create-hook

Name: create-hook
Author: NeoLabHQ

1.3kstars132forks

How to install create-hook?

neolabhq/context-engineering-kit/create-hook

$npx -y skills add NeoLabHQ/context-engineering-kit --skill create-hook

Installs into the current project.

Summary

Create and configure git hooks with intelligent project analysis, suggestions, and automated testing

Files · 1

View on GitHub

SKILL.md

1	# Create Hook Command
2
3	Analyze the project, suggest practical hooks, and create them with proper testing.
4
5	## Your Task (/create-hook)
6
7	1. Analyze environment - Detect tooling and existing hooks
8	2. Suggest hooks - Based on your project configuration
9	3. Configure hook - Ask targeted questions and create the script
10	4. Test & validate - Ensure the hook works correctly
11
12	## Your Workflow
13
14	### 1. Environment Analysis & Suggestions
15
16	Automatically detect the project tooling and suggest relevant hooks:
17
18	When TypeScript is detected (`tsconfig.json`):
19
20	- PostToolUse hook: "Type-check files after editing"
21	- PreToolUse hook: "Block edits with type errors"
22
23	When Prettier is detected (`.prettierrc`, `prettier.config.js`):
24
25	- PostToolUse hook: "Auto-format files after editing"
26	- PreToolUse hook: "Require formatted code"
27
28	*When ESLint is detected (`.eslintrc.`):**
29
30	- PostToolUse hook: "Lint and auto-fix after editing"
31	- PreToolUse hook: "Block commits with linting errors"
32
33	When package.json has scripts:
34
35	- `test` script → "Run tests before commits"
36	- `build` script → "Validate build before commits"
37
38	When a git repository is detected:
39
40	- PreToolUse/Bash hook: "Prevent commits with secrets"
41	- PostToolUse hook: "Security scan on file changes"
42
43	Decision Tree:
44
45	```
46	Project has TypeScript? → Suggest type checking hooks
47	Project has formatter? → Suggest formatting hooks
48	Project has tests? → Suggest test validation hooks
49	Security sensitive? → Suggest security hooks
50	+ Scan for additional patterns and suggest custom hooks based on:
51	- Custom scripts in package.json
52	- Unique file patterns or extensions
53	- Development workflow indicators
54	- Project-specific tooling configurations
55	```
56
57	### 2. Hook Configuration
58
59	Start by asking: "What should this hook do?" and offer relevant suggestions from your analysis.
60
61	Then understand the context from the user's description and only ask about details you're unsure about:
62
63	1. Trigger timing: When should it run?
64	- `PreToolUse`: Before file operations (can block)
65	- `PostToolUse`: After file operations (feedback/fixes)
66	- `UserPromptSubmit`: Before processing requests
67	- Other event types as needed
68
69	2. Tool matcher: Which tools should trigger it? (`Write`, `Edit`, `Bash`, `*` etc)
70
71	3. Scope: `global`, `project`, or `project-local`
72
73	4. Response approach:
74	- Exit codes only: Simple (exit 0 = success, exit 2 = block in PreToolUse)
75	- JSON response: Advanced control (blocking, context, decisions)
76	- Guide based on complexity: simple pass/fail → exit codes, rich feedback → JSON
77
78	5. Blocking behavior (if relevant): "Should this stop operations when issues are found?"
79	- PreToolUse: Can block operations (security, validation)
80	- PostToolUse: Usually provide feedback only
81
82	6. Claude integration (CRITICAL): "Should Claude Code automatically see and fix issues this hook detects?"
83	- If YES: Use `additionalContext` for error communication
84	- If NO: Use `suppressOutput: true` for silent operation
85
86	7. Context pollution: "Should successful operations be silent to avoid noise?"
87	- Recommend YES for formatting, routine checks
88	- Recommend NO for security alerts, critical errors
89
90	8. File filtering: "What file types should this hook process?"
91
92	### 3. Hook Creation
93
94	You should:
95
96	- Create hooks directory: `~/.claude/hooks/` or `.claude/hooks/` based on scope
97	- Generate script: Create hook script with:
98	- Proper shebang and executable permissions
99	- Project-specific commands (use detected config paths)
100	- Comments explaining the hook's purpose
101	- Update settings: Add hook configuration to appropriate settings.json
102	- Use absolute paths: Avoid relative paths to scripts and executables. Use `$CLAUDE_PROJECT_DIR` to reference project root
103	- Offer validation: Ask if the user wants you to test the hook
104
105	Key Implementation Standards:
106
107	- Read JSON from stdin (never use argv)
108	- Use top-level `additionalContext`/`systemMessage` for Claude communication
109	- Include `suppressOutput: true` for successful operations
110	- Provide specific error counts and actionable feedback
111	- Focus on changed files rather than entire codebase
112	- Support common development workflows
113
114	⚠️ CRITICAL: Input/Output Format
115
116	This is where most hook implementations fail. Pay extra attention to:
117
118	- Input: Reading JSON from stdin correctly (not argv)
119	- Output: Using correct top-level JSON structure for Claude communication
120	- Documentation: Consulting official docs for exact schemas when in doubt
121
122	### 4. Testing & Validation
123
124	CRITICAL: Test both happy and sad paths:
125
126	Happy Path Testing:
127
128	1. Test expected success scenario - Create conditions where hook should pass
129	- _Examples_: TypeScript (valid

People who liked this also viewed

6 picks

Type

lark-drive飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sSkillsJul 2026382k16k
lark-sharedUse for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handlingSkillsJul 2026382k16k
lark-whiteboard飞书画板：查询和编辑飞书云文档中的画板。支持导出画板为预览图片、导出原始节点结构、使用多种格式更新画板内容。当用户需要查看画板内容、导出画板图片、编辑画板时使用此 skill。不负责：飞书云文档内容编辑（lark-doc）、文档内嵌电子表格/Base（lark-sheets / lark-base）。SkillsJul 2026380k16k
lark-task飞书任务：管理任务、清单和任务智能体。创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员、上传任务附件、注册或注销任务智能体、更新任务智能体的主页数据、写入智能体任务记录。当用户需要创建待办事项、查看任务列表、跟踪任务进度、管理项目清单或给他人分配任务、为任务上传附件文件、注册注销任务智能体、更新智能体主页数据、写入任务记录时使用。SkillsJul 2026380k16k
lark-attendance飞书考勤打卡：查询自己的考勤打卡记录SkillsJul 2026330k16k
lark-apps妙搭（Spark/Miaoda）应用开发与托管：应用创建、本地全栈开发、云端生成迭代、创意设计（UI mockup / 可交互原型 / 线框图 / 落地页 / 仪表盘 / 幻灯片 deck / 视觉探索）、AI相关能力和飞书平台能力或者其他外部能力集成、日志/Trace/监控指标/PV/UV 查询、环境变量管理、应用角色与成员管理、自动化触发器（定时/记录变更/Webhook/飞书审批）。当用户要SkillsJul 2026227k16k

create-hook

1.3kstars132forks

View on GitHub

How to install create-hook?

neolabhq/context-engineering-kit/create-hook

$npx -y skills add NeoLabHQ/context-engineering-kit --skill create-hook

Installs into the current project.

Summary

Create and configure git hooks with intelligent project analysis, suggestions, and automated testing

Files · 1

View on GitHub

SKILL.md

1	# Create Hook Command
2
3	Analyze the project, suggest practical hooks, and create them with proper testing.
4
5	## Your Task (/create-hook)
6
7	1. Analyze environment - Detect tooling and existing hooks
8	2. Suggest hooks - Based on your project configuration
9	3. Configure hook - Ask targeted questions and create the script
10	4. Test & validate - Ensure the hook works correctly
11
12	## Your Workflow
13
14	### 1. Environment Analysis & Suggestions
15
16	Automatically detect the project tooling and suggest relevant hooks:
17
18	When TypeScript is detected (`tsconfig.json`):
19
20	- PostToolUse hook: "Type-check files after editing"
21	- PreToolUse hook: "Block edits with type errors"
22
23	When Prettier is detected (`.prettierrc`, `prettier.config.js`):
24
25	- PostToolUse hook: "Auto-format files after editing"
26	- PreToolUse hook: "Require formatted code"
27
28	*When ESLint is detected (`.eslintrc.`):**
29
30	- PostToolUse hook: "Lint and auto-fix after editing"
31	- PreToolUse hook: "Block commits with linting errors"
32
33	When package.json has scripts:
34
35	- `test` script → "Run tests before commits"
36	- `build` script → "Validate build before commits"
37
38	When a git repository is detected:
39
40	- PreToolUse/Bash hook: "Prevent commits with secrets"
41	- PostToolUse hook: "Security scan on file changes"
42
43	Decision Tree:
44
45	```
46	Project has TypeScript? → Suggest type checking hooks
47	Project has formatter? → Suggest formatting hooks
48	Project has tests? → Suggest test validation hooks
49	Security sensitive? → Suggest security hooks
50	+ Scan for additional patterns and suggest custom hooks based on:
51	- Custom scripts in package.json
52	- Unique file patterns or extensions
53	- Development workflow indicators
54	- Project-specific tooling configurations
55	```
56
57	### 2. Hook Configuration
58
59	Start by asking: "What should this hook do?" and offer relevant suggestions from your analysis.
60
61	Then understand the context from the user's description and only ask about details you're unsure about:
62
63	1. Trigger timing: When should it run?
64	- `PreToolUse`: Before file operations (can block)
65	- `PostToolUse`: After file operations (feedback/fixes)
66	- `UserPromptSubmit`: Before processing requests
67	- Other event types as needed
68
69	2. Tool matcher: Which tools should trigger it? (`Write`, `Edit`, `Bash`, `*` etc)
70
71	3. Scope: `global`, `project`, or `project-local`
72
73	4. Response approach:
74	- Exit codes only: Simple (exit 0 = success, exit 2 = block in PreToolUse)
75	- JSON response: Advanced control (blocking, context, decisions)
76	- Guide based on complexity: simple pass/fail → exit codes, rich feedback → JSON
77
78	5. Blocking behavior (if relevant): "Should this stop operations when issues are found?"
79	- PreToolUse: Can block operations (security, validation)
80	- PostToolUse: Usually provide feedback only
81
82	6. Claude integration (CRITICAL): "Should Claude Code automatically see and fix issues this hook detects?"
83	- If YES: Use `additionalContext` for error communication
84	- If NO: Use `suppressOutput: true` for silent operation
85
86	7. Context pollution: "Should successful operations be silent to avoid noise?"
87	- Recommend YES for formatting, routine checks
88	- Recommend NO for security alerts, critical errors
89
90	8. File filtering: "What file types should this hook process?"
91
92	### 3. Hook Creation
93
94	You should:
95
96	- Create hooks directory: `~/.claude/hooks/` or `.claude/hooks/` based on scope
97	- Generate script: Create hook script with:
98	- Proper shebang and executable permissions
99	- Project-specific commands (use detected config paths)
100	- Comments explaining the hook's purpose
101	- Update settings: Add hook configuration to appropriate settings.json
102	- Use absolute paths: Avoid relative paths to scripts and executables. Use `$CLAUDE_PROJECT_DIR` to reference project root
103	- Offer validation: Ask if the user wants you to test the hook
104
105	Key Implementation Standards:
106
107	- Read JSON from stdin (never use argv)
108	- Use top-level `additionalContext`/`systemMessage` for Claude communication
109	- Include `suppressOutput: true` for successful operations
110	- Provide specific error counts and actionable feedback
111	- Focus on changed files rather than entire codebase
112	- Support common development workflows
113
114	⚠️ CRITICAL: Input/Output Format
115
116	This is where most hook implementations fail. Pay extra attention to:
117
118	- Input: Reading JSON from stdin correctly (not argv)
119	- Output: Using correct top-level JSON structure for Claude communication
120	- Documentation: Consulting official docs for exact schemas when in doubt
121
122	### 4. Testing & Validation
123
124	CRITICAL: Test both happy and sad paths:
125
126	Happy Path Testing:
127
128	1. Test expected success scenario - Create conditions where hook should pass
129	- _Examples_: TypeScript (valid

People who liked this also viewed

6 picks

Type