Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mounra/ai-marketingnpx agentmods add skills/mounra/ai-marketing/market-report-pdfWrote 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/mounra/ai-marketing/market-report-pdf)<a href="https://agentmods.dev/skills/mounra/ai-marketing/market-report-pdf"><img src="https://agentmods.dev/badge/skills/mounra/ai-marketing/market-report-pdf/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/mounra/ai-marketing/market-report-pdf"><img src="https://agentmods.dev/badge/skills/mounra/ai-marketing/market-report-pdf.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 | $0.00000 | $0.04208 |
| Opus 5.5 | $0.00000 | $0.01683 |
| Sonnet 5.5 | $0.00000 | $0.00842 |
| Haiku 4.5 | $0.00000 | $0.00421 |
Grade A, and why
market-report-pdf 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 2mo 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 — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Générateur de Rapport Marketing PDF
Objectif du Skill
Générer un rapport marketing PDF professionnel et visuellement soigné à l'aide du script Python scripts/generate_pdf_report.py. Ce skill collecte toutes les données d'audit et d'analyse disponibles, les structure au format JSON attendu, invoque le script et produit un PDF de marque avec jauges de score, graphiques en barres, tableaux comparatifs, observations et plan d'action priorisé.
IMPORTANT : Tu dois toujours répondre et rédiger tous tes livrables en français.
Quand Utiliser
- L'utilisateur veut un rapport PDF (pas seulement Markdown)
- L'utilisateur prépare un livrable pour une présentation client
- L'utilisateur demande un "rapport soigné", "rapport client" ou "rapport PDF"
- L'utilisateur veut un rapport visuel avec graphiques et scores
- Déclenché par
/market report-pdfou/market report-pdf <domaine>
PDF vs Markdown
| Format | Idéal Pour | Avantages | Inconvénients |
|---|---|---|---|
| Présentations clients, pièces jointes email, supports commerciaux | Apparence professionnelle, mise en forme cohérente, graphiques visuels, imprimable | Plus difficile à modifier, nécessite le script Python | |
| Markdown | Usage interne, référence rapide, édition itérative, gestion de version | Facile à modifier, lisible dans n'importe quel éditeur, compatible git | Moins soigné visuellement, pas de graphiques |
Règle générale : Si le rapport va à un client ou prospect, utiliser le PDF. Pour un usage interne ou une édition ultérieure, utiliser le Markdown.
Comment Exécuter
Étape 1 : Collecter Toutes les Données Disponibles
Rassembler les données de toutes les exécutions précédentes de skills. Chercher ces fichiers dans le répertoire projet :
Sources de données principales :
AUDIT-MARKETING.md— Résultats globaux de l'auditANALYSE-LANDING.md— Analyse de conversion de la page d'atterrissageAUDIT-SEO.md— Observations SEOVOIX-DE-MARQUE.md— Analyse de la voix de marqueRAPPORT-CONCURRENTS.md— Données de comparaison concurrentielleANALYSE-FUNNEL.md— Analyse du tunnel de venteCALENDRIER-SOCIAL.md— Audit des réseaux sociauxSEQUENCES-EMAILS.md— Audit email marketingCAMPAGNES-PUB.md— Audit publicitaire
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.
- 2mo ago First seen · 350 lines · 0 tokens per session scan A 399cde7bf3d1
market-report-pdf is a skill published in the GitHub repository mounra/ai-marketing (32 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,208 tokens. 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 2026-08-30.
market-report-pdf compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| market-report-pdfmounra/ai-marketing | Skill | 32 | 7mo ago | MIT | A | 0 | Claude Code, Codex |
| document-skillstravisjneuman/.claude | Skill | 107 | 2d ago | MIT | A | 44 | Claude Code, Codex |
| analyzeShweta-Mishra-ai/tokenmizer | Skill | 35 | 2d ago | MIT | A | 76 | Claude Code |
| investment-report-readerHHFinAi/claude-equity-research-skills | Skill | 10 | 16d ago | MIT | A | 221 | Claude Code, Codex |
| dev-documentchristopherlouet/claude-base | Skill | 5 | 6d ago | MIT | A | 94 | Claude Code |
| citedy-lead-magnetscitedy/adclaw | Skill | 49 | 3mo ago | Apache-2.0 | A | 51 | Claude Code, Codex |
| tool-weasyprintb2bforce/b2bforce | Skill | 2 | 18d ago | MIT | B | 73 | Claude Code, Codex |