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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/GoogleCloudPlatform/professional-servicesnpx agentmods add skills/googlecloudplatform/professional-services/cx-knowledge-base-ingestionWrote 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/cx-knowledge-base-ingestion)<a href="https://agentmods.dev/skills/googlecloudplatform/professional-services/cx-knowledge-base-ingestion"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/professional-services/cx-knowledge-base-ingestion/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/cx-knowledge-base-ingestion"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/professional-services/cx-knowledge-base-ingestion.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 | $0.00048 | $0.01883 |
| Opus 5.5 | $0.00019 | $0.00753 |
| Sonnet 5.5 | $0.00010 | $0.00377 |
| Haiku 4.5 | $0.00005 | $0.00188 |
Grade A, and why
cx-knowledge-base-ingestion 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 2d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CX Agent Studio Knowledge Base Ingestion: Comprehensive Guide and Best Practices
Overview
CX Agent Studio integrates with Vertex AI Search (VAIS) / Discovery Engine to provide Retrieval-Augmented Generation (RAG) capabilities. Raw domain knowledge is authored locally as Markdown documents (.md) under the data/data_store/ folder, processed into compliant HTML content, and cataloged inside a JSONL manifest before being ingested into the Discovery Engine Data Store.
This skill details the file preparation rules, manifest schemas, and ingestion execution workflows.
Key capabilities covered:
- Document Formatting Guidelines: Structuring frontmatter metadata fields.
- Markdown-to-HTML Processing: Understanding manifest conversion.
- Discovery Engine JSONL Catalog Schema: Formulating the compilation entries.
- GCS Upload & API Ingestion Commands: Executing local imports dynamically.
Critical Rules (Always Apply)
[!IMPORTANT] Discovery Engine ingestion will reject files that fail schema metadata matching or are processed with invalid manifest links.
- YAML Frontmatter is Mandatory: Every Markdown file in
data/data_store/must begin with a standard YAML frontmatter block enclosing atitleand a nestedmetadatadictionary. - Brand Codes Match Constraints: The
brand_codedefined in the frontmatter metadata block must match the global brand variables (e.g.cymbal) used by the routing agents to ensure documents filter correctly during search tool executions. - Single JSONL Manifest Entry per Document: The
documents.jsonlmanifest must represent each HTML document as an individual JSON line containing theid,structData(extracted metadata), andcontent(GCS URI location). - Ensure GCS URI Alignment: The URI references inside
documents.jsonlmust point to the final destination bucket folder location in Google Cloud Storage (e.g.gs://YOUR-BUCKET/data_store/ingestion/doc.html).
Ingestion Flow Pipeline
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.
- 2d ago First seen · 168 lines · 48 tokens per session scan A ace02982abfe
cx-knowledge-base-ingestion is a skill published in the GitHub repository GoogleCloudPlatform/professional-services (3,086 stars, last pushed 2d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,883 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.
cx-knowledge-base-ingestion compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cx-knowledge-base-ingestionGoogleCloudPlatform/professional-services | Skill | 3.1k | 2d ago | Apache-2.0 | A | 48 | Gemini CLI |
| markitdownK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 62 | Claude Code, Codex |
| agents-llamaindexdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 72 | Claude Code, Codex |
| xberg-picking-a-formatxberg-io/xberg | Skill | 9.5k | yesterday | MIT | A | 51 | Claude Code |
| kb-retrieverConardLi/garden-skills | Skill | 14k | 12d ago | MIT | A | 105 | Claude Code, Codex |
| azure-aimicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 66 | Claude Code |
| azure-ai-contentunderstanding-pybenjaminasterA/antigravity-awesome-skills | Skill | 461 | yesterday | MIT | A | 0 | Claude Code, Codex |