remember-interactive-programming
github/awesome-copilot
A micro-prompt that keeps your agent thinking and working like a REPL-driven interactive programmer.
What is remember-interactive-programming?
A micro-prompt skill that reminds an AI coding agent to act as an interactive programmer, using a live REPL as the source of truth for exploring and modifying a system. It's intended for REPL-driven workflows like Clojure with Backseat Driver, prompting the agent to summarize evaluations, use structural editing, and maintain its todo list.
- Reminds the agent to treat the live system/REPL as its source of truth
- Directs the agent to use the REPL to explore and modify the system to understand needed changes
- Instructs the agent to succinctly describe large code evaluations since the human can't see them
- Encourages preference for structural editing tools when editing files
- Prompts the agent to maintain and tend its todo list
How to install remember-interactive-programming
npx skills add https://github.com/github/awesome-copilot --skill remember-interactive-programming- A live REPL accessible to the agent (e.g., Clojure with Backseat Driver, or another system with REPL access)
- Structural editing tools available for the agent to use when editing files
How to use remember-interactive-programming
- 1.Install the skill into your agent's skill directory.
- 2.Ensure your environment provides the agent with a live REPL (e.g., Clojure via Backseat Driver).
- 3.Invoke or load the skill so the agent adopts the interactive-programmer mindset during a session.
- 4.Optionally edit the prompt text to add workflow- or workspace-specific reminders.
- 5.Work with the agent as it uses the REPL to explore and modify the system, prefers structural editing tools, and maintains a todo list.
Use cases
- Working in a Clojure project where Copilot has REPL access via Backseat Driver
- Reminding the agent to explore and verify changes live in the system rather than guessing
- Ensuring the agent summarizes large code evaluations for human readability
- Encouraging use of structural editing tools instead of raw text edits
- Keeping the agent's todo list maintained during a coding session
- Clojure developers using REPL-driven workflows
- Developers using Copilot with Backseat Driver or similar REPL integrations
- Anyone working with an AI agent in a live REPL environment
remember-interactive-programming FAQ
Yes, it is designed for systems where the agent has access to a live REPL, such as Clojure with Backseat Driver, but it can work with any system offering a live REPL.
No, it's a micro-prompt that reframes the agent's behavior; it relies on existing REPL and editing tool access already available to the agent.
Yes, the description explicitly suggests adapting the prompt with reminders specific to your workflow or workspace.
It instructs the agent to succinctly describe what is being evaluated, since the human does not see the actual evaluation output.
Full instructions (SKILL.md)
Source of truth, from github/awesome-copilot.
name: remember-interactive-programming description: 'A micro-prompt that reminds the agent that it is an interactive programmer. Works great in Clojure when Copilot has access to the REPL (probably via Backseat Driver). Will work with any system that has a live REPL that the agent can use. Adapt the prompt with any specific reminders in your workflow and/or workspace.'
Remember that you are an interactive programmer with the system itself as your source of truth. You use the REPL to explore the current system and to modify the current system in order to understand what changes need to be made.
Remember that the human does not see what you evaluate with the tool:
- If you evaluate a large amount of code: describe in a succinct way what is being evaluated.
When editing files you prefer to use the structural editing tools.
Also remember to tend your todo list.
Related skills
More from github/awesome-copilot and the wider catalog.
git-commit
Execute semantic git commits with conventional message analysis and intelligent staging.
excalidraw-diagram-generator
Generate Excalidraw diagrams from natural language descriptions.
documentation-writer
Create structured technical documentation using the Diátaxis framework for tutorials, how-to guides, references, and explanations.
gh-cli
GitHub CLI comprehensive reference for repositories, issues, PRs, Actions, projects, releases, and all GitHub operations from the command line.
prd
Generate comprehensive Product Requirements Documents with executive summaries, user stories, technical specs, and risk analysis.
refactor
Surgical code refactoring to improve maintainability without changing behavior.