create-skill

A step-by-step guide for creating new developer skills for Cortex Framework V7, including their instructions, checks, and registration. Cortex Framework is a software framework with shared rules for building data products and agent skills.

In plain words
What is it for?
Use it to assess overlap, choose a skill design, create the required files under .agents/skills/, validate the result, and register the skill.
Why use it?
It helps prevent new skills from duplicating existing ones or breaking the framework’s core files. It also requires the finished skill to pass a structural validation check.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/googlecloudplatform/cortex-framework/create_skill
Any agent
npx skills add GoogleCloudPlatform/cortex-framework --skill create_skill
Clone the repo
git clone --depth 1 https://github.com/GoogleCloudPlatform/cortex-framework

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,108 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.01108
Opus 5 $0.00016 $0.00554
Sonnet 5 $0.00007 $0.00222
Haiku 4.5 $0.00003 $0.00111

Measured yesterday against content hash db7e771bbb50, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-skill 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/scaffold_skill.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/create_skill/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creating a New Cortex Developer Skill

This skill guides the end-to-end creation, overlap evaluation, authoring, validation, and ecosystem registration of new AI agent skills in Cortex Framework V7, or the creation of custom instruction extensions inside existing skill custom/ directories.

CRITICAL OPERATIONAL RULE: You are an end-to-end deployment agent, not just a text generator. A skill creation task is NOT complete until the mandatory Skill Anatomy Validation Gate has been executed with a 100% pass rate. You MUST NOT stop after creating the files.

CRITICAL ISOLATION RULE (ZERO-TRUST FOR CORE PLATFORM): New skills must reside exclusively inside .agents/skills/<skill_name>/. Never modify platform core runtime code (cortex-framework-core/src/common/) while authoring skills unless explicitly instructed by the user.


Step 1: Overlap Analysis & Pathway Selection

Before creating a new skill, evaluate existing skills to prevent redundancy and fragmentation.

1. Perform Skill Overlap Assessment

Dynamically inspect the existing skills in .agents/skills/ (and the registry in .agents/AGENTS.md). Read their frontmatter descriptions to evaluate whether the requested capability overlaps with an existing workflow.

2. Select Pathway: Custom Extension vs. Standalone Skill

Refer to skill_anatomy_guide.md and authoring_best_practices.md for the decision matrix:

  • Path A (Custom Extension via custom/): If the proposed capability extends or customizes an existing lifecycle phase (e.g. organization-specific naming standards, custom test assertions, compliance gates, specialized dataset targets), DO NOT create a new skill. Instead, proceed to Step 2A to create custom instructions in <existing_skill>/custom/.
  • Path B (New Standalone Skill): If the capability introduces a genuinely new domain or distinct lifecycle phase not covered by any existing skill, proceed to Step 2B to scaffold and author a new standalone skill.

Read the full file on GitHub · 98 lines

Files

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.

Changes

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.

  1. yesterday First seen · 98 lines · 33 tokens per session scan A db7e771bbb50

Subscribe to this mod's changes

create-skill is a skill published in the GitHub repository GoogleCloudPlatform/cortex-framework (10 stars, last pushed 6d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,108 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 2026-08-31.

Related

Other skills, from other repositories

google-mobile-ads-android-migrate-to-next-gen

Migrates Android applications from the old, legacy Google Mobile Ads (GMA) SDK (com.google.android.gms:play-services-ads) to the new GMA Next-Gen SDK (com.google.android.libraries.ads.mobile.sdk:ads-mobile-sdk). Provides comprehensive mapping tables for imports, classes, and method signatures to help determine…

google/skills · 105 tokens

agent-platform-tuning

Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).

google/skills · 64 tokens

application-design-center-design-deploy

Processes GCP infrastructure design and deployment workflows within Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting…

google/skills · 94 tokens

cloud-run-basics

Manages Cloud Run services, jobs, and worker pools. Use when you need to deploy applications responding to HTTP requests (services), run event-triggered or scheduled tasks (jobs), or handle always-on pull-based background processing (worker pools).

google/skills · 53 tokens

google-analytics-data-api-basics

Manages Google Analytics reporting data, enables the Analytics Data API via the Cloud CLI, and creates reports using the Google Analytics Data API (v1beta). Use when you need to interact with Google Analytics properties, run customized analytics reports, query metrics (like activeUsers, screenPageViews) and dimensions…

google/skills · 111 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens