Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →omnigent-ai/api-docs
Document a module or public API surface (functions, classes, CLI commands, endpoints) from the code itself.
3 of 22 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 4 comparable cases; this report requires 8.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
I want you to document `lib/cache/redis.py`. Before drafting the reference document, state how you will discover the exact public entry points, signatures, and default values from the source files.
| Checked | Without skill | With skill |
|---|---|---|
| Specifies using a research task with exploration purpose to analyze source signatures. | Missed | Passed |
| Requires collecting file and line locations as evidence during code exploration. | Missed | Passed |
The instructions your model reads when the skill loads.
Produce reference docs that match the code exactly, derived from the source, not from assumptions about what the API "probably" does.
Identify the public surface to document (a module, class, CLI command group, or set of endpoints). Then have the researcher read it carefully:
purpose: explore) to enumerate the public
entry points and report each one's real signature, parameters, defaults,
return shape, and raised errors — with file:line evidence.__all__ / export list).For each entry point:
### `<name>(<signature>)`
<one-line summary of what it does>
**Parameters**
- `<name>` (`<type>`, default `<value>`) — <meaning>
**Returns** — `<type>`: <meaning>
**Raises** — `<Error>`: <when>
**Example**
```
<minimal, runnable usage>
```
test cases passed with the skill
More skills from the same source and nearby in the registry, with their headline benchmark lift.