Add AI-Policy-Terms-Analyzer to Natural Language Processing section

[Copilot]

Adds 9TEVE-O/AI-Policy-Terms-Analyzer — a Python tool for extracting structured technical information (tech stacks, APIs, domains, third-party integrations) from policy and terms-of-service documents — to the Natural Language Processing → General section.

Entry placed alphabetically before gensim.

⚠️ Heads up: This repo is ~2 months old (created 2026-01-06) with 1 star, which falls below the CONTRIBUTING.md thresholds (3-month minimum age, 100-star floor for non-hidden-gems). Worth revisiting once the project has more community traction.

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• https://api.github.com/graphql
  • Triggering command: /usr/bin/gh gh pr list --repo 9TEVE-O/awesome-python --limit 10 --json number,title,author,url,body,files,mergeable,mergeStateStatus (http block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

find a place repo I am working on that this repo would benefit from

---

🔒 GitHub Advanced Security automatically protects Copilot coding agent pull requests. You can protect all pull requests by enabling Advanced Security for your repositories. Learn more about Advanced Security.

[9TEVE-O]

GitHub Copilot/Tutorials/Coding agent/Get the best results
Best practices for using GitHub Copilot to work on tasks
Learn how to get the best results from Copilot coding agent.

Who can use this feature?
Copilot coding agent is available with the GitHub Copilot Pro, GitHub Copilot Pro+, GitHub Copilot Business and GitHub Copilot Enterprise plans. The agent is available in all repositories stored on GitHub, except repositories owned by managed user accounts and where it has been explicitly disabled.

In this article
Note

For an introduction to Copilot coding agent, see About GitHub Copilot coding agent.

Making sure your issues are well-scoped
GitHub Copilot provides better results when assigned clear, well-scoped tasks. An ideal task includes:

A clear description of the problem to be solved or the work required.
Complete acceptance criteria on what a good solution looks like (for example, should there be unit tests?).
Directions about which files need to be changed.
If you pass a task to Copilot by assigning an issue, it's useful to think of the issue you assign to Copilot as a prompt. Consider whether the issue description is likely to work as an AI prompt, and will enable Copilot to make the required code changes.

Choosing the right type of tasks to give to Copilot
As you work with Copilot, you'll get a sense of the types of tasks it's best suited to work on. Initially, you might want to start by giving Copilot simpler tasks, to see how it works as a coding agent. For example, you could start by asking Copilot to fix bugs, alter user interface features, improve test coverage, update documentation, improve accessibility, or address technical debt.

Issues that you may choose to work on yourself, rather than assigning to Copilot, include:

Complex and broadly scoped tasks

Broad-scoped, context-rich refactoring problems requiring cross-repository knowledge and testing
Complex issues requiring understanding dependencies and legacy code
Tasks that require deep domain knowledge
Tasks that involve substantial business logic
Large changes to a codebase requiring design consistency
Sensitive and critical tasks

Production-critical issues
Tasks involving security, personally identifiable information, authentication repercussions
Incident response
Ambiguous tasks

Tasks lacking clear definition: tasks with ambiguous requirements, open-ended tasks, tasks that require working through uncertainty to find a solution
Learning tasks

Tasks where the developer wants to learn to achieve a deeper understanding
Using comments to iterate on a pull request
Working with Copilot on a pull request is just like working with a human developer: it's common for the pull request to need further work before it can be merged. The process for getting the pull request to a mergeable state is exactly the same when the pull request is created by Copilot as when it's created by a human.

You can also mention @copilot in comments on the pull request—explaining what you think is incorrect, or could be improved—and leave Copilot to make the required changes. Alternatively, you can work on the feature branch yourself and push changes to the pull request.

After a user with write access mentions @copilot in a comment, Copilot will start to make any required changes, and will update the pull request when it's done. Because Copilot starts looking at comments as soon as they are submitted, if you are likely to make multiple comments on a pull request it's best to batch them by clicking Start a review, rather than clicking Add single comment. You can then submit all of your comments at once, triggering Copilot to work on your entire review, rather than working on individual comments separately.

Note

Copilot only responds to comments from people who have write access to the repository.

As Copilot makes changes to the pull request, it will keep the title and body up to date so they reflect the current changes.

Adding custom instructions to your repository
By adding custom instructions to your repository, you can guide Copilot on how to understand your project and how to build, test and validate its changes.

If Copilot is able to build, test and validate its changes in its own development environment, it is more likely to produce good pull requests which can be merged quickly.

Copilot coding agent supports a number of different types of custom instructions files:

/.github/copilot-instructions.md
/.github/instructions/**/*.instructions.md
**/AGENTS.md
/CLAUDE.md
/GEMINI.md
For more information, see Adding repository custom instructions for GitHub Copilot.

Repository-wide instructions
To add instructions that apply to all tasks assigned to Copilot in your repository, create a .github/copilot-instructions.md file in the root of your repository. This file should contain information about your project, such as how to build and test it, and any coding standards or conventions you want Copilot to follow. Note that the instructions will also apply to Copilot Chat and Copilot code review.

The first time you ask Copilot to create a pull request in a given repository, Copilot will leave a comment with a link to automatically generate custom instructions. You can also ask Copilot to generate custom instructions for you at any time using our recommended prompt. See Adding repository custom instructions for GitHub Copilot.

You can also choose to write your own custom instructions at any time. Here is an example of an effective copilot-instructions.md file:

This is a Go based repository with a Ruby client for certain API endpoints. It is primarily responsible for ingesting metered usage for GitHub and recording that usage. Please follow these guidelines when contributing:

Code Standards

Required Before Each Commit

• Run make fmt before committing any changes to ensure proper code formatting
• This will run gofmt on all Go files to maintain consistent style

Development Flow

• Build: make build
• Test: make test
• Full CI check: make ci (includes build, fmt, lint, test)

Repository Structure

• cmd/: Main service entry points and executables
• internal/: Logic related to interactions with other GitHub services
• lib/: Core Go packages for billing logic
• admin/: Admin interface components
• config/: Configuration files and templates
• docs/: Documentation
• proto/: Protocol buffer definitions. Run make proto after making updates here.
• ruby/: Ruby implementation components. Updates to this folder should include incrementing this version file using semantic versioning: ruby/lib/billing-platform/version.rb
• testing/: Test helpers and fixtures

Key Guidelines

1. Follow Go best practices and idiomatic patterns
2. Maintain existing code structure and organization
3. Use dependency injection patterns where appropriate
4. Write unit tests for new functionality. Use table-driven unit tests when possible.
5. Document public APIs and complex logic. Suggest changes to the docs/ folder when appropriate

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.
To continue using code reviews, you can upgrade your account or add credits to your account and enable them for code reviews in your settings.

[9TEVE-O]

Double check