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 khalilbenaz/claude-skills-collection --skill public-speaking-coachgit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/public-speaking-coach)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/public-speaking-coach"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/public-speaking-coach/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/khalilbenaz/claude-skills-collection/public-speaking-coach"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/public-speaking-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.01870 |
| Opus 5 | $0.00034 | $0.00935 |
| Sonnet 5 | $0.00013 | $0.00374 |
| Haiku 4.5 | $0.00007 | $0.00187 |
Grade A, and why
public-speaking-coach 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 9d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Public Speaking Coach
Workflow en étapes
Étape 1 — Cadrage initial (2 min)
Collecter d'emblée :
- Type : pitch investisseur / conférence technique / formation / réunion de direction / démo produit
- Durée : < 5 min / 5–20 min / > 20 min
- Audience : taille, niveau technique, attentes, culture (FR/EN/mixte)
- Enjeux : décision à prendre, changement à impulser, information à transmettre
Décision : si la durée est < 3 min, basculer sur le format elevator pitch (accroche + 3 points + call to action). Si > 30 min, structurer en blocs de 7–10 min avec transitions actives.
Étape 2 — Structure du discours
Utiliser le modèle PEEC pour chaque intervention :
P — Problème / contexte (pourquoi vous parlez)
E — Exploration (3 points max, pas plus)
E — Exemple concret pour chaque point
C — Call-to-action / conclusion mémorable
Accroche efficace (choisir une seule technique) :
- Chiffre surprenant : "80 % des projets IA échouent avant la prod — voici pourquoi."
- Question rhétorique : "Combien d'entre vous ont déjà raté un déploiement un vendredi soir ?"
- Anecdote courte < 30 sec qui pose le problème réel
Transitions : verbaliser la transition entre chaque bloc pour éviter les ruptures :
"Maintenant qu'on sait pourquoi, voyons comment."
Étape 3 — Voix et rythme
Exercice mesurable avant la présentation :
1. Lire à voix haute 2 min → compter les mots/min (cible : 120–140 wpm FR, 130–150 wpm EN)
2. Identifier les 3 moments où placer une PAUSE (≥ 2 sec) pour l'impact
3. Encercler les mots-clés à appuyer avec le volume
4. Tester le tout sur smartphone → réécouter, noter les "euh" et les décrochages
Indicateurs cibles :
| Critère | Débutant à corriger | Cible |
|---|---|---|
| Débit | > 160 wpm | 120–140 wpm |
| Pauses | Aucune ou remplissage "euh" | ≥ 2 pauses intentionnelles |
| Volume | Monotone | Variation sur les mots-clés |
Étape 4 — Langage corporel
Règles concrètes :
- Contact visuel : triangle 3 points (gauche/centre/droite), 3–5 sec par personne, ne pas fixer les slides
- Mains : position de repos = devant vous, à hauteur de ceinture, paumes visibles (signe d'ouverture)
- Déplacement : avancer d'un pas pour insister, reculer pour laisser l'audience réfléchir
- Posture : pieds à largeur d'épaules, ne pas se balancer — ancrer les pieds au sol
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.
- 9d ago First seen · 146 lines · 67 tokens per session scan A 776cf2aa30f0
public-speaking-coach is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 19d ago), licensed MIT. It adds 67 tokens to every session and 1,870 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 2026-09-03.
Other skills, from other repositories
explain
Explains code/architecture with Mermaid diagrams and sequence flows. Triggers: what does X do, how does Y work, explain code, sequence diagram.
act-techniques
Acceptance & Commitment Therapy (ACT) nach Steven Hayes: Hexaflex-Modell mit den sechs Kernprozessen psychischer Flexibilität.
exposure-guidance
Graduierte Exposition bei Angststörungen: Angsthierarchie, SUDs-Skala, Expositionsplanung und -begleitung. Nur Psychoedukation, keine Durchführung.
systemisch-loesungsfokussiert
Systemic and solution-focused methods: miracle question, scaling, exception exploration, circular questions, hypothetical questions, worsening questions, coping questions. Merged from solution-focused-therapy and systemic-questioning.
trauma-psychoeducation
Trauma-Psychoedukation: Traumadefinition, normale Reaktionen, Fenster der Belastbarkeit, Triggermanagement und Selbstfürsorge.
behavioral-activation
Verhaltensaktivierung bei Depression: Den Teufelskreis durchbrechen, Aktivitätsprotokoll, Wochenplanung und wertebasierte Aktivitäten.