Google Cloud Professional Services is a repository of example solutions and tools for building systems with Google Cloud products. Teams can use them as references or adapt them for workloads involving services such as GKE, BigQuery, Dataflow, and machine learning APIs. The catalogue entries are skills related to this repository.
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 GoogleCloudPlatform/professional-services --skill asop-studio-sop-authoringgit clone --depth 1 https://github.com/GoogleCloudPlatform/professional-servicesWrote 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/googlecloudplatform/professional-services/asop-studio-sop-authoring)<a href="https://agentmods.dev/skills/googlecloudplatform/professional-services/asop-studio-sop-authoring"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/professional-services/asop-studio-sop-authoring/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/googlecloudplatform/professional-services/asop-studio-sop-authoring"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/professional-services/asop-studio-sop-authoring.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 | $0.00045 | $0.05457 |
| Opus 5.5 | $0.00018 | $0.02183 |
| Sonnet 5.5 | $0.00009 | $0.01091 |
| Haiku 4.5 | $0.00005 | $0.00546 |
Grade A, and why
asop-studio-sop-authoring 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 yesterday.
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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ASOP Studio SOP Authoring Skill
This skill is the definitive specification and authoring guide for designing agentic Standard Operating Procedure (SOP) workflows in the ASOP Studio YAML format (SOP Version 2). It provides rules, syntax patterns, best practices, and anti-patterns for generating high-quality, actionable, and testable multi-file SOP projects optimized for graph-guided agent execution.
1. How Graph-Guided Execution Works
Before generating SOPs, you must understand how they are executed by the underlying runtime engine (enter_node). At every turn, the engine executes actions and routes deterministically:
- Programmatic Action Execution: Upon entering a node, the engine sequentially runs all backend tool calls defined in the
actionsblock. Their outputs are stored inaction_results(e.g.,action_results.get_pizza_menu.result). - Programmatic Condition Evaluation: The engine then evaluates any
condition_routes. If a condition evaluates to true (based on variables in session state), the engine automatically traverses to the target node within the same turn without asking the LLM or user. It repeats steps 1 and 2 for the target node. It does this up to a depth of 10 nodes. - LLM Instruction and Intent Prep: Traversal pauses only when it reaches a node requiring user interaction (meaning it has
intent_routesor isEND). The engine returns the accumulated instructions, the action results, and the available user intent transitions. - LLM Presentation & Input Parsing: The LLM presents the information to the user using the accumulated instructions and action results. When the user replies, the LLM maps their response to one of the active
intent_routes. If the route containsset_variables, the LLM extracts those parameters into session state, and initiates the nextenter_nodeturn at the target node.
2. SOP Project Structure & Naming Conventions
To keep complex workflows maintainable, clean, and decoupled, ASOP Studio uses a multi-file project directory instead of a single monolithic file.
What ships with it
3 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.
- yesterday First seen · 334 lines · 45 tokens per session scan A e94c388eb902
asop-studio-sop-authoring is a skill published in the GitHub repository GoogleCloudPlatform/professional-services (3,086 stars, last pushed 2d ago), licensed Apache-2.0. It adds 45 tokens to every session and 5,457 once invoked, about $0.0002 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 2026-11-05.
asop-studio-sop-authoring compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| asop-studio-sop-authoringGoogleCloudPlatform/professional-services | Skill | 3.1k | 2d ago | Apache-2.0 | A | 45 | Gemini CLI |
| securing-kubernetes-on-cloudxalgorix/xalgorix | Skill | 1.3k | yesterday | Apache-2.0 | A | 80 | Claude Code, Codex |
| implementing-gcp-binary-authorizationxalgorix/xalgorix | Skill | 1.3k | yesterday | Apache-2.0 | A | 39 | Claude Code, Codex |
| vertex-deployGoogleCloudPlatform/vertex-ai-samples | Skill | 795 | today | Apache-2.0 | A | 0 | Claude Code, Codex |
| vertex-inferenceGoogleCloudPlatform/vertex-ai-samples | Skill | 795 | today | Apache-2.0 | A | 0 | Claude Code, Codex |
| genai-sdkGoogleCloudPlatform/vertex-ai-samples | Skill | 795 | today | Apache-2.0 | A | 73 | Claude Code, Codex |
| open-modelGoogleCloudPlatform/vertex-ai-samples | Skill | 795 | today | Apache-2.0 | A | 0 | Claude Code, Codex |