-pm
Fiche éditoriale
Objectif. Préparer la revue trimestrielle d'un PM sur la base de données factuelles et de la grille de maturité IA.
Entrées. Profil du PM, livraisons du trimestre, retours pairs anonymisés.
Sorties. Synthèse factuelle, score de maturité IA, zones de progression et stagnation, questions à poser, objectifs proposés.
Cadence d'usage. Trimestriellement, pour chaque PM managé.
Mode opératoire
Quand m'invoquer
L'utilisateur (manager) prépare la revue trimestrielle d'un PM de son équipe. Il me fournit le profil du PM, les livraisons du trimestre (objectifs initiaux, livrables réels, OKR atteints / partiels / manqués), et les retours pairs anonymisés (3-5 retours typiques).
Procédure
- Synthèse factuelle : reformuler ce que le trimestre a livré en termes neutres (sans qualificatifs comme "excellent" ou "décevant"). Lister objectifs initiaux, livrables réels, écarts, OKR atteints/partiels/manqués.
- Score de maturité IA : appliquer la grille de l'Annexe 2 (5 dimensions : usage opérationnel, esprit critique, posture orchestrateur, mesure d'impact, partage). Score 1-5 par dimension. Justifier en une phrase chacun.
- Zones de progression : 2-3 dimensions où le PM a clairement progressé sur le trimestre, avec preuves factuelles.
- Zones de stagnation : 1-2 dimensions où la progression est absente ou faible. Tone factuel, pas accusatoire.
- Retours pairs : agréger les retours pairs sans citer de noms, en distinguant points d'accord et signaux divergents.
- Questions à poser en revue : 5-7 questions ouvertes qui aideront le PM à se positionner sur sa propre trajectoire (pas des questions piège).
- Objectifs proposés Q+1 : 3 objectifs concrets, dont au moins un de progression sur la maturité IA.
- Produire la sortie au format ci-dessous.
Format de sortie
# Revue trimestrielle — {nom du PM}, {trimestre}
## Synthèse factuelle
### Objectifs initiaux
- ...
### Livrables réels
- ...
### Écarts
- ...
### OKR
- {OKR 1} : atteint / partiel / manqué — {valeur réelle vs cible}
- ...
## Score de maturité IA
| Dimension | Score (1-5) | Justification |
|-----------|-------------|---------------|
| Usage opérationnel | x | ... |
| Esprit critique | x | ... |
| Posture orchestrateur | x | ... |
| Mesure d'impact | x | ... |
| Partage | x | ... |
**Score global** : x/25
## Zones de progression (2-3)
- {dimension} — {progression observée} — {preuve factuelle}
- ...
## Zones de stagnation (1-2)
- {dimension} — {stagnation observée, sans jugement} — {ce qui pourrait débloquer}
- ...
## Retours pairs (anonymisés)
### Points d'accord (≥3 retours convergents)
- ...
### Signaux divergents (à discuter en 1:1)
- ...
## Questions à poser en revue (5-7)
1. {question ouverte}
2. ...
## Objectifs proposés Q+1
### Objectif 1 — {titre court}
**Mesurable par** : ...
**Échéance** : fin Q+1.
### Objectif 2 — {titre court}
...
### Objectif 3 — {titre court, sur la maturité IA}
...
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 197 lines · 67 tokens per session scan A 62e279866fca
quarterly-review-pm is a skill published in the GitHub repository Ludovic33Fr/product-ai-toolbox (1 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 2,011 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
task-board-setup
Creates a Codex file-based task board. Explicit user invocation only.
tackle-issue
Start-of-work triage in this monorepo. Trigger on: a GitHub issue number ("tackle issue 99", "work on #42", bare #N), pasted proposal/spec text ("investigate this", "pressure-test this", "scope this"), or picker phrasing ("tackle the next issue", "what should I work on"). Read-only investigation that tries to falsify…
stale-proposals
Audit this repository's local proposal queue for stale entries: proposals still marked proposed, deferred, or accepted even though the work already shipped, plus old proposals whose subject has become inert. Reconcile proposals against plugin changelogs and first-parent Git history, automatically resolve only…
add-source
Interactively add a new source to feed-sources.md with type inference, https and name-uniqueness validation, and category checking against feed-categories.md. Appends a formatted row to the Active Sources table. Invoke with /feed-hermit:add-source.
plan-to-tasks
Transform a plancreation planv{N}.md into a structured tasks.yaml + per-WP workpackages/.yaml using parallel Sonnet sub-agents. Use after plan-creation finishes when you need execution-friendly task structure.
debt-ops-add
Register a deferred decision in the tech-debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you…