More screenshots
Works with the AI Agents you already use
pydoc
Look up real Python signatures, docstrings, and symbols directly from your local system environment.
$5
/moSubscription · cancel anytime
Secure checkout via Stripe
- Always the latest version
- Delivered live to your agent via MCP
- Cancel anytime, access ends at period end
pydoc
Example session with this skill installed
/pydoc json.dumps
- Read your context and instructions
- Compiled the pydoc
I have retrieved the documentation and signature for json.dumps from the system Python environment.
Python Documentation: json.dumps
| Attribute | Value |
|---|---|
| Fully Qualified Name | json.dumps |
| Signature | dumps(obj, *, skipkeys=False, ensure_ascii=True, check_circular=True, allow_nan=True, cls=None, indent=None, separators=None, default=None, sort_keys=False, **kw) |
| Module | json |
| Return Type | str |
Docstring
Serialize obj to a JSON formatted str.
If skipkeys is true then dict keys that are not basic types
(str, int, float, bool, None) will be skipped
instead of raising a TypeError.
If ensure_ascii is false, then the return value can contain non-ASCII
characters if they appear in strings contained in obj. Otherwise, all
such characters are escaped in JSON strings.
If check_circular is false, then the circular reference check
for container types will be skipped and a circular reference will
result in an RecursionError (or worse).
If allow_nan is false, then it will be a ValueError to
serialize out of range float values (nan, inf, -inf) in
strict compliance of the JSON specification, instead of using the
JavaScript equivalents (NaN, Infinity, -Infinity).
If indent is a non-negative integer, then JSON array elements and
object members will be pretty-printed with that indent level. An indent
level of 0 will only insert newlines. None (the default) selects the
most compact representation.
Next steps
- Run
/pydoc json.loadsto view the deserialization signature. - Use
/pydoc --list jsonto see all available functions in the json module. - Try
/pydoc --find json indentto find where the indent logic is handled.
Subscription · always the latest version
- Secure checkout via Stripe
- Cancel anytime
- Delivered live via MCP
About this skill
Stop guessing Python API signatures and relying on outdated training data. This skill provides direct access to the documentation, type annotations, and docstrings of any package or module installed in your local Python environment. It introspects the live system to ensure you are writing code against the actual versions currently running on your machine.
What it does
- Live Introspection retrieves real docstrings and signatures from the system Python interpreter.
- Deep Exploration documents nested subtrees of packages, classes, and modules with configurable depth.
- Symbol Discovery searches for functions, classes, or members using substring, glob, or regex patterns.
- Structural Listing enumerates the contents of specific packages or the entire top-level environment.
- Member Filtering isolates specific object types like methods, classes, or functions during searches.
How it works
- Run
/pydoc <name>to pull the full signature and docstring for a specific module, class, or function. - Use
/pydoc --listto browse available packages or see the internal structure of a specific root. - Use
/pydoc --findwith a query string to locate a symbol when you only know part of its name. - Apply flags like
--privateto include internal members or-rto recursively document a whole package.
Frameworks & tools
This skill runs on python3 (3.10+ recommended) using the Python standard library. It executes introspection scripts via Bash to query the local environment without external dependencies.
Why this beats prompting it yourself
General LLMs often hallucinate parameters or use outdated API versions. This skill queries your specific local installation, giving you the exact signatures and type hints present in your current environment.
Use cases
- Verify exact keyword arguments for an installed library function.
- Explore the internal structure and available methods of a new package.
- Locate a specific utility function across a large installed codebase.
- Check type annotations for complex objects to ensure IDE-like accuracy.
Known limitations
Requires system python3 (3.10+ recommended). It only sees packages installed in the system environment; virtualenv support is not explicitly provided.
Requires system python3 (3.10+ recommended). Only queries the system Python environment; no explicit virtualenv or third-party dependency isolation.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 12 days ago
Requires