Azure AI Projects Python SDK
microsoft/skills
Reference for building on Microsoft Foundry with the azure-ai-projects Python SDK: project clients, versioned agents, evaluations, connections, datasets and indexes.
Parsing and ingestion directives for the Python-based Agent Development Kit (ADK) conversational agent framework.
Install Adk Framework Ingestor
$ npx skills add GoogleCloudPlatform/cxas-scrapi --skill adk-framework-ingestor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install GoogleCloudPlatform/cxas-scrapi adk-framework-ingestor --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/GoogleCloudPlatform/cxas-scrapi.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk .claude/skills/adk-framework-ingestor && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "adk-framework-ingestor" agent skill from https://github.com/GoogleCloudPlatform/cxas-scrapi/tree/main/.agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk into .claude/skills/adk-framework-ingestor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adk-framework-ingestor", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/GoogleCloudPlatform/cxas-scrapi/tree/main/.agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adkType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add GoogleCloudPlatform/cxas-scrapi --skill adk-framework-ingestor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install GoogleCloudPlatform/cxas-scrapi adk-framework-ingestor --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GoogleCloudPlatform/cxas-scrapi.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk .agents/skills/adk-framework-ingestor && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "adk-framework-ingestor" agent skill from https://github.com/GoogleCloudPlatform/cxas-scrapi/tree/main/.agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk into .agents/skills/adk-framework-ingestor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adk-framework-ingestor", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add GoogleCloudPlatform/cxas-scrapi --skill adk-framework-ingestor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install GoogleCloudPlatform/cxas-scrapi adk-framework-ingestor --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GoogleCloudPlatform/cxas-scrapi.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk .cursor/skills/adk-framework-ingestor && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "adk-framework-ingestor" agent skill from https://github.com/GoogleCloudPlatform/cxas-scrapi/tree/main/.agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk into .cursor/skills/adk-framework-ingestor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adk-framework-ingestor", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/GoogleCloudPlatform/cxas-scrapi.git --path .agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add GoogleCloudPlatform/cxas-scrapi --skill adk-framework-ingestor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install GoogleCloudPlatform/cxas-scrapi adk-framework-ingestor --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GoogleCloudPlatform/cxas-scrapi.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk .gemini/skills/adk-framework-ingestor && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "adk-framework-ingestor" agent skill from https://github.com/GoogleCloudPlatform/cxas-scrapi/tree/main/.agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk into .gemini/skills/adk-framework-ingestor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adk-framework-ingestor", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install GoogleCloudPlatform/cxas-scrapi adk-framework-ingestorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add GoogleCloudPlatform/cxas-scrapi --skill adk-framework-ingestor -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/GoogleCloudPlatform/cxas-scrapi.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk .github/skills/adk-framework-ingestor && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "adk-framework-ingestor" agent skill from https://github.com/GoogleCloudPlatform/cxas-scrapi/tree/main/.agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk into .github/skills/adk-framework-ingestor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adk-framework-ingestor", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add GoogleCloudPlatform/cxas-scrapi --skill adk-framework-ingestor -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install GoogleCloudPlatform/cxas-scrapi adk-framework-ingestor --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GoogleCloudPlatform/cxas-scrapi.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk .opencode/skills/adk-framework-ingestor && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "adk-framework-ingestor" agent skill from https://github.com/GoogleCloudPlatform/cxas-scrapi/tree/main/.agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk into .opencode/skills/adk-framework-ingestor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adk-framework-ingestor", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
adk-framework-ingestor- GitHub stars
- 107
- Token cost
- ~1.4k tokens
- SKILL.md length
- 504 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Parsing and ingestion directives for the Python-based Agent Development Kit (ADK) conversational agent framework.
- Works in 3 steps: ADK Workspace Layout → Ingestion & Parsing Directives → Dialogue Simulation Guidelines
- Tasks that involve Building AI agents
- SKILL.md covers 1. ADK Workspace Layout, 2. Ingestion & Parsing… and 3. Dialogue Simulation…
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Adk Framework Ingestor is an agent skill from GoogleCloudPlatform/cxas-scrapi. Parsing and ingestion directives for the Python-based Agent Development Kit (ADK) conversational agent framework.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Building AI agents. It works with Python. The repository describes itself as: A powerful Python API, CLI, and set of Agent Skills for CX Agent Studio to automate, evaluate, and scale your agents with ease. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Building AI agents
Example prompts
- “/adk-framework-ingestor”
Requirements
- Python 3
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit ffba639. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Adk Framework Ingestor loads about 1.4k tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 504 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from GoogleCloudPlatform/cxas-scrapi at commit ffba639, republished under its Apache-2.0 licence (© GoogleCloudPlatform). 504 words, ~1,382 tokens.
Download SKILL.mdSave it as
.claude/skills/adk-framework-ingestor/SKILL.md (or your agent's skills folder).- name
- adk-framework-ingestor
- description
- Parsing and ingestion directives for the Python-based Agent Development Kit (ADK) conversational agent framework.
ADK Framework Ingestor Skill
This skill standardizes how agents ingest, parse, and extract conversational behaviors and Critical User Journeys (CUJs) from Python workspaces built on the Agent Development Kit (ADK) framework.
1. ADK Workspace Layout
An ADK workspace typically consists of multiple decoupled microservices, each containing its own python project. The structure below is illustrative; actual directory and file names may vary:
<workspace_root>/
├── <service_name>/ # Individual project directory (e.g., router, auth, useraccount)
│ ├── main.py # Fast API or WebSocket entry point
│ ├── ReadMe.md # Setup and configuration details
│ ├── pyproject.toml # Dependency list
│ ├── vitals.yaml # Health check parameters
│ └── app/ # Core application module
│ ├── agents/ # Individual conversational agent definitions
│ │ └── <agent_name>/
│ │ ├── agent.py # Configures the agent, lists tools, and declares child agents
│ │ ├── prompt.py # Defines raw prompt strings and formatting logic
│ │ └── tools.py # Implements agent-specific tool methods
│ ├── config/ # Environment configuration module
│ │ ├── app.py # General settings and global prompts
│ │ └── state.py # Defines state machine keys and initializer dictionaries
│ └── services/ # Back-end service integrations2. Ingestion & Parsing Directives
Unlike declarative frameworks, ADK agent behaviors are defined procedurally in Python. The parser MUST dynamically discover and extract conversational behaviors following these directives (do not assume the specific names in the examples below are present in the target codebase):
A. Agent Registry Parsing
- Root Agent Discovery: Identify the primary entry agent by inspecting the
application entry points (e.g.,
main.pyor the main router service). Locate its definition file (typically underapp/agents/<root_agent_name>/agent.py) and extract the root agent class declaration. - Sub-Agent Mapping: Trace how child agents are registered. Look for
dictionaries or lists mapping states to agents (common patterns include
variables like
state_agents,sub_agents, or transition mappings) to establish the agent hierarchy. - Registered Tools Identification: Map python tool functions passed to the
agent constructor (typically via a
tools=[...]argument or decorator). Trace their parameter structures in the correspondingtools.pyor imported modules.- Rule: If a python tool function invokes helper methods from an external
toolset (e.g.,
tools.<toolset_name>_<operation>), classify this tool as a Webhook. Recursively extract its parameter/response schemas from the associated OpenAPI specification (typically found intoolsets/<toolset_name>/open_api_toolset/open_api_schema.yamlor similar).
- Rule: If a python tool function invokes helper methods from an external
toolset (e.g.,
B. Prompt & Constraint Extraction
Read the prompt definition files (typically prompt.py or prompts.py) associated
with each discovered agent:
- Primary Prompt Text: Locate the core prompt string variables containing
system instructions (e.g., variables ending in
_PROMPT). - Custom Verbalization Rules: Extract programmatic formatting blocks or string concatenations that append mandatory verbal instructions (e.g., rules forcing the agent to relay messages verbatim or format specific outputs).
Show full SKILL.md (193 more words)Show less
C. State Machine & Variable Mapping
Because state transitions are written in Python, you MUST map the context
variables used for flow control (typically defined in app/config/state.py or
equivalent state configuration files):
- Context Variables: Catalog all state keys or context variables (e.g., session variables, flags, or status codes) that act as triggers for branching.
- Transition Conditions: Analyze the agent's decision logic (e.g., in
callbacks.pyor transition handler methods) to map conditional checks directing flows to other agents (e.g., checking if a user is authenticated before transferring to a secure agent).
3. Dialogue Simulation Guidelines
When simulating natural dialogue transcripts from parsed ADK models, follow these guidelines:
- Dialogue Entry Triggers: Start the dialogue with a
Userturn that naturally triggers the entry conditions for the target state or agent being tested. - Strict Verbatim Playback: If the extracted prompts contain explicit,
non-negotiable formatting rules (e.g., spelling out numbers, avoiding specific
phrases), the simulated
Agentturns MUST strictly adhere to those rules. - Implicit Transitions: Represent programmatic transitions (e.g., silent
state updates, automatic transfers, or background confirmations) in the
transcripts as immediate
system_actionblocks or silent transfers rather than generating artificial spoken turns.
© GoogleCloudPlatform, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk of GoogleCloudPlatform/cxas-scrapi.
Open the folder on GitHubat commit ffba639
Compare with similar skills
Adk Framework Ingestor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Adk Framework Ingestor this skillGoogleCloudPlatform/cxas-scrapi | 107 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Azure AI Projects Python SDKmicrosoft/skills | 3.1k | 6 repos | ~2.8k | Automated safety check: Pass | MIT | |
| Senior Prompt Engineermaslennikov-ig/claude-code-orchestrator-kit | 260 | 4 repos | ~1.4k | Automated safety check: Pass | Custom licence | |
| Google Agents CLI Adk Codepifferologo/cloud-agents-cli | 129 | 1 repos | ~768 | Automated safety check: Pass | Apache-2.0 | |
| DSPy Language Model ProgrammingOrchestra-Research/AI-Research-SKILLs | 13k | 10 repos | ~3.8k | Automated safety check: Pass | MIT | |
| E2b Code Interpreteragent-sandbox/agent-sandbox | 218 | — | ~2.3k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Senior Prompt Engineer
maslennikov-ig/claude-code-orchestrator-kit
Provides reference guides and Python scripts for prompt optimization, RAG evaluation, and agent orchestration when building or tuning LLM systems.
Google Agents CLI Adk Code
pifferologo/cloud-agents-cli
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management", or needs ADK (Agent…
DSPy Language Model Programming
Orchestra-Research/AI-Research-SKILLs
Teaches an agent to build LM pipelines, RAG systems and agents in DSPy using signatures, modules and optimizers instead of hand-tuned prompts.
E2b Code Interpreter
agent-sandbox/agent-sandbox
Execute code in E2B sandboxes and integrate with LLMs for tool calling.
- Official
Code Snippets
MicrosoftDocs/semantic-kernel-docs
How to reference code from sample repos in Agent Framework docs pages using :::code directives, snippet tags, zone pivots, and highlight attributes.
More from GoogleCloudPlatform/cxas-scrapi
All 14 skills in this repoCxas Agent Foundry
GoogleCloudPlatform/cxas-scrapi
End-to-end GECX/CXAS/CES conversational agent lifecycle -- build agents from requirements (PRD-to-agent), create and run evals (goldens, simulations, tool tests, callback tests), debug failures, and…
Cxas Autolabel Rules
GoogleCloudPlatform/cxas-scrapi
Author, validate, and manage Contact Center AI (CCAI) Insights Autolabeling Rules.
Cxas Configurable Dashboards
GoogleCloudPlatform/cxas-scrapi
Author, validate, and manage Contact Center AI (CCAI) Insights Configurable Dashboards.
Cxas Dfcx Migration
GoogleCloudPlatform/cxas-scrapi
Migrate Dialogflow CX (DFCX) agents to CXAS (Customer Experience Agent Studio) agents.
Cxas Loss Analysis
GoogleCloudPlatform/cxas-scrapi
Retrieves non-contained CCAI Insights conversations (losses), uses agent intelligence to cluster them into common failure patterns, and generates a markdown report.
Cxas Sim Eval
GoogleCloudPlatform/cxas-scrapi
Converts CXAS golden evaluations to SCRAPI SimulationEvals test cases.
Related
Works with
Categories
Questions about Adk Framework Ingestor
What does Adk Framework Ingestor do?
Parsing and ingestion directives for the Python-based Agent Development Kit (ADK) conversational agent framework. Adk Framework Ingestor is an agent skill from GoogleCloudPlatform/cxas-scrapi. Parsing and ingestion directives for the Python-based Agent Development Kit (ADK) conversational agent framework.
When should I use Adk Framework Ingestor?
Adk Framework Ingestor fits situations like: tasks that involve Building AI agents.
How do I install Adk Framework Ingestor in Claude Code?
Run `npx skills add GoogleCloudPlatform/cxas-scrapi --skill adk-framework-ingestor -a claude-code`. Or copy the skill folder (.agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk in GoogleCloudPlatform/cxas-scrapi) into .claude/skills/adk-framework-ingestor in your project. Claude Code loads it when a task matches its description.
How do I install Adk Framework Ingestor in Codex?
Run `npx skills add GoogleCloudPlatform/cxas-scrapi --skill adk-framework-ingestor -a codex`. Or copy the skill folder (.agents/skills/cxas-cuj-report-generator/ingestors/frameworks/adk in GoogleCloudPlatform/cxas-scrapi) into .agents/skills/adk-framework-ingestor in your project. Codex loads it when a task matches its description.
Can I use Adk Framework Ingestor in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GoogleCloudPlatform/cxas-scrapi --skill adk-framework-ingestor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/adk-framework-ingestor, .gemini/skills/adk-framework-ingestor, .github/skills/adk-framework-ingestor and .opencode/skills/adk-framework-ingestor in your project.
What does Adk Framework Ingestor need to run?
SKILL.md names no scripts, command-line tools or credentials: Adk Framework Ingestor is instructions for the agent only. Our summary lists: Python 3.
Does Adk Framework Ingestor access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Adk Framework Ingestor safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Adk Framework Ingestor use?
Adk Framework Ingestor is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Adk Framework Ingestor use?
About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Adk Framework Ingestor?
Skills that share tags, products or a category with Adk Framework Ingestor: Azure AI Projects Python SDK (microsoft/skills, 3.1k stars), Senior Prompt Engineer (maslennikov-ig/claude-code-orchestrator-kit, 260 stars), Google Agents CLI Adk Code (pifferologo/cloud-agents-cli, 129 stars) and DSPy Language Model Programming (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Adk Framework Ingestor?
GoogleCloudPlatform (a GitHub organization) maintains it in GoogleCloudPlatform/cxas-scrapi, which has 107 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 8, 2026.
Source: GoogleCloudPlatform/cxas-scrapi on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.