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 power-bi-designergit 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/power-bi-designer)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/power-bi-designer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/power-bi-designer/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/power-bi-designer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/power-bi-designer.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 | $0.00071 | $0.01974 |
| Opus 5 | $0.00036 | $0.00987 |
| Sonnet 5 | $0.00014 | $0.00395 |
| Haiku 4.5 | $0.00007 | $0.00197 |
Grade A, and why
power-bi-designer 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power BI Designer
Workflow
1. Analyser les besoins métier
- Identifier les KPIs (ex. : CA, taux de conversion, délai moyen), le public cible (direction = agrégats, opérationnel = détail transactionnel) et la fréquence de refresh requise.
- Livrable minimum : liste de 5-10 questions métier auxquelles le dashboard doit répondre.
2. Concevoir le modèle de données (star schema)
- Tables de faits : mesures numériques + clés étrangères uniquement. Jamais de colonnes de description.
- Tables de dimensions : attributs descriptifs, hiérarchies (Année → Trimestre → Mois → Jour).
- Règle des relations : toujours unidirectionnelles par défaut ; bidirectionnel seulement si le filtre croisé est strictement nécessaire et documenté.
- Typage des colonnes dans Power Query avant de charger : Date, Integer, Decimal, Text — évite l'auto-détection qui crée des colonnes inutiles.
// Power Query — typage explicite en fin de requête
#"Types appliqués" = Table.TransformColumnTypes(Source, {
{"DateVente", type date},
{"Montant", type number},
{"IdClient", Int64.Type}
})
3. Connecter et transformer les sources (Power Query / M)
- Utiliser le Query Folding : filtrer et agréger côté source (SQL, SSAS) avant de ramener les données dans Power BI.
- Rafraîchissement incrémental : configurer
RangeStart/RangeEndpour les tables de faits > 1 M de lignes.
// Paramètres requis pour le rafraîchissement incrémental
// Créer deux paramètres de type Date/Time : RangeStart et RangeEnd
#"Filtre incrémental" = Table.SelectRows(Source, each
[DateVente] >= RangeStart and [DateVente] < RangeEnd
)
- Désactiver le chargement des requêtes intermédiaires (staging) pour ne charger que les tables finales.
4. Écrire les mesures DAX
Règle fondamentale : mesures pour les calculs dynamiques, colonnes calculées uniquement pour les attributs statiques.
-- Mesure de base
CA Total = SUM(Ventes[Montant])
-- DIVIDE pour éviter les divisions par zéro
Taux Conversion =
DIVIDE(
COUNTROWS(FILTER(Leads, Leads[Statut] = "Converti")),
COUNTROWS(Leads),
0
)
-- YTD (Year-to-Date)
CA YTD =
CALCULATE(
[CA Total],
DATESYTD(Calendrier[Date])
)
-- Comparaison année précédente
CA N-1 =
CALCULATE(
[CA Total],
SAMEPERIODLASTYEAR(Calendrier[Date])
)
-- Variation %
Var% CA =
DIVIDE([CA Total] - [CA N-1], [CA N-1], BLANK())
-- Mesure avec contexte filtré
CA Région Active =
CALCULATE(
[CA Total],
KEEPFILTERS(Régions[Actif] = TRUE())
)
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 · 166 lines · 71 tokens per session scan A 292f7ea7f505
power-bi-designer is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 19d ago), licensed MIT. It adds 71 tokens to every session and 1,974 once invoked, about $0.0004 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
model-routing-patterns
Multi-model pipelines (Haiku/Sonnet/Opus): cost routing, escalation, fallback chains. Triggers: model routing, Haiku, Sonnet, Opus, escalation, fallback chain.
rag-patterns
RAG: embeddings, chunking, hybrid search (BM25+vector), reranking, CRAG, multi-hop. Triggers: RAG, embedding, pgvector, Qdrant, Pinecone, Weaviate, reranker, semantic search.
evaluate
Evaluates RAG retrieval and LLM-as-judge metrics (faithfulness, relevancy, context precision). Triggers: measure RAG quality, knowledge gap, RAG eval, golden dataset.
json-mode-patterns
Structured JSON output from Claude: tool-use-as-JSON, schema, parsing, partial recovery. Triggers: JSON mode, structured output, schema validation, JSON parsing.
index
Reindexes KB for semantic search via vector store (Qdrant). Triggers: reindex KB, rebuild index, vector reindex, refresh embeddings.
ai-portable-setup
Erstellt einen portablen KI-Arbeitsbereich auf einem USB-Stick oder beliebigen Laufwerk. RAG-Pipeline mit lokalen LLM-Modellen (Ollama), Vektordatenbank (ChromaDB) und vorkonfigurierten Prompts.