This section teaches any AI coding agent how to audit and maintain the project's AI context files.

Call Azure AI Foundry Agents in the OpenAI Request/Response format.

This is an example of a very thorough and detailed AGENTS.md file. Most codebases would not need this much information, nor would the files be as long, but this is a good reference and covers all area

- After all code changes, run the `slop-refinery-quick-checks` skill.

You are an agent discovery assistant. Help the user see what BRad Method agents are available.

Use when working with iOS/macOS Keychain Services (SecItem queries, kSecClass, OSStatus errors), biometric authentication (LAContext, Face ID, Touch ID), CryptoKit (AES-GCM, ChaChaPoly, ECDSA, ECDH, HPKE, ML-KEM), Secure Enclave, secure credential storage (OAuth tokens, API keys), certificate pinning (SecTrust, SPKI), keychain sharing across apps/extensions, migrating secrets from UserDefaults or plists, or OWASP MASVS/MASTG mobile compliance on Apple platforms.

Use when you need to clarify requirements and route to the right workflow (idea → executable input). Project intake + routing: help the user brainstorm and clarify intent, persist goal/context artifacts, then dispatch to the right workflow or step skill. Default route is workflow-ship-faster (Next.js 16.1.1) for idea/prototype→launch. Triggers: project kickoff, requirements clarification, brainstorm, ideas, discovery, intake.

Publish Markdown content into X (Twitter) Articles as a **draft**, preserving formatting via rich text paste and deterministic image insertion.

Imports JIRA tickets (via API or web scraping) and converts them to local story files. Supports single tickets, bulk imports via JQL, and optional dev workflow kickoff. Works with or without API credentials.

This skill helps you add new rules to the attgo-linter project.

Formats or checks C/C++ and project code style using env/bin/format-all-sources.py and clang-format. Use when the user asks to format code, fix style, run format check, or when lint fails due to formatting.

Run or design an experiment with fixed/varying variables, metrics, and recorded results. Use for ablations, evals, or hyperparameter runs.

Audit and clean unused files, dependencies, and manifest issues with Knip in this repository. Use when running `pnpm lint:knip` or `pnpm lint:knip:strict`, triaging findings, fixing real hygiene issues, or deciding whether a Knip finding should become a targeted ignore in `.knip.jsonc`.

Choose typefaces based on voice and context, not trends. Use when selecting fonts for a project, evaluating type choices, or understanding what a typeface communicates before anyone reads a word.

Visual weight, attention order, and the decisions that guide the eye. Use when building layouts, evaluating information architecture, or diagnosing why a design feels confusing.

Creates a complete NotebookLM learning package for any topic using the NLM CLI (`/Users/user/.local/bin/nlm`).

Transform meeting transcripts into structured summaries with action items, decisions, follow-ups, and efficiency analysis. Works with any meeting format.

pine-strategy-builder

Compare, evaluate, and upgrade SKILL.md skills. This skill should be used when introducing a new skill that overlaps with an existing one, checking if an installed skill has upstream updates, merging two skills with complementary strengths, evaluating whether a skill is worth installing, or auditing unused skills. Trigger phrases include 'compare skills', 'check for updates', 'merge skills', 'evaluate this skill', 'upgrade skill', 'audit skills'.

Git version control essentials and best practices. Use when working with git repositories, commits, branches, merges, rebases, remotes, or resolving conflicts. Triggers on git commands, branch operations, merge/rebase questions, or version control workflows.

Web scraping and data extraction from websites. Use when users need to extract data from web pages, scrape multiple URLs, gather structured information from websites, or collect data in bulk from online sources. Supports single-page scraping, multi-page crawling, and handling dynamic JavaScript-rendered content.

Fetch and display open todo items from Apple Notes, preserving the note's existing structure.

Research assistant for non-coding tasks -- planning, research, scheduling, information gathering

Use when playing sounds in hooks, notifications, or alerts. Reference for macOS/iOS system sounds with file paths and Michael's favorites by use case.

Quick reference for deciding where information should be stored across Claude sessions.

16S/amplicon metagenomics diversity and community analysis.

The `Alexa::ASK::Skill` resource creates an Alexa skill that enables customers to access new abilities\. For more information about developing a skill, see the [Build Skills with the Alexa Skills Kit

Clinics

Hiplot

Omics

Hiplot

Hiplot

Python

Hiplot

Distribution

Expert in GitHub workflows including issue management, PR operations, and branch conventions. Use when working with GitHub via MCP.

Follow bocpy commenting and documentation conventions. Use when: adding comments to C or Python files, writing docstrings, documenting structs or classes, adding Doxygen doc-comments, using Sphinx param style, suppressing linter warnings with noqa, or following flake8 style rules (Q000, D205, D209, N802).

Agent development guide providing build commands, code style guidelines, and development workflow instructions for the Terraphim AI project.

- Respond in Japanese

No agents currently active.

Create, manage, and control Gigabrain autonomous trading agents on Hyperliquid. Use when the user wants to create trading bots, manage agent wallets, configure trading strategies, enable/disable agents, check agent execution history, or get strategy suggestions. Full lifecycle from strategy design to wallet management and execution monitoring.

When the user wants to write content for a LinkedIn carousel, slide deck, or swipeable multi-slide format. Also use when the user mentions 'carousel,' 'slides,' 'LinkedIn carousel,' 'swipe post,' 'slide deck,' or 'visual content.' Outputs slide-by-slide text content (not visual design). For single posts, see post-writer-sms. For threads, see thread-writer-sms.

When the user wants to turn one piece of content into multiple formats or adapt content across platforms. Also use when the user mentions 'repurpose,' 'turn this into,' 'adapt this for,' 'cross-post,' 'reformat,' 'blog to social,' 'newsletter to posts,' or 'get more from this content.' For writing original posts, see post-writer-sms. For threads, see thread-writer-sms. For carousels, see carousel-writer-sms.

When the user wants to set up or update their social media profile, voice, audience, content pillars, or platform preferences. Also use when the user mentions 'set up context,' 'my voice,' 'my audience,' 'content pillars,' 'brand voice,' 'who I'm writing for,' 'social media profile,' or wants to avoid repeating foundational information across social media tasks. Use this at the start of any new project before using other social media skills — it creates .agents/social-media-context-sms.md that all other skills reference.

1. Get a GitHub Personal Access Token (PAT) with `read:user` scope

Programmatic access to KEGG via BioServices for pathway analysis, gene functions, and metabolic cross-referencing.

Query the wiki for information. Uses a tiered search strategy to minimize token usage. Synthesizes an answer with citations, and optionally files the result as a thread.

This skill helps determine appropriate version bumps following [Semantic Versioning](https://semver.org/).

Guidance for using FileDataSource and creating custom file reader extensions in BeepDM. Use when implementing or extending DataManagementEngineStandard/FileManager with new formats via IFileFormatReader and FileReaderFactory.