create-skill

Name: create-skill
Author: Affitor

1installs184forks

How to install create-skill?

affitor/affiliate-skills/create-skill

$npx -y skills add Affitor/affiliate-skills --skill create-skill

Installs into the current project.

Summary

Turn a repeatable AI prompt or workflow into a structured, shareable skill for the affiliate-skills GitHub repository. Use this skill when the user wants to create a new skill, write a SKILL.md, convert a prompt to a skill, share a skill via the GitHub repo, or document an AI wor

Files · 1

View on GitHub

SKILL.md

1	# List Affitor Skill
2
3	Turn a repeatable AI prompt or workflow into a structured, shareable skill for the
4	[affiliate-skills GitHub repository](https://github.com/Affitor/affiliate-skills).
5	The output is a complete SKILL.md file that works in any AI agent — shared via
6	`npx skills add Affitor/affiliate-skills` so anyone can install it.
7
8	## Stage
9
10	This skill belongs to Stage S8: Meta
11
12	## When to Use
13
14	- User has a prompt they keep reusing and wants to turn it into a shareable skill
15	- User wants to create a new skill for the affiliate-skills repository
16	- User wants to write a SKILL.md file in the standard format
17	- User says "make this a skill" or "write a skill for X"
18	- User wants to package an AI workflow so others can replicate it
19
20	## Input Schema
21
22	```
23	{
24	raw_prompt: string # (required) The prompt, workflow description, or detailed explanation of what the skill does
25	failure_modes: string # (optional) What goes wrong when the output is bad — helps write better Instructions and Error Handling
26	niche: string # (optional) Category hint, e.g., "content", "research", "seo"
27	examples: string # (optional) Example input/output pairs the user already has
28	}
29	```
30
31	## Workflow
32
33	### Step 1: Understand What the Prompt Actually Does
34
35	Before writing anything, analyze the user's raw prompt or workflow description:
36
37	1. Task type — Is this content creation, research, analysis, planning, automation, or something else?
38	2. Variable inputs — What changes each time? (product name, URL, audience, topic, etc.)
39	3. Fixed structure — What stays the same? (output format, sections, tone, constraints)
40	4. Quality differentiator — What makes a good output vs. a bad one?
41	5. Failure modes — Where does the AI tend to go wrong without explicit guidance?
42
43	If the user gave a vague description instead of an actual prompt, ask:
44	- "What do you typically paste into ChatGPT/Claude for this?"
45	- "What does the output look like when it works well?"
46	- "What goes wrong when it doesn't?"
47
48	If the user says "just do it", infer from context and proceed.
49
50	### Step 2: Determine Skill Metadata
51
52	Based on the analysis, determine:
53
54	\| Field \| How to decide \|
55	\|-------\|--------------\|
56	\| `name` \| Short, action-oriented. "Comparison Post Writer" not "A Skill for Writing Comparison Posts" \|
57	\| `slug` \| kebab-case of name, e.g., `comparison-post-writer` \|
58	\| `category` \| One of: research, content, seo, landing, distribution, analytics, automation, meta \|
59	\| `level` \| beginner (1-step, no tools), intermediate (multi-step, 1 tool), advanced (complex workflow, multiple tools) \|
60	\| `stage` \| S1-Research, S2-Content, S3-Blog, S4-Landing, S5-Distribution, S6-Analytics, S7-Automation, S8-Meta \|
61	\| `tags` \| 3-6 lowercase tags relevant to the skill's domain \|
62	\| `tools` \| What external tools the skill needs: `web_search`, `web_fetch`, `code_execution`, none \|
63
64	### Step 3: Write the SKILL.md
65
66	Create a complete SKILL.md following this exact structure. Every section is required.
67
68	Frontmatter (YAML)
69	```yaml
70	---
71	name: [slug]
72	description: >
73	[2-3 lines. First line: what it does. Second line: trigger phrases.
74	This is used for skill discovery — be specific about use cases.]
75	license: MIT
76	version: "1.0.0"
77	tags: [relevant tags]
78	compatibility: "Claude Code, ChatGPT, Gemini CLI, Cursor, Windsurf, OpenClaw, any AI agent"
79	metadata:
80	author: [user handle or "affitor"]
81	version: "1.0"
82	stage: [S1-S8]
83	---
84	```
85
86	Title and Introduction
87	One paragraph. What the skill does and what makes the output reliable. No marketing speak.
88
89	When to Use
90	3-5 specific trigger scenarios. "Writing a blog post" is too vague. "You need to publish a comparison post for two competing SaaS tools this week" is useful.
91
92	Input Schema
93	Typed definition of every variable input. Mark required vs optional.
94
95	Workflow (numbered steps)
96	This is the core. Each step must be concrete enough that any AI model produces consistent output:
97
98	- Action — what to do
99	- Approach — how to do it specifically
100	- Quality bar — what good looks like
101
102	Bad: "3. Write the pros and cons"
103	Good: "3. Write at least 3 pros and 2 cons. Each must reference

People who liked this also viewed

6 picks

Type

create-skill

1installs184forks

View on GitHub

How to install create-skill?

affitor/affiliate-skills/create-skill

$npx -y skills add Affitor/affiliate-skills --skill create-skill

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# List Affitor Skill
2
3	Turn a repeatable AI prompt or workflow into a structured, shareable skill for the
4	[affiliate-skills GitHub repository](https://github.com/Affitor/affiliate-skills).
5	The output is a complete SKILL.md file that works in any AI agent — shared via
6	`npx skills add Affitor/affiliate-skills` so anyone can install it.
7
8	## Stage
9
10	This skill belongs to Stage S8: Meta
11
12	## When to Use
13
14	- User has a prompt they keep reusing and wants to turn it into a shareable skill
15	- User wants to create a new skill for the affiliate-skills repository
16	- User wants to write a SKILL.md file in the standard format
17	- User says "make this a skill" or "write a skill for X"
18	- User wants to package an AI workflow so others can replicate it
19
20	## Input Schema
21
22	```
23	{
24	raw_prompt: string # (required) The prompt, workflow description, or detailed explanation of what the skill does
25	failure_modes: string # (optional) What goes wrong when the output is bad — helps write better Instructions and Error Handling
26	niche: string # (optional) Category hint, e.g., "content", "research", "seo"
27	examples: string # (optional) Example input/output pairs the user already has
28	}
29	```
30
31	## Workflow
32
33	### Step 1: Understand What the Prompt Actually Does
34
35	Before writing anything, analyze the user's raw prompt or workflow description:
36
37	1. Task type — Is this content creation, research, analysis, planning, automation, or something else?
38	2. Variable inputs — What changes each time? (product name, URL, audience, topic, etc.)
39	3. Fixed structure — What stays the same? (output format, sections, tone, constraints)
40	4. Quality differentiator — What makes a good output vs. a bad one?
41	5. Failure modes — Where does the AI tend to go wrong without explicit guidance?
42
43	If the user gave a vague description instead of an actual prompt, ask:
44	- "What do you typically paste into ChatGPT/Claude for this?"
45	- "What does the output look like when it works well?"
46	- "What goes wrong when it doesn't?"
47
48	If the user says "just do it", infer from context and proceed.
49
50	### Step 2: Determine Skill Metadata
51
52	Based on the analysis, determine:
53
54	\| Field \| How to decide \|
55	\|-------\|--------------\|
56	\| `name` \| Short, action-oriented. "Comparison Post Writer" not "A Skill for Writing Comparison Posts" \|
57	\| `slug` \| kebab-case of name, e.g., `comparison-post-writer` \|
58	\| `category` \| One of: research, content, seo, landing, distribution, analytics, automation, meta \|
59	\| `level` \| beginner (1-step, no tools), intermediate (multi-step, 1 tool), advanced (complex workflow, multiple tools) \|
60	\| `stage` \| S1-Research, S2-Content, S3-Blog, S4-Landing, S5-Distribution, S6-Analytics, S7-Automation, S8-Meta \|
61	\| `tags` \| 3-6 lowercase tags relevant to the skill's domain \|
62	\| `tools` \| What external tools the skill needs: `web_search`, `web_fetch`, `code_execution`, none \|
63
64	### Step 3: Write the SKILL.md
65
66	Create a complete SKILL.md following this exact structure. Every section is required.
67
68	Frontmatter (YAML)
69	```yaml
70	---
71	name: [slug]
72	description: >
73	[2-3 lines. First line: what it does. Second line: trigger phrases.
74	This is used for skill discovery — be specific about use cases.]
75	license: MIT
76	version: "1.0.0"
77	tags: [relevant tags]
78	compatibility: "Claude Code, ChatGPT, Gemini CLI, Cursor, Windsurf, OpenClaw, any AI agent"
79	metadata:
80	author: [user handle or "affitor"]
81	version: "1.0"
82	stage: [S1-S8]
83	---
84	```
85
86	Title and Introduction
87	One paragraph. What the skill does and what makes the output reliable. No marketing speak.
88
89	When to Use
90	3-5 specific trigger scenarios. "Writing a blog post" is too vague. "You need to publish a comparison post for two competing SaaS tools this week" is useful.
91
92	Input Schema
93	Typed definition of every variable input. Mark required vs optional.
94
95	Workflow (numbered steps)
96	This is the core. Each step must be concrete enough that any AI model produces consistent output:
97
98	- Action — what to do
99	- Approach — how to do it specifically
100	- Quality bar — what good looks like
101
102	Bad: "3. Write the pros and cons"
103	Good: "3. Write at least 3 pros and 2 cons. Each must reference

People who liked this also viewed

6 picks

Type