Borrowing it
Nothing to install: this file belongs to HaoZhang615/ads-copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HaoZhang615/ads-copilot/main/.github/skills/fabric-ads-session/SKILL.mdgit clone --depth 1 https://github.com/HaoZhang615/ads-copilotWrote 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/haozhang615/ads-copilot/fabric-ads-session)<a href="https://agentmods.dev/skills/haozhang615/ads-copilot/fabric-ads-session"><img src="https://agentmods.dev/badge/skills/haozhang615/ads-copilot/fabric-ads-session/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/haozhang615/ads-copilot/fabric-ads-session"><img src="https://agentmods.dev/badge/skills/haozhang615/ads-copilot/fabric-ads-session.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 | $0.00127 | $0.02278 |
| Opus 5.5 | $0.00051 | $0.00911 |
| Sonnet 5.5 | $0.00025 | $0.00456 |
| Haiku 4.5 | $0.00013 | $0.00228 |
Grade A, and why
fabric-ads-session 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Fabric ADS Session
This skill provides domain-specific knowledge for Microsoft Fabric to be used within an Architecture Design Session. The ADS methodology (persona, pacing, session structure, decision narration, trade-off framework, self-critique) is defined in the runtime system prompt — this skill supplies the Fabric-specific questions, patterns, components, and references that the methodology operates on.
Domain: Microsoft Fabric
This skill covers the Microsoft Fabric unified analytics platform including:
- Data Engineering: Spark Notebooks, Data Factory Pipelines, Dataflows Gen2, OneLake, Lakehouse, Delta Lake (Parquet)
- Data Warehousing: Fabric Warehouse (T-SQL), SQL Analytics Endpoint (read-only T-SQL over Lakehouse), Direct Lake mode
- Real-Time Intelligence: Eventhouse, KQL Database, Eventstreams, Data Activator, Real-Time Dashboards
- Business Intelligence: Power BI (native), Semantic Models, Direct Lake, Paginated Reports, Copilot in Power BI
- Data Science: ML Models, Experiments, PREDICT function, Spark MLlib
- Governance: Microsoft Purview integration, Sensitivity Labels, Endorsement, Domains, Data Lineage
- Infrastructure: Capacity Units (F SKUs), OneLake Shortcuts, Mirroring, Managed Private Endpoints, Deployment Pipelines
Phase-Specific Fabric Questions
Phase 1: Context Discovery
Ask about:
- Business problem or opportunity driving this initiative
- Industry and regulatory context
- Greenfield project vs. migration from existing system (Synapse, Power BI Premium, on-prem SQL, Databricks)
- Key stakeholders and decision-makers
- Timeline and budget constraints
- Success criteria (what does "done" look like?)
- KPIs, latency targets, and cost envelope
- Microsoft 365 licensing (E3/E5) — determines Fabric capacity entitlements
Adapt: If user mentions migration, read references/migration-patterns.md. If user names a specific industry, read references/industry-templates.md for starter context.
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- fabric-ads-session/references/conversation-framework.md 23 KB
- fabric-ads-session/references/fabric-patterns.md 32 KB
- fabric-ads-session/references/industry-templates.md 12 KB
- fabric-ads-session/references/migration-patterns.md 27 KB
- fabric-ads-session/references/probing-questions.md 15 KB
- fabric-ads-session/references/readiness-checklist.md 8.3 KB
- fabric-ads-session/references/technical-deep-dives.md 22 KB
- fabric-ads-session/references/trade-offs-and-failure-modes.md 35 KB
- fabric-ads-session/scripts/generate_architecture.py 26 KB runs code
- fabric-ads-session/skill.json 422 B
- fabric-ads-session/SKILL.md 10 KB
- references/conversation-framework.md 23 KB
- references/fabric-patterns.md 32 KB
- references/industry-templates.md 12 KB
- references/migration-patterns.md 27 KB
- references/probing-questions.md 15 KB
- references/readiness-checklist.md 8.3 KB
- references/technical-deep-dives.md 22 KB
- references/trade-offs-and-failure-modes.md 35 KB
- scripts/generate_architecture.py 26 KB runs code
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 · 172 lines · 127 tokens per session scan A 48be940428b7
fabric-ads-session is a skill published in the GitHub repository HaoZhang615/ads-copilot (2 stars, last pushed 8mo ago), licensed MIT. It adds 127 tokens to every session and 2,278 once invoked, about $0.0005 per session on Opus 5.5. 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.
fabric-ads-session compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fabric-ads-sessionHaoZhang615/ads-copilot | Skill | 2 | 8mo ago | MIT | A | 127 | Claude Code, Codex |
| code-to-diagramzebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 74 | Claude Code, Codex |
| init-workspace-documentationgriddynamics/rosetta | Skill | 370 | yesterday | Apache-2.0 | A | 10 | Claude Code |
| apex-azure-bicep-patternsjonathan-vella/apex-accelerator | Skill | 50 | 2d ago | MIT | A | 100 | Claude Code |
| apex-python-diagramsjonathan-vella/apex-accelerator | Skill | 50 | 2d ago | MIT | A | 86 | Claude Code |
| apex-vendor-promptingjonathan-vella/apex-accelerator | Skill | 50 | 2d ago | MIT | A | 95 | Claude Code |
| apex-azure-artifactsjonathan-vella/apex-accelerator | Skill | 50 | 2d ago | MIT | A | 98 | Claude Code |