code-quality

Name: code-quality
Author: fusengine

48installs3forks

How to install code-quality?

fusengine/agents/code-quality

$npx -y skills add fusengine/agents --skill code-quality

Installs into the current project.

Summary

Code quality validation with linters, SOLID principles, DRY detection, error detection, and architecture compliance across all languages. Use when: validating code quality after modifications — SOLID compliance, DRY duplication, linter errors, or architecture violations. Do NOT u

Files · 1

View on GitHub

SKILL.md

1	# Code Quality Skill
2
3	Canonical workflow definition: `agents/sniper.md` (this skill and the sniper agent share the same 7-phase workflow — update both together).
4
5	## 🚨 MANDATORY 7-PHASE WORKFLOW
6
7	```
8	PHASE 1: Exploration (explore-codebase) → BLOCKER
9	PHASE 2: Documentation (research-expert) → BLOCKER
10	PHASE 3: Impact Analysis (Grep usages) → BLOCKER
11	PHASE 3.5: DRY Detection (jscpd duplication) → NON-BLOCKING
12	PHASE 4: Error Detection (linters)
13	PHASE 5: Precision Correction (with docs + impact + DRY)
14	PHASE 6: Verification (re-run linters, tests, duplication)
15	```
16
17	CRITICAL: Phases 1-3 are BLOCKERS. Never skip them.
18	DRY: Phase 3.5 is non-blocking but findings inform Phase 5 corrections.
19
20	---
21
22	## PHASE 1: Architecture Exploration
23
24	Launch explore-codebase agent FIRST:
25	```
26	> Agent(subagent_type="fuse-ai-pilot:explore-codebase", prompt="...")
27	```
28
29	Gather:
30	1. Programming language(s) detected
31	2. Existing linter configs (.eslintrc, .prettierrc, pyproject.toml)
32	3. Package managers and installed linters
33	4. Project structure and conventions
34	5. Framework versions (package.json, go.mod, Cargo.toml)
35	6. Architecture patterns (Clean, Hexagonal, MVC)
36	7. State management (Zustand, Redux, Context)
37	8. Interface/types directories location
38
39	---
40
41	## PHASE 2: Documentation Research
42
43	Launch research-expert agent:
44	```
45	> Agent(subagent_type="fuse-ai-pilot:research-expert", prompt="Verify [library/framework] documentation for [error type]. Find [language] best practices for [specific issue].")
46	```
47
48	Request for each error:
49	- Official API documentation
50	- Current syntax and deprecations
51	- Best practices for error patterns
52	- Version-specific breaking changes
53	- Security advisories
54	- Language-specific SOLID patterns
55
56	---
57
58	## PHASE 3: Impact Analysis
59
60	For EACH element to modify: Grep usages → assess risk → document impact.
61
62	\| Risk \| Criteria \| Action \|
63	\|------\|----------\|--------\|
64	\| 🟢 LOW \| Internal, 0-1 usages \| Proceed \|
65	\| 🟡 MEDIUM \| 2-5 usages, compatible \| Proceed with care \|
66	\| 🔴 HIGH \| 5+ usages OR breaking \| Flag to user FIRST \|
67
68	---
69
70	## PHASE 3.5: Code Duplication Detection (DRY)
71
72	Tool: `jscpd` — 150+ languages — `npx jscpd ./src --threshold 5 --reporters console,json`
73
74	\| Level \| Threshold \| Action \|
75	\|-------\|-----------\|--------\|
76	\| 🟢 Excellent \| < 3% \| No action needed \|
77	\| 🟡 Good \| 3-5% \| Document, fix if time \|
78	\| 🟠 Acceptable \| 5-10% \| Extract shared logic \|
79	\| 🔴 Critical \| > 10% \| Mandatory refactoring \|
80
81	See [references/duplication-thresholds.md](references/duplication-thresholds.md) for per-language thresholds, config, and extraction patterns.
82	See [references/linter-commands.md](references/linter-commands.md) for language-specific jscpd commands.
83
84	---
85
86	## Linter Commands
87	See [references/linter-commands.md](references/linter-commands.md) for language-specific commands.
88
89	---
90
91	## Error Priority Matrix
92
93	\| Priority \| Type \| Examples \| Action \|
94	\|----------\|------\|----------\|--------\|
95	\| Critical \| Security \| SQL injection, XSS, CSRF, auth bypass \| Fix IMMEDIATELY \|
96	\| High \| Logic \| SOLID violations, memory leaks, race conditions \| Fix same session \|
97	\| High \| DRY \| Code duplication > 10%, copy-paste logic blocks \| Mandatory refactoring \|
98	\| Medium \| DRY \| Code duplication 5-10%, repeated patterns \| Extract shared logic \|
99	\| Medium \| Performance \| N+1 queries, deprecated APIs, inefficient algorithms \| Fix if time \|
100	\| Low \| Style \| Formatting, naming, missing docs \| Fix if time \|
101
102	---
103
104	## SOLID Validation
105	See [references/solid-validation.md](references/solid-validation.md) for S-O-L-I-D detection patterns and fix examples.
106
107	---
108
109	## File Size Rules
110	See [references/file-size-rules.md](references/file-size-rules.md) for LoC limits, calculation, and split strategies.
111
112	---
113
114	## Architecture Rules
115	See [references/architecture-patterns.md](references/architecture-patterns.md) for project structures and patterns.
116
117	---
118
119	## Validation Report Format
120	See [references/validation-report.md](references/validation-report.md) for the complete sniper report template.
121
122	---
123
124	## Complete Workflow Example
125	See [references/examples.md](references/examples.md) for detailed walkthrough.
126
127	---
128
129	## Forbidden Behaviors
130
131	### Workflow Violations
132	- ❌ Skip PHASE 1 (explore-codebase)
133	- ❌ Skip PHASE 2 (research-expert)
134	- ❌ Skip PHASE 3 (impact analysis)
135	- ❌ Skip PHASE 3.5 (DRY detection)
136	- ❌ Jump to corrections without completing Phases 1-3
137	- ❌ Proceed when BLOCKER is active
138
139	### Code Qualit

People who liked this also viewed

6 picks

Type

code-quality

48installs3forks

View on GitHub

How to install code-quality?

fusengine/agents/code-quality

$npx -y skills add fusengine/agents --skill code-quality

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Code Quality Skill
2
3	Canonical workflow definition: `agents/sniper.md` (this skill and the sniper agent share the same 7-phase workflow — update both together).
4
5	## 🚨 MANDATORY 7-PHASE WORKFLOW
6
7	```
8	PHASE 1: Exploration (explore-codebase) → BLOCKER
9	PHASE 2: Documentation (research-expert) → BLOCKER
10	PHASE 3: Impact Analysis (Grep usages) → BLOCKER
11	PHASE 3.5: DRY Detection (jscpd duplication) → NON-BLOCKING
12	PHASE 4: Error Detection (linters)
13	PHASE 5: Precision Correction (with docs + impact + DRY)
14	PHASE 6: Verification (re-run linters, tests, duplication)
15	```
16
17	CRITICAL: Phases 1-3 are BLOCKERS. Never skip them.
18	DRY: Phase 3.5 is non-blocking but findings inform Phase 5 corrections.
19
20	---
21
22	## PHASE 1: Architecture Exploration
23
24	Launch explore-codebase agent FIRST:
25	```
26	> Agent(subagent_type="fuse-ai-pilot:explore-codebase", prompt="...")
27	```
28
29	Gather:
30	1. Programming language(s) detected
31	2. Existing linter configs (.eslintrc, .prettierrc, pyproject.toml)
32	3. Package managers and installed linters
33	4. Project structure and conventions
34	5. Framework versions (package.json, go.mod, Cargo.toml)
35	6. Architecture patterns (Clean, Hexagonal, MVC)
36	7. State management (Zustand, Redux, Context)
37	8. Interface/types directories location
38
39	---
40
41	## PHASE 2: Documentation Research
42
43	Launch research-expert agent:
44	```
45	> Agent(subagent_type="fuse-ai-pilot:research-expert", prompt="Verify [library/framework] documentation for [error type]. Find [language] best practices for [specific issue].")
46	```
47
48	Request for each error:
49	- Official API documentation
50	- Current syntax and deprecations
51	- Best practices for error patterns
52	- Version-specific breaking changes
53	- Security advisories
54	- Language-specific SOLID patterns
55
56	---
57
58	## PHASE 3: Impact Analysis
59
60	For EACH element to modify: Grep usages → assess risk → document impact.
61
62	\| Risk \| Criteria \| Action \|
63	\|------\|----------\|--------\|
64	\| 🟢 LOW \| Internal, 0-1 usages \| Proceed \|
65	\| 🟡 MEDIUM \| 2-5 usages, compatible \| Proceed with care \|
66	\| 🔴 HIGH \| 5+ usages OR breaking \| Flag to user FIRST \|
67
68	---
69
70	## PHASE 3.5: Code Duplication Detection (DRY)
71
72	Tool: `jscpd` — 150+ languages — `npx jscpd ./src --threshold 5 --reporters console,json`
73
74	\| Level \| Threshold \| Action \|
75	\|-------\|-----------\|--------\|
76	\| 🟢 Excellent \| < 3% \| No action needed \|
77	\| 🟡 Good \| 3-5% \| Document, fix if time \|
78	\| 🟠 Acceptable \| 5-10% \| Extract shared logic \|
79	\| 🔴 Critical \| > 10% \| Mandatory refactoring \|
80
81	See [references/duplication-thresholds.md](references/duplication-thresholds.md) for per-language thresholds, config, and extraction patterns.
82	See [references/linter-commands.md](references/linter-commands.md) for language-specific jscpd commands.
83
84	---
85
86	## Linter Commands
87	See [references/linter-commands.md](references/linter-commands.md) for language-specific commands.
88
89	---
90
91	## Error Priority Matrix
92
93	\| Priority \| Type \| Examples \| Action \|
94	\|----------\|------\|----------\|--------\|
95	\| Critical \| Security \| SQL injection, XSS, CSRF, auth bypass \| Fix IMMEDIATELY \|
96	\| High \| Logic \| SOLID violations, memory leaks, race conditions \| Fix same session \|
97	\| High \| DRY \| Code duplication > 10%, copy-paste logic blocks \| Mandatory refactoring \|
98	\| Medium \| DRY \| Code duplication 5-10%, repeated patterns \| Extract shared logic \|
99	\| Medium \| Performance \| N+1 queries, deprecated APIs, inefficient algorithms \| Fix if time \|
100	\| Low \| Style \| Formatting, naming, missing docs \| Fix if time \|
101
102	---
103
104	## SOLID Validation
105	See [references/solid-validation.md](references/solid-validation.md) for S-O-L-I-D detection patterns and fix examples.
106
107	---
108
109	## File Size Rules
110	See [references/file-size-rules.md](references/file-size-rules.md) for LoC limits, calculation, and split strategies.
111
112	---
113
114	## Architecture Rules
115	See [references/architecture-patterns.md](references/architecture-patterns.md) for project structures and patterns.
116
117	---
118
119	## Validation Report Format
120	See [references/validation-report.md](references/validation-report.md) for the complete sniper report template.
121
122	---
123
124	## Complete Workflow Example
125	See [references/examples.md](references/examples.md) for detailed walkthrough.
126
127	---
128
129	## Forbidden Behaviors
130
131	### Workflow Violations
132	- ❌ Skip PHASE 1 (explore-codebase)
133	- ❌ Skip PHASE 2 (research-expert)
134	- ❌ Skip PHASE 3 (impact analysis)
135	- ❌ Skip PHASE 3.5 (DRY detection)
136	- ❌ Jump to corrections without completing Phases 1-3
137	- ❌ Proceed when BLOCKER is active
138
139	### Code Qualit

People who liked this also viewed

6 picks

Type