behavioral-guidelines

Name: behavioral-guidelines
Author: ThibautBaissac

635stars79forks

How to install behavioral-guidelines?

thibautbaissac/rails_ai_agents/behavioral-guidelines

$npx -y skills add ThibautBaissac/rails_ai_agents --skill behavioral-guidelines

Installs into the current project.

Summary

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Files · 1

View on GitHub

SKILL.md

1	# Guidelines
2
3	Behavioral guidelines to reduce common LLM coding mistakes.
4
5	Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.
6
7	## 1. Think Before Coding
8
9	Don't assume. Don't hide confusion. Surface tradeoffs.
10
11	Before implementing:
12	- State your assumptions explicitly. If uncertain, ask.
13	- If multiple interpretations exist, present them - don't pick silently.
14	- If a simpler approach exists, say so. Push back when warranted.
15	- If something is unclear, stop. Name what's confusing. Ask.
16
17	## 2. Simplicity First
18
19	Minimum code that solves the problem. Nothing speculative.
20
21	- No features beyond what was asked.
22	- No abstractions for single-use code.
23	- No "flexibility" or "configurability" that wasn't requested.
24	- No error handling for impossible scenarios.
25	- If you write 200 lines and it could be 50, rewrite it.
26
27	Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
28
29	## 3. Surgical Changes
30
31	Touch only what you must. Clean up only your own mess.
32
33	When editing existing code:
34	- Don't "improve" adjacent code, comments, or formatting.
35	- Don't refactor things that aren't broken.
36	- Match existing style, even if you'd do it differently.
37	- If you notice unrelated dead code, mention it - don't delete it.
38
39	When your changes create orphans:
40	- Remove imports/variables/functions that YOUR changes made unused.
41	- Don't remove pre-existing dead code unless asked.
42
43	The test: Every changed line should trace directly to the user's request.
44
45	## 4. Goal-Driven Execution
46
47	Define success criteria. Loop until verified.
48
49	Transform tasks into verifiable goals:
50	- "Add validation" → "Write tests for invalid inputs, then make them pass"
51	- "Fix the bug" → "Write a test that reproduces it, then make it pass"
52	- "Refactor X" → "Ensure tests pass before and after"
53
54	For multi-step tasks, state a brief plan:
55	```
56	1. [Step] → verify: [check]
57	2. [Step] → verify: [check]
58	3. [Step] → verify: [check]
59	```
60
61	Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.

People who liked this also viewed

6 picks

Type

behavioral-guidelines

635stars79forks

View on GitHub

How to install behavioral-guidelines?

thibautbaissac/rails_ai_agents/behavioral-guidelines

$npx -y skills add ThibautBaissac/rails_ai_agents --skill behavioral-guidelines

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Guidelines
2
3	Behavioral guidelines to reduce common LLM coding mistakes.
4
5	Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.
6
7	## 1. Think Before Coding
8
9	Don't assume. Don't hide confusion. Surface tradeoffs.
10
11	Before implementing:
12	- State your assumptions explicitly. If uncertain, ask.
13	- If multiple interpretations exist, present them - don't pick silently.
14	- If a simpler approach exists, say so. Push back when warranted.
15	- If something is unclear, stop. Name what's confusing. Ask.
16
17	## 2. Simplicity First
18
19	Minimum code that solves the problem. Nothing speculative.
20
21	- No features beyond what was asked.
22	- No abstractions for single-use code.
23	- No "flexibility" or "configurability" that wasn't requested.
24	- No error handling for impossible scenarios.
25	- If you write 200 lines and it could be 50, rewrite it.
26
27	Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
28
29	## 3. Surgical Changes
30
31	Touch only what you must. Clean up only your own mess.
32
33	When editing existing code:
34	- Don't "improve" adjacent code, comments, or formatting.
35	- Don't refactor things that aren't broken.
36	- Match existing style, even if you'd do it differently.
37	- If you notice unrelated dead code, mention it - don't delete it.
38
39	When your changes create orphans:
40	- Remove imports/variables/functions that YOUR changes made unused.
41	- Don't remove pre-existing dead code unless asked.
42
43	The test: Every changed line should trace directly to the user's request.
44
45	## 4. Goal-Driven Execution
46
47	Define success criteria. Loop until verified.
48
49	Transform tasks into verifiable goals:
50	- "Add validation" → "Write tests for invalid inputs, then make them pass"
51	- "Fix the bug" → "Write a test that reproduces it, then make it pass"
52	- "Refactor X" → "Ensure tests pass before and after"
53
54	For multi-step tasks, state a brief plan:
55	```
56	1. [Step] → verify: [check]
57	2. [Step] → verify: [check]
58	3. [Step] → verify: [check]
59	```
60
61	Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.

People who liked this also viewed

6 picks

Type