microsoft/cat-agent-skills is a static website that catalogs reusable instruction sets and related packages for AI agents. People use it to search, filter, rate, and download skills for Cowork, Copilot Studio, and Scout, along with Copilot plugins and Scout automations. The catalogue entries are the skills, instructions, plugins, and settings displayed by the site.
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 microsoft/cat-agent-skills --skill power-automate-desktop-assessmentgit clone --depth 1 https://github.com/microsoft/cat-agent-skillsWrote 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/microsoft/cat-agent-skills/power-automate-desktop-assessment)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/power-automate-desktop-assessment"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/power-automate-desktop-assessment/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/microsoft/cat-agent-skills/power-automate-desktop-assessment"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/power-automate-desktop-assessment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 12 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 300 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 304 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 305 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Prompt Injection · line 300 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 302 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 304 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 305 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 306 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 308 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 309 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 310 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 311 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00048 | $0.09515 |
| Opus 5 | $0.00024 | $0.04757 |
| Sonnet 5 | $0.00010 | $0.01903 |
| Haiku 4.5 | $0.00005 | $0.00951 |
Grade A, and why
power-automate-desktop-assessment 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 8d 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 — 634 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power Automate Desktop Assessment
Use this skill when assessing, reviewing, or preparing recommendations for a Microsoft Power Automate Desktop (PAD) project, desktop flow, exported solution/package, cloud-flow orchestration around desktop flows, or related Power Platform automation artifacts. The goal is to produce an evidence-based assessment with findings, risks, severity, and actionable remediation.
Source references
Use these references as the baseline for assessment criteria:
Microsoft Learn: Power Automate and enterprise guidance
- Power Automate documentation hub: https://learn.microsoft.com/en-us/power-automate/
- Power Automate guidance documentation: https://learn.microsoft.com/en-us/power-automate/guidance/
- Power Automate planning guidance: https://learn.microsoft.com/en-us/power-automate/guidance/planning/introduction
- Automation CoE guidance: https://learn.microsoft.com/en-us/power-automate/guidance/automation-coe/overview
- Automation Kit guidance: https://learn.microsoft.com/en-us/power-automate/guidance/automation-kit/overview/introduction
- Application lifecycle management for automation projects: https://learn.microsoft.com/en-us/power-automate/guidance/planning/application-lifecycle-management
Microsoft Learn: cloud flow coding guidelines
- Cloud flow coding guidelines overview: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/
- Naming conventions: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/use-consistent-naming-conventions
- Solution-aware flows: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/understand-benefits-solution-aware-flows
- Scopes: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/create-scopes
- Child flows/reuse: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/create-reusable-code
- Parallel execution and concurrency: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/implement-parallel-execution
- Data operations: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/use-data-operations
- Trigger optimization: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/optimize-power-automate-triggers
- Work only with relevant data: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/work-with-relevant-data
- Avoid anti-patterns: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/avoid-anti-patterns
- Environment variables: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/use-environment-variables
- Robust error handling: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/error-handling
- Flow Checker: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/manage-flows-flow-checker
- Test cloud flows: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/test-cloud-flows
- Troubleshoot cloud flows: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/troubleshoot-cloud-flows
- Platform limits and throttling: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/understand-limits
- Secure inputs/outputs/triggers: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/use-secure-inputs-outputs-triggers
- Generic configuration: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/keep-flow-configuration-generic
- Flow ownership/access: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/understand-access-to-flows
- Dataverse/Purview auditing: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/use-auditing-dataverse
- Prevent data exfiltration: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/prevent-data-exfiltration
- Monitoring and alerting: https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/monitoring-and-alerting
What ships with it
6 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.
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.
- 8d ago First seen · 634 lines · 48 tokens per session scan A 815bf62c7b11
power-automate-desktop-assessment is a skill published in the GitHub repository microsoft/cat-agent-skills (69 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 9,515 once invoked, about $0.0002 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
gke-node-notready
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't…
gke-ai-troubleshooting-jobset-interruption
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or…
gke-workload-troubleshooting
Diagnoses GKE workload failures (CrashLoopBackOff, OOMKilled, ImagePullBackOff, Pending, etc.) via logs and events. Use when pods fail to start or crash repeatedly. Don't use for GKE cluster infrastructure provisioning, node pool creation, or non-Kubernetes Google Cloud services.
gke-ai-troubleshooting-handle-disruption-gpu-tpu
Diagnoses, predicts, and mitigates node disruptions during Compute Engine host maintenance and hardware or software maintenance events for GPU and TPU workloads on GKE. Use when diagnosing node disruptions, predicting host maintenance events on GPU/TPU nodepools, inspecting node interruption PromQL metrics, auditing…
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
troubleshoot-sandbox
Troubleshoot OpenSandbox issues by running diagnostics (logs, inspect, events, summary) via CLI or HTTP API to diagnose sandbox failures like OOM, crash, image pull errors, network problems, etc.