langchain-tool-builder

Name: langchain-tool-builder
Author: simbajigege

8installs21forks

How to install langchain-tool-builder?

simbajigege/book2skills/langchain-tool-builder

$npx -y skills add simbajigege/book2skills --skill langchain-tool-builder

Installs into the current project.

Summary

Build LangChain (Python) tools using Claude Code's fail-closed design pattern — unified name/schema/security/execution in one class, with automatic three-layer execution (validate → permission → call). Use this skill whenever the user wants to define a new LangChain tool, add per

Files · 1

View on GitHub

SKILL.md

1	# LangChain Tool Builder
2
3	Helps define LangChain (Python) tools using Claude Code's `buildTool()` pattern:
4	a unified class that co-locates identity, schema, security properties, and execution logic,
5	with fail-closed defaults so new tools are safe by default.
6
7	## Why this pattern matters
8
9	Claude Code enforces three things that vanilla LangChain tools lack:
10	1. Fail-closed defaults — `is_read_only`, `is_destructive`, `is_concurrency_safe` all default to False.
11	A tool that forgets to declare its properties is conservatively treated as write-capable.
12	2. Layered execution — `validate_semantics → check_permissions → _call` are separate methods,
13	so validation logic doesn't bleed into permission logic or business logic.
14	3. Self-contained definition — schema, description, security metadata, and execution all live
15	in one class. No separate permission middleware to wire up.
16
17	## Workflow
18
19	### Step 1 — Install the base class
20
21	Check if `claude_style_tool.py` exists in the project's utils directory.
22	The expected location for the `ai-base` project is:
23	`/Users/jigege/ai-base/backend/base/utils/claude_style_tool.py`
24
25	If it doesn't exist, copy it from `references/claude_style_tool.py` in this skill directory.
26	Tell the user where it was placed and what it provides.
27
28	If working in a different project, ask the user where their utils/tools directory is.
29
30	### Step 2 — Interview the user
31
32	Collect answers to these questions. Defaults are shown — skip questions where the default is clearly fine.
33
34	Naming convention: use `{service}_{action}_{resource}` format with a service prefix so the tool stays unambiguous when multiple tool sets are loaded simultaneously (e.g. `stock_get_price`, `stock_list_symbols`, `github_create_issue`). Start with a verb: `get`, `list`, `search`, `create`, `delete`.
35
36	\| Field \| Question \| Default \|
37	\|---\|---\|---\|
38	\| `name` \| 工具名（格式：`{service}_{action}_{resource}`，例如 `stock_get_price`） \| — required \|
39	\| `description` \| 给 LLM 看的一句话描述：精确匹配实际功能，不要模糊扩大，否则 agent 会在不该用的场景误调用 \| — required \|
40	\| Schema fields \| 工具接受哪些参数？（字段名、类型、说明；在 Field description 里加 example，如 `e.g. '2024-01-01'`） \| — required \|
41	\| `is_read_only` \| 这个工具只读数据，不写入/不产生副作用吗？ \| `False` \|
42	\| `is_destructive` \| 这个工具会做不可逆操作（删除、覆盖）吗？ \| `False` \|
43	\| `is_concurrency_safe` \| 这个工具可以和其他工具同时运行吗？ \| `False` \|
44	\| `response_format` \| 返回数据是给 agent 程序化处理（JSON）还是给用户展示（Markdown）？ \| 视场景，默认 Markdown \|
45	\| 是否列表工具 \| 如果返回多条记录，要支持分页吗？ \| 超过 50 条建议加 \|
46	\| `_validate_input_semantics` \| 有没有需要在执行前拦截的语义问题？（如：参数太短、路径格式不对） \| 不需要 \|
47	\| `_check_permissions` \| 有没有需要检查的权限？（如：只允许读特定路径、需要某个 env var） \| 不需要 \|
48	\| `_call` \| 工具的核心执行逻辑是什么？ \| — required \|
49
50	You don't have to ask all questions upfront — you can infer reasonable answers from context.
51	For example, a "search" tool is almost certainly `is_read_only=True, is_concurrency_safe=True`.
52
53	### Step 3 — Generate the tool file
54
55	Create a `.py` file for the tool. Follow this field order (matches Claude Code's BashTool):
56
57	```
58	1. imports
59	2. Input schema (Pydantic BaseModel)
60	3. Tool class:
61	a. name, description, args_schema — identity
62	b. is_read_only, is_destructive, is_concurrency_safe, max_result_chars — security metadata
63	c. _validate_input_semantics() — semantic validation (omit if unneeded)
64	d. _check_permissions() — permission check (omit if unneeded)
65	e. _call() — actual logic
66	```
67
68	Suggest a file path consistent with the project's tool/agent directory structure.
69	For `ai-base`, suggest: `/Users/jigege/ai-base/backend/base/tools/<tool_name>.py`
70
71	### Step 4 — Show security property summary
72
73	After generating, print a one-line summary of the tool's security posture:
74
75	```
76	SearchDocsTool: read_only=True destructive=False concurrency_safe=True max_result=10K
77	```
78
79	This helps the user quickly verify the fail-closed properties are set correctly.
80
81	---
82
83	## Output template
84
85	Use this structure when generating the tool file. Adjust based on what the user actually needs.
86
87	```python
88	"""<tool_name>.py — <one-line description>"""
89
90	from typing import Optional
91	from pydantic import BaseModel, Field
92	from base.utils.claude_style_tool import ClaudeStyleTool
93
94
95	# ---------------------------------------------------------------------------
96	# Input schema
97	# ----------------------------------------------------------------------

People who liked this also viewed

6 picks

Type

langchain-tool-builder

8installs21forks

View on GitHub

How to install langchain-tool-builder?

simbajigege/book2skills/langchain-tool-builder

$npx -y skills add simbajigege/book2skills --skill langchain-tool-builder

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# LangChain Tool Builder
2
3	Helps define LangChain (Python) tools using Claude Code's `buildTool()` pattern:
4	a unified class that co-locates identity, schema, security properties, and execution logic,
5	with fail-closed defaults so new tools are safe by default.
6
7	## Why this pattern matters
8
9	Claude Code enforces three things that vanilla LangChain tools lack:
10	1. Fail-closed defaults — `is_read_only`, `is_destructive`, `is_concurrency_safe` all default to False.
11	A tool that forgets to declare its properties is conservatively treated as write-capable.
12	2. Layered execution — `validate_semantics → check_permissions → _call` are separate methods,
13	so validation logic doesn't bleed into permission logic or business logic.
14	3. Self-contained definition — schema, description, security metadata, and execution all live
15	in one class. No separate permission middleware to wire up.
16
17	## Workflow
18
19	### Step 1 — Install the base class
20
21	Check if `claude_style_tool.py` exists in the project's utils directory.
22	The expected location for the `ai-base` project is:
23	`/Users/jigege/ai-base/backend/base/utils/claude_style_tool.py`
24
25	If it doesn't exist, copy it from `references/claude_style_tool.py` in this skill directory.
26	Tell the user where it was placed and what it provides.
27
28	If working in a different project, ask the user where their utils/tools directory is.
29
30	### Step 2 — Interview the user
31
32	Collect answers to these questions. Defaults are shown — skip questions where the default is clearly fine.
33
34	Naming convention: use `{service}_{action}_{resource}` format with a service prefix so the tool stays unambiguous when multiple tool sets are loaded simultaneously (e.g. `stock_get_price`, `stock_list_symbols`, `github_create_issue`). Start with a verb: `get`, `list`, `search`, `create`, `delete`.
35
36	\| Field \| Question \| Default \|
37	\|---\|---\|---\|
38	\| `name` \| 工具名（格式：`{service}_{action}_{resource}`，例如 `stock_get_price`） \| — required \|
39	\| `description` \| 给 LLM 看的一句话描述：精确匹配实际功能，不要模糊扩大，否则 agent 会在不该用的场景误调用 \| — required \|
40	\| Schema fields \| 工具接受哪些参数？（字段名、类型、说明；在 Field description 里加 example，如 `e.g. '2024-01-01'`） \| — required \|
41	\| `is_read_only` \| 这个工具只读数据，不写入/不产生副作用吗？ \| `False` \|
42	\| `is_destructive` \| 这个工具会做不可逆操作（删除、覆盖）吗？ \| `False` \|
43	\| `is_concurrency_safe` \| 这个工具可以和其他工具同时运行吗？ \| `False` \|
44	\| `response_format` \| 返回数据是给 agent 程序化处理（JSON）还是给用户展示（Markdown）？ \| 视场景，默认 Markdown \|
45	\| 是否列表工具 \| 如果返回多条记录，要支持分页吗？ \| 超过 50 条建议加 \|
46	\| `_validate_input_semantics` \| 有没有需要在执行前拦截的语义问题？（如：参数太短、路径格式不对） \| 不需要 \|
47	\| `_check_permissions` \| 有没有需要检查的权限？（如：只允许读特定路径、需要某个 env var） \| 不需要 \|
48	\| `_call` \| 工具的核心执行逻辑是什么？ \| — required \|
49
50	You don't have to ask all questions upfront — you can infer reasonable answers from context.
51	For example, a "search" tool is almost certainly `is_read_only=True, is_concurrency_safe=True`.
52
53	### Step 3 — Generate the tool file
54
55	Create a `.py` file for the tool. Follow this field order (matches Claude Code's BashTool):
56
57	```
58	1. imports
59	2. Input schema (Pydantic BaseModel)
60	3. Tool class:
61	a. name, description, args_schema — identity
62	b. is_read_only, is_destructive, is_concurrency_safe, max_result_chars — security metadata
63	c. _validate_input_semantics() — semantic validation (omit if unneeded)
64	d. _check_permissions() — permission check (omit if unneeded)
65	e. _call() — actual logic
66	```
67
68	Suggest a file path consistent with the project's tool/agent directory structure.
69	For `ai-base`, suggest: `/Users/jigege/ai-base/backend/base/tools/<tool_name>.py`
70
71	### Step 4 — Show security property summary
72
73	After generating, print a one-line summary of the tool's security posture:
74
75	```
76	SearchDocsTool: read_only=True destructive=False concurrency_safe=True max_result=10K
77	```
78
79	This helps the user quickly verify the fail-closed properties are set correctly.
80
81	---
82
83	## Output template
84
85	Use this structure when generating the tool file. Adjust based on what the user actually needs.
86
87	```python
88	"""<tool_name>.py — <one-line description>"""
89
90	from typing import Optional
91	from pydantic import BaseModel, Field
92	from base.utils.claude_style_tool import ClaudeStyleTool
93
94
95	# ---------------------------------------------------------------------------
96	# Input schema
97	# ----------------------------------------------------------------------

People who liked this also viewed

6 picks

Type