elviskahoro/assistant-python icon
public
Published on 6/10/2025
Python

Prompts
Models
Context
anthropic Claude 3.7 Sonnet model icon

Claude 3.7 Sonnet

anthropic

200kinput·8.192koutput
anthropic Claude 3.5 Sonnet model icon

Claude 3.5 Sonnet

anthropic

200kinput·8.192koutput
mistral Codestral model icon

Codestral

mistral

voyage voyage-code-3 model icon

voyage-code-3

voyage

voyage Voyage AI rerank-2 model icon

Voyage AI rerank-2

voyage

together Llama 4 Maverick Instruct (17Bx128E) model icon

Llama 4 Maverick Instruct (17Bx128E)

together

gemini Gemini 2.5 Pro model icon

Gemini 2.5 Pro

gemini

1048kinput·65.536koutput
relace Relace Instant Apply model icon

Relace Instant Apply

relace

40kinput·32koutput
xAI Grok 2 model icon

Grok 2

xAI

openai OpenAI GPT-4o model icon

OpenAI GPT-4o

OpenAI

128kinput·16.384koutput
gemini Gemini 2.0 Flash model icon

Gemini 2.0 Flash

gemini

1048kinput·8.192koutput
together Llama 4 Scout Instruct (17Bx16E) model icon

Llama 4 Scout Instruct (17Bx16E)

together

openai Morph Fast Apply model icon

Morph Fast Apply

OpenAI

anthropic Claude 3.5 Haiku model icon

Claude 3.5 Haiku

anthropic

200kinput·8.192koutput
openai o3-mini model icon

o3-mini

OpenAI

200kinput·100koutput
voyage voyage-code-2 model icon

voyage-code-2

voyage

mistral Mistral Embed model icon

Mistral Embed

mistral

openai o1 model icon

o1

OpenAI

200kinput·100koutput
openai OpenAI GPT-4o Mini model icon

OpenAI GPT-4o Mini

OpenAI

128kinput·16.384koutput
ollama qwen2.5-coder 1.5b model icon

qwen2.5-coder 1.5b

ollama

32kinput·8.192koutput
ollama nomic-embed-text latest model icon

nomic-embed-text latest

ollama

lmstudio deepseek-r1 8b model icon

deepseek-r1 8b

lmstudio

novita llama-3.3-70b-instruct model icon

llama-3.3-70b-instruct

novita

lmstudio qwen2.5-coder 1.5b model icon

qwen2.5-coder 1.5b

lmstudio

ncompass Qwen 2.5 Coder 32b model icon

Qwen 2.5 Coder 32b

ncompass

mistral Mistral Large model icon

Mistral Large

mistral

deepinfra Qwen2.5 Coder 32B Instruct model icon

Qwen2.5 Coder 32B Instruct

deepinfra

ollama deepseek-r1 8b model icon

deepseek-r1 8b

ollama

128kinput·32.768koutput
sambanova DeepSeek R1 model icon

DeepSeek R1

sambanova

deepinfra DeepSeek R1 model icon

DeepSeek R1

deepinfra

anthropic CodeGate Anthropic model icon

CodeGate Anthropic

anthropic

novita deepseek-r1 model icon

deepseek-r1

novita

openai OpenAI text-embedding-3-large model icon

OpenAI text-embedding-3-large

OpenAI

anthropic Claude 4 Opus model icon

Claude 4 Opus

anthropic

200kinput·32koutput

No Rules configured

No Docs configured

Prompts

Learn more
prompt-changelog
Prompt for changelog
You are helping me write product changelog entries in a clean, narrative format. Each entry begins with a date heading (`##`) and is grouped by product area or feature using subheadings (`###`). Beneath each subheading, write one or more paragraphs that explain what was added, improved, or fixed — focusing on the value to the user. Use clear, professional language, and feel free to include contextual links, images, or short code snippets to demonstrate usage. **Do not use bullet points**. Write like a mini product update or blog post — informative, structured, and easy to read.
---
## Template for a New Changelog Entry

```md
## [Month Day, Year]

### [Feature or Area Title]

[Brief paragraph or two that describes the update, the motivation behind it, and the user-facing impact. Link to any relevant documentation or blog posts. Optional: include a code snippet if the update introduces a new API, config, or usage pattern.] ```

```python
# (optional code snippet to show usage)
```

---

## ✅ Full Example

```md ## January 22, 2025
### Chalk's C++ SQL Driver for Spanner now supports inputs (parameterized queries)

Chalk’s C++ driver now supports [Spanner](https://cloud.google.com/spanner) queries that explicitly accept input parameters.  
These resolvers now run faster, with some query latencies dropping from 24ms to 10ms.

### Enhanced visibility into your Chalk deployment

The Chalk query plan viewer now highlights nodes for [Chalk expressions](/docs/expression) and [SQL resolvers](https://docs.chalk.ai/docs/sql-resolvers) using Chalk's C++ driver in orange.  
Differentiate between various node types at a glance to debug Chalk queries in less time.

The Kubernetes resource page in the Chalk dashboard has been enhanced to include data from the Kubernetes events API, increasing visibility into nodes, pods, and more objects to come.  
Expanding the types of events and their granularity provides better insights into jobs. These include events like node removal, pod scheduling, and deployment failures.

The query plan viewer in the Chalk dashboard now supports breadcrumbs to hyperlink to a feature’s parent in the query plan viewer, enabling quicker traversal through a feature’s lineage.

![Colored nodes in Chalk's query plan viewer](/img/changelog-25_01_22-query_plan_viewer.png) ```
Noun and tense style guide
A style guide for balancing product-centric language with appropriate reader address
Help me revise technical documentation for Chalk by applying these guidelines:
## Product vs. Reader Focus
For technical documentation about Chalk, we need to balance two important principles:
1. **When describing product capabilities**: Focus on Chalk as the subject of sentences rather than the user
   - Highlight how Chalk enables and unlocks specific functionalities
   - Emphasize Chalk's capabilities and features
   - Use active voice where appropriate to describe what Chalk does
   - Frame user actions in terms of what Chalk makes possible

2. **When providing instructions or addressing the reader directly**: Use "you" and "your" appropriately
   - Address the reader as "you" rather than using "we," "our," or "us"
   - Assume the reader is the person performing tasks or making decisions
   - Use the imperative form for direct instructions (the "you" is implied)
   - Reserve the term "user" specifically for end users of the software that your reader is developing

## Examples of Product-Centric Transformations:
BEFORE: "You can analyze your data by clicking the dashboard button."   AFTER: "Chalk enables data analysis through the dashboard button."
BEFORE: "Your configuration settings allow you to customize the interface."   AFTER: "Chalk's configuration settings provide interface customization options."
BEFORE: "When you run this command, your system will update automatically."   AFTER: "Running this command prompts Chalk to update the system automatically."
## Examples of Appropriate Reader Address:
BEFORE: "The following sections describe how we can create a website."   AFTER: "The following sections describe how you can create a website."
BEFORE: "Let's add a description to our table."   AFTER: "Consider adding a description to your table."
BEFORE: "This document shows the user how to develop an app for their organization."   AFTER: "This document shows you how to develop an app for your organization."
## Guidelines for Instructions:
- For direct actions, use the imperative form: "Click Submit." - When establishing context before instructions: "You can obtain the IP address for the appliance from your network administrator. Store the address in a variable for future use." - Avoid mixing imperative instructions with narrative text. Consider formatting action steps as a procedure.
## First-Person Plural (We/Our/Us):
- Use first-person plural pronouns only when referring to Chalk's organization - Ensure the antecedent for "we," "our," or "us" is clear - Example: "Chalk provides A and B, but we don't provide C and D." - Example: "For more information, contact our support team."
## Audience Consistency:
- Identify clearly who "you" refers to (a developer? a sysadmin?) - Be consistent about audience throughout the document - Consider including an explicit audience statement near the beginning
Please review the text I provide and suggest revisions that balance these principles - using product-centric language where appropriate while maintaining clear, direct address to the reader when providing instructions or guidance.
Release notes
Release notes
You are helping to create simplified summaries of technical release notes. Your task is to:
      1. Summarize the technical changes into 3-5 bullet points (max)
      2. Focus on the most important changes or features
      3. Use simple, non-technical language that would be understandable to non-technical stakeholders
      4. Keep each bullet point short and concise
      5. Ensure the summary is professionally written

      Don't use introduction headers for each bullet, just write the bullet out as a partial sentence
      Use hyphen's for the actual bullet so instead of "*" use "-"

Context

Learn more
@diff
Reference all of the changes you've made to your current branch
@codebase
Reference the most relevant snippets from your codebase
@url
Reference the markdown converted contents of a given URL
@folder
Uses the same retrieval mechanism as @Codebase, but only on a single folder
@terminal
Reference the last command you ran in your IDE's terminal and its output
@code
Reference specific functions or classes from throughout your project
@file
Reference any file in your current workspace
@repo-map
Reference the outline of your codebase
@docs
Reference the contents from any documentation site
@currentFile
Reference the currently open file
@open
Reference the contents of all of your open files
@greptile
Query a Greptile index of the current repo/branch
@jira
Reference the conversation in a Jira issue
@problems
Get Problems from the current file
@os
Reference the architecture and platform of your current operating system
@commit
@clipboard
Reference recent clipboard items

No Data configured

MCP Servers

Learn more

Exa

npx -y exa-mcp-server

Memory

npx -y @modelcontextprotocol/server-memory

Browser MCP

npx -y @browsermcp/mcp@latest

Postgres

npx -y @modelcontextprotocol/server-postgres ${{ secrets.elviskahoro/assistant-python/anthropic/postgres-mcp/CONNECTION_STRING }}

GitHub

npx -y @modelcontextprotocol/server-github

Tavily Search

npx -y tavily-mcp@0.1.4

Filesystem

npx -y @modelcontextprotocol/server-filesystem ${{ secrets.elviskahoro/assistant-python/anthropic/filesystem-mcp/PATH }}