skill-creator

Name: skill-creator
Author: thomast1906

189stars53forks

How to install skill-creator?

thomast1906/github-copilot-agent-skills/skill-creator

$npx -y skills add thomast1906/github-copilot-agent-skills --skill skill-creator

Installs into the current project.

Summary

Create, update, review, and validate GitHub Copilot agent skills (SKILL.md files). Use this skill whenever someone wants to create a new skill, build a skill from scratch, package domain knowledge into a reusable agent skill, turn a workflow into a skill, or asks "how do I teach

Files · 1

View on GitHub

SKILL.md

1	# Skill Creator
2
3	Create high-quality GitHub Copilot agent skills (SKILL.md) that transform the general-purpose agent into a specialized expert.
4
5	## What Is a Skill
6
7	A skill is a modular, self-contained knowledge package stored in `.github/skills/<skill-name>/SKILL.md`. It provides:
8
9	- Specialized workflows — Multi-step procedures for a specific domain
10	- Domain expertise — Company-specific schemas, patterns, business logic
11	- Tool integrations — Instructions for APIs, file formats, or services
12	- Bundled resources — Scripts, reference docs, and templates for reuse
13
14	Skills load in three levels (progressive disclosure):
15
16	1. Metadata (`name` + `description`) — Always in context (~100 words). This is the trigger mechanism.
17	2. SKILL.md body — Loaded when the skill triggers. Keep under 500 lines.
18	3. Bundled resources — Loaded on demand (scripts/, references/, assets/).
19
20	## Skill Anatomy
21
22	```
23	skill-name/
24	├── SKILL.md (required)
25	│ ├── YAML frontmatter name + description (required)
26	│ └── Markdown instructions
27	└── Bundled Resources (optional)
28	├── scripts/ Executable code for deterministic/repetitive tasks
29	├── references/ Docs loaded into context as needed
30	└── assets/ Output files (templates, icons, boilerplate)
31	```
32
33	Do NOT include: setup guides, changelogs, or user-facing documentation — skills are instructions for the agent, not onboarding docs for humans.
34
35	---
36
37	## Is a Skill the Right Vehicle?
38
39	Not every workflow needs a skill. Before creating one, choose the right tool:
40
41	\| Situation \| Use instead \|
42	\|---\|---\|
43	\| A rule that applies to ALL Copilot interactions in this repo \| `copilot-instructions.md` entry \|
44	\| A rule scoped to specific file types (e.g., always use `kebab-case` for Bicep variable names) \| `.github/instructions/*.instructions.md` with `applyTo` glob \|
45	\| A one-off prompt you run occasionally \| `.github/prompts/*.prompt.md` \|
46	\| A multi-step workflow with domain knowledge that benefits from on-demand loading \| Skill \|
47	\| A complex workflow with a dedicated agent persona \| `.github/agents/*.agent.md` \|
48
49	A skill is the right choice when: the workflow is too detailed for `copilot-instructions.md`, it should only load for relevant requests (not every conversation), and it encapsulates reusable domain knowledge or a repeatable process.
50
51	If the user's need is better served by a simpler vehicle, say so and use that instead. Not everything needs to be a skill.
52
53	---
54
55	## Creation Process
56
57	### Phase 1 — Discovery
58
59	Understand the problem before writing a single line. Ask conversationally:
60
61	- What workflow do you want to make consistent? Walk through the steps you do today.
62	- What goes wrong without the skill? (Inconsistency, forgotten steps, repeated explanation, wrong outputs)
63	- Who will use this skill? (Just you, your team, public)
64	- What tools or services are involved?
65
66	Collect 2–3 concrete use cases. For each, capture:
67
68	```
69	Trigger: What the user says/does
70	Steps: Sequence of actions
71	Tools: Built-in or MCP tools needed
72	Result: What success looks like (specific output)
73	```
74
75	Exit criteria: 2–3 use cases defined, success criteria agreed, tools/dependencies identified.
76
77	### Phase 2 — Architecture
78
79	Make structural decisions before writing:
80
81	1. Choose the primary pattern — Sequential workflow, iterative refinement, domain-specific intelligence, or multi-tool coordination. Read [references/workflows.md](references/workflows.md) for structure templates and the pattern-selection guide — load it now if you are unsure which pattern fits.
82	2. Plan the folder structure — Only add `scripts/`, `references/`, or `assets/` when there is a clear reason:
83	- Same code rewritten repeatedly → `scripts/`
84	- Reference material > ~100 lines → `references/`
85	- Output uses templates/images → `assets/`
86	3. Draft the description — This is the most important piece. See [Writing the Description](#writing-the-description) below.
87	4. Map content to disclosure levels — What goes in SKILL.md body vs. reference files?
88
89	Exit criteria: Pattern selected, folder structure planned, description drafted, content mapped.
90
91	### Phase 3 — Craft
92
93	Write SKILL.md with precision.
94
95	Frontmatter rules:
96
97	```yaml
98	---
99	name: kebab-cas

People who liked this also viewed

6 picks

Type

skill-creator

189stars53forks

View on GitHub

How to install skill-creator?

thomast1906/github-copilot-agent-skills/skill-creator

$npx -y skills add thomast1906/github-copilot-agent-skills --skill skill-creator

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Skill Creator
2
3	Create high-quality GitHub Copilot agent skills (SKILL.md) that transform the general-purpose agent into a specialized expert.
4
5	## What Is a Skill
6
7	A skill is a modular, self-contained knowledge package stored in `.github/skills/<skill-name>/SKILL.md`. It provides:
8
9	- Specialized workflows — Multi-step procedures for a specific domain
10	- Domain expertise — Company-specific schemas, patterns, business logic
11	- Tool integrations — Instructions for APIs, file formats, or services
12	- Bundled resources — Scripts, reference docs, and templates for reuse
13
14	Skills load in three levels (progressive disclosure):
15
16	1. Metadata (`name` + `description`) — Always in context (~100 words). This is the trigger mechanism.
17	2. SKILL.md body — Loaded when the skill triggers. Keep under 500 lines.
18	3. Bundled resources — Loaded on demand (scripts/, references/, assets/).
19
20	## Skill Anatomy
21
22	```
23	skill-name/
24	├── SKILL.md (required)
25	│ ├── YAML frontmatter name + description (required)
26	│ └── Markdown instructions
27	└── Bundled Resources (optional)
28	├── scripts/ Executable code for deterministic/repetitive tasks
29	├── references/ Docs loaded into context as needed
30	└── assets/ Output files (templates, icons, boilerplate)
31	```
32
33	Do NOT include: setup guides, changelogs, or user-facing documentation — skills are instructions for the agent, not onboarding docs for humans.
34
35	---
36
37	## Is a Skill the Right Vehicle?
38
39	Not every workflow needs a skill. Before creating one, choose the right tool:
40
41	\| Situation \| Use instead \|
42	\|---\|---\|
43	\| A rule that applies to ALL Copilot interactions in this repo \| `copilot-instructions.md` entry \|
44	\| A rule scoped to specific file types (e.g., always use `kebab-case` for Bicep variable names) \| `.github/instructions/*.instructions.md` with `applyTo` glob \|
45	\| A one-off prompt you run occasionally \| `.github/prompts/*.prompt.md` \|
46	\| A multi-step workflow with domain knowledge that benefits from on-demand loading \| Skill \|
47	\| A complex workflow with a dedicated agent persona \| `.github/agents/*.agent.md` \|
48
49	A skill is the right choice when: the workflow is too detailed for `copilot-instructions.md`, it should only load for relevant requests (not every conversation), and it encapsulates reusable domain knowledge or a repeatable process.
50
51	If the user's need is better served by a simpler vehicle, say so and use that instead. Not everything needs to be a skill.
52
53	---
54
55	## Creation Process
56
57	### Phase 1 — Discovery
58
59	Understand the problem before writing a single line. Ask conversationally:
60
61	- What workflow do you want to make consistent? Walk through the steps you do today.
62	- What goes wrong without the skill? (Inconsistency, forgotten steps, repeated explanation, wrong outputs)
63	- Who will use this skill? (Just you, your team, public)
64	- What tools or services are involved?
65
66	Collect 2–3 concrete use cases. For each, capture:
67
68	```
69	Trigger: What the user says/does
70	Steps: Sequence of actions
71	Tools: Built-in or MCP tools needed
72	Result: What success looks like (specific output)
73	```
74
75	Exit criteria: 2–3 use cases defined, success criteria agreed, tools/dependencies identified.
76
77	### Phase 2 — Architecture
78
79	Make structural decisions before writing:
80
81	1. Choose the primary pattern — Sequential workflow, iterative refinement, domain-specific intelligence, or multi-tool coordination. Read [references/workflows.md](references/workflows.md) for structure templates and the pattern-selection guide — load it now if you are unsure which pattern fits.
82	2. Plan the folder structure — Only add `scripts/`, `references/`, or `assets/` when there is a clear reason:
83	- Same code rewritten repeatedly → `scripts/`
84	- Reference material > ~100 lines → `references/`
85	- Output uses templates/images → `assets/`
86	3. Draft the description — This is the most important piece. See [Writing the Description](#writing-the-description) below.
87	4. Map content to disclosure levels — What goes in SKILL.md body vs. reference files?
88
89	Exit criteria: Pattern selected, folder structure planned, description drafted, content mapped.
90
91	### Phase 3 — Craft
92
93	Write SKILL.md with precision.
94
95	Frontmatter rules:
96
97	```yaml
98	---
99	name: kebab-cas

People who liked this also viewed

6 picks

Type