command-creator

Name: command-creator
Author: softspark

161stars21forks

How to install command-creator?

softspark/ai-toolkit/command-creator

$npx -y skills add softspark/ai-toolkit --skill command-creator

Installs into the current project.

Summary

Creates new Claude Code slash commands with frontmatter and validation. Triggers: new slash command, create command, command scaffold.

Files · 1

View on GitHub

SKILL.md

1	# Command Creator
2
3	$ARGUMENTS
4
5	Create a new Claude Code slash command following ai-toolkit conventions.
6
7	## Workflow
8
9	1. Capture intent -- what should the command do and who invokes it?
10	2. Pick scope -- project command, user command, or plugin command?
11	3. Define frontmatter -- description, argument hint, allowed tools, model if needed
12	4. Write command body -- instructions for Claude, not explanation for the user
13	5. Add validation context -- expected output, constraints, follow-up checks
14	6. Test and iterate -- invoke the command with representative arguments
15
16	## Command Locations
17
18	- Project: `.claude/commands/<name>.md`
19	- User: `~/.claude/commands/<name>.md`
20	- Plugin: `plugin-name/commands/<name>.md`
21
22	In `ai-toolkit`, command-development guidance belongs in skill form and any reusable command templates should live under `app/skills/<skill-name>/templates/` or KB docs.
23
24	## Frontmatter Template
25
26	```yaml
27	---
28	description: "One-line help text shown in /help"
29	argument-hint: "[target]"
30	allowed-tools: Read, Grep, Bash
31	model: sonnet
32	---
33	```
34
35	## Command Authoring Rules
36
37	- Write commands as instructions for Claude, not marketing copy for the user
38	- Keep the first paragraph action-oriented and deterministic
39	- Use `$ARGUMENTS` early when the command takes user input
40	- Prefer numbered phases for multi-step workflows
41	- List required checks explicitly (`lint`, `tests`, `docs`, etc.)
42	- Avoid hidden assumptions about project structure unless the command is project-specific
43	- Description ≥50 chars with a trigger hint (`Use when…`) — short descriptions cause adjacent commands to fight for the same query
44	- Include hard rules (MUST / NEVER / CRITICAL) so the agent cannot improvise around safety boundaries
45	- Include "When NOT to use" naming 2-3 adjacent commands, to prevent over-triggering
46
47	## Minimal Template
48
49	```markdown
50	---
51	description: "{Third-person description, min 50 chars, with trigger hint like 'Use when...'}"
52	argument-hint: "[arguments]"
53	allowed-tools: Read, Grep, Bash
54	---
55
56	# {Command Title}
57
58	$ARGUMENTS
59
60	Perform the requested task using this workflow:
61
62	1. Gather context from the repository.
63	2. Ask clarifying questions if critical information is missing.
64	3. Execute the task using the smallest safe set of changes.
65	4. Validate the result.
66	5. Summarize outcome and follow-up actions.
67
68	## Example
69
70	\`\`\`
71	/{command} example-argument
72	\`\`\`
73
74	## Rules
75
76	- MUST {non-negotiable rule}
77	- NEVER {forbidden action}
78
79	## Gotchas
80
81	- {environment-specific trap — only if the command has one; omit the section otherwise}
82
83	## When NOT to Use
84
85	- For {adjacent use case} -- use `/{other-command}` instead
86	- If {precondition} is not met
87	```
88
89	Follow [Anthropic's Gotchas guidance](https://agentskills.io/skill-creation/best-practices.md#gotchas-sections): "concrete corrections to mistakes the agent will make without being told otherwise" — not general advice. Omit the section when no domain traps exist.
90
91	## Validation Checklist
92
93	- [ ] Command file uses markdown and valid YAML frontmatter
94	- [ ] Description ≥50 chars, third-person, with trigger hint
95	- [ ] At least one concrete code-fenced example
96	- [ ] `## Rules` with MUST / NEVER / CRITICAL (prescriptive)
97	- [ ] `## Gotchas` when the command has real environment-specific traps (optional)
98	- [ ] `## When NOT to Use` section naming 2-3 adjacent commands
99	- [ ] Body is instruction-oriented, not user-facing prose
100	- [ ] `$ARGUMENTS` is present when arguments are expected
101	- [ ] Validation steps are explicit
102	- [ ] Command has been tested with at least one realistic invocation

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

command-creator

161stars21forks

View on GitHub

How to install command-creator?

softspark/ai-toolkit/command-creator

$npx -y skills add softspark/ai-toolkit --skill command-creator

Installs into the current project.

Summary

Creates new Claude Code slash commands with frontmatter and validation. Triggers: new slash command, create command, command scaffold.

Files · 1

View on GitHub

SKILL.md

1	# Command Creator
2
3	$ARGUMENTS
4
5	Create a new Claude Code slash command following ai-toolkit conventions.
6
7	## Workflow
8
9	1. Capture intent -- what should the command do and who invokes it?
10	2. Pick scope -- project command, user command, or plugin command?
11	3. Define frontmatter -- description, argument hint, allowed tools, model if needed
12	4. Write command body -- instructions for Claude, not explanation for the user
13	5. Add validation context -- expected output, constraints, follow-up checks
14	6. Test and iterate -- invoke the command with representative arguments
15
16	## Command Locations
17
18	- Project: `.claude/commands/<name>.md`
19	- User: `~/.claude/commands/<name>.md`
20	- Plugin: `plugin-name/commands/<name>.md`
21
22	In `ai-toolkit`, command-development guidance belongs in skill form and any reusable command templates should live under `app/skills/<skill-name>/templates/` or KB docs.
23
24	## Frontmatter Template
25
26	```yaml
27	---
28	description: "One-line help text shown in /help"
29	argument-hint: "[target]"
30	allowed-tools: Read, Grep, Bash
31	model: sonnet
32	---
33	```
34
35	## Command Authoring Rules
36
37	- Write commands as instructions for Claude, not marketing copy for the user
38	- Keep the first paragraph action-oriented and deterministic
39	- Use `$ARGUMENTS` early when the command takes user input
40	- Prefer numbered phases for multi-step workflows
41	- List required checks explicitly (`lint`, `tests`, `docs`, etc.)
42	- Avoid hidden assumptions about project structure unless the command is project-specific
43	- Description ≥50 chars with a trigger hint (`Use when…`) — short descriptions cause adjacent commands to fight for the same query
44	- Include hard rules (MUST / NEVER / CRITICAL) so the agent cannot improvise around safety boundaries
45	- Include "When NOT to use" naming 2-3 adjacent commands, to prevent over-triggering
46
47	## Minimal Template
48
49	```markdown
50	---
51	description: "{Third-person description, min 50 chars, with trigger hint like 'Use when...'}"
52	argument-hint: "[arguments]"
53	allowed-tools: Read, Grep, Bash
54	---
55
56	# {Command Title}
57
58	$ARGUMENTS
59
60	Perform the requested task using this workflow:
61
62	1. Gather context from the repository.
63	2. Ask clarifying questions if critical information is missing.
64	3. Execute the task using the smallest safe set of changes.
65	4. Validate the result.
66	5. Summarize outcome and follow-up actions.
67
68	## Example
69
70	\`\`\`
71	/{command} example-argument
72	\`\`\`
73
74	## Rules
75
76	- MUST {non-negotiable rule}
77	- NEVER {forbidden action}
78
79	## Gotchas
80
81	- {environment-specific trap — only if the command has one; omit the section otherwise}
82
83	## When NOT to Use
84
85	- For {adjacent use case} -- use `/{other-command}` instead
86	- If {precondition} is not met
87	```
88
89	Follow [Anthropic's Gotchas guidance](https://agentskills.io/skill-creation/best-practices.md#gotchas-sections): "concrete corrections to mistakes the agent will make without being told otherwise" — not general advice. Omit the section when no domain traps exist.
90
91	## Validation Checklist
92
93	- [ ] Command file uses markdown and valid YAML frontmatter
94	- [ ] Description ≥50 chars, third-person, with trigger hint
95	- [ ] At least one concrete code-fenced example
96	- [ ] `## Rules` with MUST / NEVER / CRITICAL (prescriptive)
97	- [ ] `## Gotchas` when the command has real environment-specific traps (optional)
98	- [ ] `## When NOT to Use` section naming 2-3 adjacent commands
99	- [ ] Body is instruction-oriented, not user-facing prose
100	- [ ] `$ARGUMENTS` is present when arguments are expected
101	- [ ] Validation steps are explicit
102	- [ ] Command has been tested with at least one realistic invocation

People who liked this also viewed

6 picks

Type