antivibe

Name: antivibe
Author: mohi-devhub

662stars42forks

How to install antivibe?

mohi-devhub/antivibe/antivibe

$npx -y skills add mohi-devhub/antivibe --skill antivibe

Installs into the current project.

Summary

Code learning and audit framework. Analyze any codebase — new, legacy, or AI-generated — and produce educational explanations or architectural audits. Use when the user wants to understand WHAT and WHY behind any code, not just accept it.

Files · 1

View on GitHub

SKILL.md

1	# AntiVibe - Code Learning & Audit Framework
2
3	## Purpose
4
5	AntiVibe generates learning-focused explanations or architectural audits of any code — AI-generated, legacy, or otherwise. It helps developers understand:
6	- What the code does (functionality)
7	- Why it was written this way (design decisions)
8	- When to use these patterns (context)
9	- What alternatives exist (broader knowledge)
10
11	Works on any codebase — you don't need recent git history or AI-authored files.
12
13	## When to Use
14
15	Use AntiVibe when:
16	1. Manual invocation: User types `/antivibe` or "deep dive"
17	2. Post-task learning: After a feature/phase completes, user wants to learn from it
18	3. Legacy codebases: User wants to understand existing code they didn't write
19	4. Proactive: User says "explain what AI wrote", "walk me through", "audit this", or points at a file/directory
20
21	## What AntiVibe Produces
22
23	Output saved to `deep-dive/` folder as markdown:
24
25	```
26	deep-dive/
27	├── auth-system-2026-01-15.md
28	├── api-layer-2026-01-15.md
29	└── database-models-2026-01-15.md
30	```
31
32	The exact sections depend on the output mode (see [Output Mode](#output-mode)):
33
34	\| Section \| `compact` (default) \| `full` \|
35	\|---------\|:---:\|:---:\|
36	\| Overview — what the code does and why it exists \| ✅ \| ✅ \|
37	\| Key Components / Concepts — design patterns, algorithms, CS concepts used \| ✅ \| ✅ \|
38	\| Code Walkthrough — file-by-file, line-by-line notes \| — \| ✅ \|
39	\| Learning Resources — curated docs, tutorials, videos \| — \| ✅ \|
40	\| Related Code — links to other files in the codebase \| — \| ✅ \|
41
42	## Configuration
43
44	### Known Concepts (Skip List)
45
46	Concepts listed here will not be explained in full — the explainer will only note that they were used and in what context. Edit this list to match your current knowledge.
47
48	```yaml
49	known_concepts:
50	- async/await
51	- React hooks
52	- REST APIs
53	```
54
55	### Output Mode
56
57	Controls how much detail is generated per run. Default is `compact` to keep token costs low.
58
59	```yaml
60	output_mode: compact
61	```
62
63	\| Mode \| What's included \|
64	\|------\|----------------\|
65	\| `compact` (default) \| Overview, key components (function-level, one line each), concepts (what + why only). No resources. No line-by-line. Max 5 files. \|
66	\| `full` \| Everything in compact, plus: line-by-line walkthrough, prerequisites, curated resources, Next Steps. \|
67
68	Override inline in your request:
69	- `"/antivibe full"`, `"full deep dive"`, `"include resources"` → `full` mode
70	- Default: `compact`
71
72	### Default Skill Level
73
74	Sets the explanation depth when no level is specified in the request. Options: `junior`, `mid`, `senior`. Default: `mid`.
75
76	```yaml
77	default_level: mid
78	```
79
80	\| Level \| Behavior \|
81	\|-------\|----------\|
82	\| `junior` \| Define all terms. Use analogies. Explain language features. Show full code snippets with inline comments. \|
83	\| `mid` \| Skip basics. Focus on design decisions and trade-offs. Brief code references only. \|
84	\| `senior` \| Skip obvious patterns. Focus only on non-obvious choices, edge cases, and architectural trade-offs. \|
85
86	Level can also be specified inline in the request:
87	- `"explain for a junior"`, `"I'm new to this"` → `junior`
88	- `"I know the basics"`, `"mid level"` → `mid`
89	- `"senior mode"`, `"skip the basics"`, `"just the trade-offs"` → `senior`
90
91	---
92
93	## Workflow
94
95	### Step 0: Apply User Configuration
96	Before analyzing, read the configuration above:
97	- Load the `known_concepts` skip list. Any concept in this list will be acknowledged in one sentence instead of fully explained.
98	- Detect the skill level: check the user's request first (inline phrases take priority), then fall back to `default_level`. Apply this level consistently throughout the entire output.
99	- If level = `senior`, route to `agents/auditor.md` instead of continuing this workflow.
100
101	### Step 1: Identify Code to Analyze
102
103	Use the first applicable mode:
104
105	1. Explicit — User named specific files, a directory, or a module in their request → use those directly. No git needed. Example: "explain `src/auth/`" or "walk me through `api/routes.py`".
106
107	2. Recent — No explicit target given, project is a git repo, and `git diff HEAD` has output → use those changed files (current behavior for post-AI-task learning).
108
109	3. Scan — No explicit target, no usable gi

People who liked this also viewed

6 picks

Type

antivibe

662stars42forks

View on GitHub

How to install antivibe?

mohi-devhub/antivibe/antivibe

$npx -y skills add mohi-devhub/antivibe --skill antivibe

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# AntiVibe - Code Learning & Audit Framework
2
3	## Purpose
4
5	AntiVibe generates learning-focused explanations or architectural audits of any code — AI-generated, legacy, or otherwise. It helps developers understand:
6	- What the code does (functionality)
7	- Why it was written this way (design decisions)
8	- When to use these patterns (context)
9	- What alternatives exist (broader knowledge)
10
11	Works on any codebase — you don't need recent git history or AI-authored files.
12
13	## When to Use
14
15	Use AntiVibe when:
16	1. Manual invocation: User types `/antivibe` or "deep dive"
17	2. Post-task learning: After a feature/phase completes, user wants to learn from it
18	3. Legacy codebases: User wants to understand existing code they didn't write
19	4. Proactive: User says "explain what AI wrote", "walk me through", "audit this", or points at a file/directory
20
21	## What AntiVibe Produces
22
23	Output saved to `deep-dive/` folder as markdown:
24
25	```
26	deep-dive/
27	├── auth-system-2026-01-15.md
28	├── api-layer-2026-01-15.md
29	└── database-models-2026-01-15.md
30	```
31
32	The exact sections depend on the output mode (see [Output Mode](#output-mode)):
33
34	\| Section \| `compact` (default) \| `full` \|
35	\|---------\|:---:\|:---:\|
36	\| Overview — what the code does and why it exists \| ✅ \| ✅ \|
37	\| Key Components / Concepts — design patterns, algorithms, CS concepts used \| ✅ \| ✅ \|
38	\| Code Walkthrough — file-by-file, line-by-line notes \| — \| ✅ \|
39	\| Learning Resources — curated docs, tutorials, videos \| — \| ✅ \|
40	\| Related Code — links to other files in the codebase \| — \| ✅ \|
41
42	## Configuration
43
44	### Known Concepts (Skip List)
45
46	Concepts listed here will not be explained in full — the explainer will only note that they were used and in what context. Edit this list to match your current knowledge.
47
48	```yaml
49	known_concepts:
50	- async/await
51	- React hooks
52	- REST APIs
53	```
54
55	### Output Mode
56
57	Controls how much detail is generated per run. Default is `compact` to keep token costs low.
58
59	```yaml
60	output_mode: compact
61	```
62
63	\| Mode \| What's included \|
64	\|------\|----------------\|
65	\| `compact` (default) \| Overview, key components (function-level, one line each), concepts (what + why only). No resources. No line-by-line. Max 5 files. \|
66	\| `full` \| Everything in compact, plus: line-by-line walkthrough, prerequisites, curated resources, Next Steps. \|
67
68	Override inline in your request:
69	- `"/antivibe full"`, `"full deep dive"`, `"include resources"` → `full` mode
70	- Default: `compact`
71
72	### Default Skill Level
73
74	Sets the explanation depth when no level is specified in the request. Options: `junior`, `mid`, `senior`. Default: `mid`.
75
76	```yaml
77	default_level: mid
78	```
79
80	\| Level \| Behavior \|
81	\|-------\|----------\|
82	\| `junior` \| Define all terms. Use analogies. Explain language features. Show full code snippets with inline comments. \|
83	\| `mid` \| Skip basics. Focus on design decisions and trade-offs. Brief code references only. \|
84	\| `senior` \| Skip obvious patterns. Focus only on non-obvious choices, edge cases, and architectural trade-offs. \|
85
86	Level can also be specified inline in the request:
87	- `"explain for a junior"`, `"I'm new to this"` → `junior`
88	- `"I know the basics"`, `"mid level"` → `mid`
89	- `"senior mode"`, `"skip the basics"`, `"just the trade-offs"` → `senior`
90
91	---
92
93	## Workflow
94
95	### Step 0: Apply User Configuration
96	Before analyzing, read the configuration above:
97	- Load the `known_concepts` skip list. Any concept in this list will be acknowledged in one sentence instead of fully explained.
98	- Detect the skill level: check the user's request first (inline phrases take priority), then fall back to `default_level`. Apply this level consistently throughout the entire output.
99	- If level = `senior`, route to `agents/auditor.md` instead of continuing this workflow.
100
101	### Step 1: Identify Code to Analyze
102
103	Use the first applicable mode:
104
105	1. Explicit — User named specific files, a directory, or a module in their request → use those directly. No git needed. Example: "explain `src/auth/`" or "walk me through `api/routes.py`".
106
107	2. Recent — No explicit target given, project is a git repo, and `git diff HEAD` has output → use those changed files (current behavior for post-AI-task learning).
108
109	3. Scan — No explicit target, no usable gi

People who liked this also viewed

6 picks

Type