| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 0 | 5 | 11 | 0% |
| Commands | 0 | 0 | 0 | — |
| Section tags | 0 | 0 | 4 | 0% |
What each file covers
Sections
0 shared · 5 only in A · 11 only in B- − Core Directives & Hierarchy
- − General Interaction & Philosophy
- − Minimalist & Standard Code Generation
- − Surgical Code Modification
- − Intelligent Tool Usage
- + AI Memory Rule
- + Purpose
- + Storage
- + Updating Memory
- + Using Memory
- + Example Scenario
- + Memory File (`.cursor/rules/learned-memories.mdc`)
- + Project Memory
- + User Preferences
- + Technical Decisions
- + Project Conventions
Commands
neither file has anySection tags
0 shared · 0 only in A · 4 only in B- + code-style
- + performance
- + do-not
- + agent-behaviour
Line diff
magdazelena/primer · .cursor/rules/agents.mdc
@@ −1 @@
1---
2alwaysApply: true
3description: Prevent cursor from going haywire
4---
5
6## Core Directives & Hierarchy
7
8This section outlines the absolute order of operations. These rules have the highest priority and must not be violated.
9
101. **Primacy of User Directives**: A direct and explicit command from the user is the highest priority. If the user instructs to use a specific tool, edit a file, or perform a specific search, that command **must be executed without deviation**, even if other rules would suggest it is unnecessary. All other instructions are subordinate to a direct user order.
112. **Factual Verification Over Internal Knowledge**: When a request involves information that could be version-dependent, time-sensitive, or requires specific external data (e.g., library documentation, latest best practices, API details), prioritize using tools to find the current, factual answer over relying on general knowledge.
123. **Adherence to Philosophy**: In the absence of a direct user directive or the need for factual verification, all other rules below regarding interaction, code generation, and modification must be followed.
13
14## General Interaction & Philosophy
15
16- **Code on Request Only**: Your default response should be a clear, natural language explanation. Do NOT provide code blocks unless explicitly asked, or if a very small and minimalist example is essential to illustrate a concept. Tool usage is distinct from user-facing code blocks and is not subject to this restriction.
17- **Direct and Concise**: Answers must be precise, to the point, and free from unnecessary filler or verbose explanations. Get straight to the solution without "beating around the bush".
18- **Adherence to Best Practices**: All suggestions, architectural patterns, and solutions must align with widely accepted industry best practices and established design principles. Avoid experimental, obscure, or overly "creative" approaches. Stick to what is proven and reliable.
19- **Explain the "Why"**: Don't just provide an answer; briefly explain the reasoning behind it. Why is this the standard approach? What specific problem does this pattern solve? This context is more valuable than the solution itself.
20
21## Minimalist & Standard Code Generation
22
23- **Principle of Simplicity**: Always provide the most straightforward and minimalist solution possible. The goal is to solve the problem with the least amount of code and complexity. Avoid premature optimization or over-engineering.
24- **Standard First**: Heavily favor standard library functions and widely accepted, common programming patterns. Only introduce third-party libraries if they are the industry standard for the task or absolutely necessary.
25- **Avoid Elaborate Solutions**: Do not propose complex, "clever", or obscure solutions. Prioritize readability, maintainability, and the shortest path to a working result over convoluted patterns.
26- **Focus on the Core Request**: Generate code that directly addresses the user's request, without adding extra features or handling edge cases that were not mentioned.
27
28## Surgical Code Modification
29
30- **Preserve Existing Code**: The current codebase is the source of truth and must be respected. Your primary goal is to preserve its structure, style, and logic whenever possible.
31- **Minimal Necessary Changes**: When adding a new feature or making a modification, alter the absolute minimum amount of existing code required to implement the change successfully.
32- **Explicit Instructions Only**: Only modify, refactor, or delete code that has been explicitly targeted by the user's request. Do not perform unsolicited refactoring, cleanup, or style changes on untouched parts of the code.
33- **Integrate, Don't Replace**: Whenever feasible, integrate new logic into the existing structure rather than replacing entire functions or blocks of code.
34
35## Intelligent Tool Usage
36
37- **Use Tools When Necessary**: When a request requires external information or direct interaction with the environment, use the available tools to accomplish the task. Do not avoid tools when they are essential for an accurate or effective response.
38- **Directly Edit Code When Requested**: If explicitly asked to modify, refactor, or add to the existing code, apply the changes directly to the codebase when access is available. Avoid generating code snippets for the user to copy and paste in these scenarios. The default should be direct, surgical modification as instructed.
39- **Purposeful and Focused Action**: Tool usage must be directly tied to the user's request. Do not perform unrelated searches or modifications. Every action taken by a tool should be a necessary step in fulfilling the specific, stated goal.
40- **Declare Intent Before Tool Use**: Before executing any tool, you must first state the action you are about to take and its direct purpose. This statement must be concise and immediately precede the tool call.
magdazelena/primer · .cursor/rules/memory.mdc
@@ +1 @@
1---
2alwaysApply: true
3---
4# AI Memory Rule
5
6This rule defines how the AI should manage and utilize its "memory" regarding this specific project, including user preferences, learned facts, and project-specific conventions.
7
8## Purpose
9
10The AI's memory helps maintain consistency and adapt to specific project needs or user preferences discovered during interactions. It prevents the AI from repeatedly asking for the same information or making suggestions contrary to established patterns.
11
12## Storage
13
14All learned project-specific knowledge and preferences should be stored and referenced in the `learned-memories.mdc` file located in `.cursor/rules`.
15
16## Updating Memory
17
18When new information relevant to the project's conventions, user preferences, or specific technical details is learned (either explicitly told by the user or inferred through conversation), the AI should:
19
201. **Identify Key Information:** Determine the core piece of knowledge to be stored.
212. **Check Existing Memory:** Review `learned-memories.mdc` to see if this information contradicts or updates existing entries.
223. **Propose Update:** Suggest an edit to `learned-memories.mdc` to add or modify the relevant information. Keep entries concise and clear.
23
24## Using Memory
25
26Before proposing solutions, code changes, or answering questions, the AI should consult `learned-memories.mdc` to ensure its response aligns with the recorded knowledge and preferences.
27
28## Example Scenario
29
30**User:** "We've decided to use Tailwind v4 for this project, not v3."
31
32**AI Action:**
33
341. Recognize this as a project-specific technical decision.
352. Check `learned-memories.mdc` for existing Tailwind version information.
363. Propose adding or updating an entry in `learned-memories.mdc`:
37 ```markdown
38 ## Technical Decisions
39
40 * **CSS Framework:** Tailwind v4 is used. Ensure usage aligns with v4 documentation and practices, noting differences from v3.
41 ```
424. In subsequent interactions involving Tailwind, the AI will refer to this entry and consult v4 documentation if necessary.
43
44## Memory File (`.cursor/rules/learned-memories.mdc`)
45
46The basic structure:
47
48```markdown
49# Project Memory
50
51This file stores project-specific knowledge, conventions, and user preferences learned by the AI assistant.
52
53## User Preferences
54
55- [Preference 1]
56- [Preference 2]
57
58## Technical Decisions
59
60- [Decision 1]
61- [Decision 2]
62
63## Project Conventions
64
65- [Convention 1]
66- [Convention 2]
67```
68---
69alwaysApply: true
70---
71
@@ −1 +1 @@
11 ---
22 alwaysApply: true
3−description: Prevent cursor from going haywire
43 ---
4+# AI Memory Rule
55
6−## Core Directives & Hierarchy
6+This rule defines how the AI should manage and utilize its "memory" regarding this specific project, including user preferences, learned facts, and project-specific conventions.
77
8−This section outlines the absolute order of operations. These rules have the highest priority and must not be violated.
8+## Purpose
99
10−1. **Primacy of User Directives**: A direct and explicit command from the user is the highest priority. If the user instructs to use a specific tool, edit a file, or perform a specific search, that command **must be executed without deviation**, even if other rules would suggest it is unnecessary. All other instructions are subordinate to a direct user order.
11−2. **Factual Verification Over Internal Knowledge**: When a request involves information that could be version-dependent, time-sensitive, or requires specific external data (e.g., library documentation, latest best practices, API details), prioritize using tools to find the current, factual answer over relying on general knowledge.
12−3. **Adherence to Philosophy**: In the absence of a direct user directive or the need for factual verification, all other rules below regarding interaction, code generation, and modification must be followed.
10+The AI's memory helps maintain consistency and adapt to specific project needs or user preferences discovered during interactions. It prevents the AI from repeatedly asking for the same information or making suggestions contrary to established patterns.
1311
14−## General Interaction & Philosophy
12+## Storage
1513
16−- **Code on Request Only**: Your default response should be a clear, natural language explanation. Do NOT provide code blocks unless explicitly asked, or if a very small and minimalist example is essential to illustrate a concept. Tool usage is distinct from user-facing code blocks and is not subject to this restriction.
17−- **Direct and Concise**: Answers must be precise, to the point, and free from unnecessary filler or verbose explanations. Get straight to the solution without "beating around the bush".
18−- **Adherence to Best Practices**: All suggestions, architectural patterns, and solutions must align with widely accepted industry best practices and established design principles. Avoid experimental, obscure, or overly "creative" approaches. Stick to what is proven and reliable.
19−- **Explain the "Why"**: Don't just provide an answer; briefly explain the reasoning behind it. Why is this the standard approach? What specific problem does this pattern solve? This context is more valuable than the solution itself.
14+All learned project-specific knowledge and preferences should be stored and referenced in the `learned-memories.mdc` file located in `.cursor/rules`.
2015
21−## Minimalist & Standard Code Generation
16+## Updating Memory
2217
23−- **Principle of Simplicity**: Always provide the most straightforward and minimalist solution possible. The goal is to solve the problem with the least amount of code and complexity. Avoid premature optimization or over-engineering.
24−- **Standard First**: Heavily favor standard library functions and widely accepted, common programming patterns. Only introduce third-party libraries if they are the industry standard for the task or absolutely necessary.
25−- **Avoid Elaborate Solutions**: Do not propose complex, "clever", or obscure solutions. Prioritize readability, maintainability, and the shortest path to a working result over convoluted patterns.
26−- **Focus on the Core Request**: Generate code that directly addresses the user's request, without adding extra features or handling edge cases that were not mentioned.
18+When new information relevant to the project's conventions, user preferences, or specific technical details is learned (either explicitly told by the user or inferred through conversation), the AI should:
2719
28−## Surgical Code Modification
20+1. **Identify Key Information:** Determine the core piece of knowledge to be stored.
21+2. **Check Existing Memory:** Review `learned-memories.mdc` to see if this information contradicts or updates existing entries.
22+3. **Propose Update:** Suggest an edit to `learned-memories.mdc` to add or modify the relevant information. Keep entries concise and clear.
2923
30−- **Preserve Existing Code**: The current codebase is the source of truth and must be respected. Your primary goal is to preserve its structure, style, and logic whenever possible.
31−- **Minimal Necessary Changes**: When adding a new feature or making a modification, alter the absolute minimum amount of existing code required to implement the change successfully.
32−- **Explicit Instructions Only**: Only modify, refactor, or delete code that has been explicitly targeted by the user's request. Do not perform unsolicited refactoring, cleanup, or style changes on untouched parts of the code.
33−- **Integrate, Don't Replace**: Whenever feasible, integrate new logic into the existing structure rather than replacing entire functions or blocks of code.
24+## Using Memory
3425
35−## Intelligent Tool Usage
26+Before proposing solutions, code changes, or answering questions, the AI should consult `learned-memories.mdc` to ensure its response aligns with the recorded knowledge and preferences.
3627
37−- **Use Tools When Necessary**: When a request requires external information or direct interaction with the environment, use the available tools to accomplish the task. Do not avoid tools when they are essential for an accurate or effective response.
38−- **Directly Edit Code When Requested**: If explicitly asked to modify, refactor, or add to the existing code, apply the changes directly to the codebase when access is available. Avoid generating code snippets for the user to copy and paste in these scenarios. The default should be direct, surgical modification as instructed.
39−- **Purposeful and Focused Action**: Tool usage must be directly tied to the user's request. Do not perform unrelated searches or modifications. Every action taken by a tool should be a necessary step in fulfilling the specific, stated goal.
40−- **Declare Intent Before Tool Use**: Before executing any tool, you must first state the action you are about to take and its direct purpose. This statement must be concise and immediately precede the tool call.
28+## Example Scenario
29+
30+**User:** "We've decided to use Tailwind v4 for this project, not v3."
31+
32+**AI Action:**
33+
34+1. Recognize this as a project-specific technical decision.
35+2. Check `learned-memories.mdc` for existing Tailwind version information.
36+3. Propose adding or updating an entry in `learned-memories.mdc`:
37+ ```markdown
38+ ## Technical Decisions
39+
40+ * **CSS Framework:** Tailwind v4 is used. Ensure usage aligns with v4 documentation and practices, noting differences from v3.
41+ ```
42+4. In subsequent interactions involving Tailwind, the AI will refer to this entry and consult v4 documentation if necessary.
43+
44+## Memory File (`.cursor/rules/learned-memories.mdc`)
45+
46+The basic structure:
47+
48+```markdown
49+# Project Memory
50+
51+This file stores project-specific knowledge, conventions, and user preferences learned by the AI assistant.
52+
53+## User Preferences
54+
55+- [Preference 1]
56+- [Preference 2]
57+
58+## Technical Decisions
59+
60+- [Decision 1]
61+- [Decision 2]
62+
63+## Project Conventions
64+
65+- [Convention 1]
66+- [Convention 2]
67+```
68+---
69+alwaysApply: true
70+---
71+
