From rapido-canva
Generates CODIR (comité de direction) presentations by collecting data from Rapido servers, building an outline, validating via Canva, and exporting slides.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rapido-canva:presentation-codirThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Charger `${CLAUDE_PLUGIN_ROOT}/reference/directives-outils.md`,
Charger ${CLAUDE_PLUGIN_ROOT}/reference/directives-outils.md,
${CLAUDE_PLUGIN_ROOT}/reference/pieges-canva.md et
${CLAUDE_PLUGIN_ROOT}/reference/CONFORMITE.md.
comite-de-direction ;
sinon collecter directement : CRM (get_dashboard_general_stats,
get_revenue_summary, get_stats_pipeline_global), CMS
(list_scheduled_posts + post_insights par lots de 10), RH
(get-projects-list-tool, get-dailies-tool), FoodEatUp
(finance_summary, establishment_id requis). Chaque chiffre garde sa
source.- Item\n- Item), jamais « • ».
Sauter un domaine non disponible (le dire).request-outline-review (topic ≤ 150
caractères, audience: "professional", length: "balanced" si 6 slides,
pages = l'outline ci-dessus, brand_kit_id si choisi via
list-brand-kits). Attendre la VALIDATION de l'utilisateur dans le widget.
Toute demande de modification (retirer une slide, réordonner…) = re-appeler
request-outline-review avec l'outline modifié.generate-design-structured (topic, audience, style,
length, design_type: "presentation", presentation_outlines = outline
approuvé). JAMAIS generate-design pour cette présentation.get-export-formats puis export-design
(format.type: "pptx" ou "pdf" selon le choix de l'utilisateur) ;
afficher l'URL de téléchargement.npx claudepluginhub prendstapart/plugin-claude-mcp-braindcode- --plugin rapido-canvaGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.
Dispatches multiple subagents concurrently for independent tasks without shared state. Use when facing 2+ unrelated failures or subsystems that can be investigated in parallel.