🧭

AutomationPython

Environment Discovery

Environment Discovery is an Automation skill for Claude Code, published by vstorm-co in pydantic-deepagents.

1K stars126 forkson vstorm-co/pydantic-deepagentsAdded 2026/08/21Repository updated 2026/08/20

View source on GitHub Download repo ZIP

agent-frameworkai-agentsanthropicclaude-codeclicoding-agentdeep-researchdocker-sandboxllmsmcpplaywrightpydanticpydantic-aipythonsubagentstuivstorm

Install in seconds

Install Environment Discovery

Copy Environment Discovery into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/vstorm-co/pydantic-deepagents/tree/main/pydantic_deep/bundled_skills/environment-discovery ~/.claude/skills/environment-discovery

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/vstorm-co/pydantic-deepagents.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: pydantic_deep/bundled_skills/environment-discovery/SKILL.md in vstorm-co/pydantic-deepagents
Installs to: ~/.claude/skills/environment-discovery
Collection: One of 14 skills cataloged from this repository
Category: Automation — 1523 skills

What Environment Discovery does

Environment Discovery guides an agent to inspect files, tools, and data formats before making changes. Use it when dropped into an unfamiliar workspace or when file contents, build tools, or dependencies are unknown.

Environment Discovery is cataloged under Automation on DirSkills. Environment Discovery comes from a repository tagged agent-framework, ai-agents, anthropic, claude-code and cli.

Documentation

README

Excerpt

Environment Discovery

When dropped into an unfamiliar environment, ALWAYS explore before acting.

Step 1: Understand the workspace

ls -la /app/          # or the working directory
find . -type f | head -50

What files exist? What are their sizes?
Are there READMEs, Makefiles, config files?
What languages/frameworks are involved?

Step 2: Inspect data files

Before writing any code that reads data, understand the format:

file <filename> — detect file type (binary, text, encoding)
head -20 <file> — first lines of text files
xxd <file> | head -20 — hex dump for binary files
wc -l <file> — line count for text files
stat <file> — exact file size in bytes
python3 -c "import struct; ..." — parse binary headers

Step 3: Check available tools

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Environment Discovery

What else does vstorm-co publish alongside Environment Discovery?
Environment Discovery is one of 14 skills that DirSkills catalogs from vstorm-co/pydantic-deepagents, the repository it ships in. Its siblings there include Build And Compile, Code Review and Code Review. Each one is a separate skill with its own page in this directory, installs the same way Environment Discovery does, and is maintained by vstorm-co in that same repository. The rest of the collection is listed on the vstorm-co/pydantic-deepagents page.
How does Environment Discovery compare to other Automation skills?
Environment Discovery ranks #828 by stars among the 1523 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Environment Discovery against them. Open each page to compare what they document and how they install.

More from vstorm-co/pydantic-deepagents

Environment Discovery is one of 14 skills cataloged on DirSkills from vstorm-co/pydantic-deepagents.

See all 14 skills →

Build And Compile

Build And Compile helps detect build systems, compile code, and resolve missing dependencies across languages. Use it when builds fail, libraries are missing, or link errors need fixing.

Code Review

Code Review reviews Python code for security, correctness, and best practices. Use it to assess structure, error handling, type hints, and documentation before merging changes.

Code Review

Code Review performs a systematic review for correctness, security, performance, style, and testing gaps. Use it to inspect changed code and report concrete issues with suggested fixes.

Data Formats

Data Formats helps inspect and parse binary, text, structured, and custom files. Use it when a file type is unknown, mixed, or needs format-specific handling.

Diagram Design

Diagram Design helps create research diagrams with Excalidraw MCP tools. Use it for comparisons, process flows, timelines, architectures, and other structured research findings.

Git Workflow

Git Workflow covers commit formatting, branching, pull requests, and conflict resolution. Use it when working through standard Git changes safely in a team setting.

More Automation skills

Environment Discovery is one of 1523 Automation skills cataloged on DirSkills, ranked #828 by stars among them.

Browse all Automation skills →

Autonomous Loops

Autonomous Loops provides patterns and reference implementations for running Claude Code in autonomous loops, from simple sequential pipelines to RFC-driven multi-agent DAG systems. Retained for compatibility; use continuous-agent-loop for new guidance.

Autonomous Agent Harness

Autonomous Agent Harness turns Claude Code into a self-directing agent system with persistent memory, scheduled tasks, computer use, and task queuing. Use it when continuous autonomous operation, scheduled tasks, or self-directing agent loops are needed.

Automation Audit Ops

Automation Audit Ops audits live automations, jobs, hooks, and connectors to identify what is working, broken, redundant, or missing before any fixes are made.