template

Name: template
Author: muratcankoylan

17kstars1.4kforks

How to install template?

muratcankoylan/agent-skills-for-context-engineering/template

$npx -y skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill template

Installs into the current project.

Summary

Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.

Files · 1

View on GitHub

SKILL.md

1	# Skill Name
2
3	Provide a clear, concise description of what this skill covers and when to use it. This description appears in skill discovery and should help agents (and humans) determine when this skill is relevant.
4
5	Important: Keep the total SKILL.md body under 500 lines for optimal performance. Move detailed reference material to separate files in the `references/` directory.
6
7	Every skill body must make its ownership boundary explicit. The description and `When to Activate` section should say what the skill owns and which adjacent skills own nearby work. This prevents broad skills from stealing activation from narrower skills.
8
9	## When to Activate
10
11	Describe specific situations, tasks, or contexts where this skill should be activated. Include both direct triggers (specific keywords or task types) and indirect signals (broader patterns that indicate skill relevance).
12
13	Write in third person. The description is injected into the system prompt, and inconsistent point-of-view can cause discovery problems.
14
15	- Good: "Processes Excel files and generates reports"
16	- Avoid: "I can help you process Excel files"
17
18	Include a short "Do not activate" block for adjacent skills. Example:
19
20	- Do not activate for project-level pipeline shape: `project-development`.
21	- Do not activate for individual tool schema design: `tool-design`.
22
23	## Core Concepts
24
25	Explain the fundamental concepts covered by this skill. These are the mental models, principles, or frameworks that the skill teaches.
26
27	Default assumption: Claude is already very smart. Only add context Claude does not already have. Challenge each piece of information:
28	- "Does Claude really need this explanation?"
29	- "Can I assume Claude knows this?"
30	- "Does this paragraph justify its token cost?"
31
32	Prefer behavior-changing mechanisms over general background. If a concept should be reusable across the corpus, add or update a record in `researcher/mechanisms/registry.jsonl`.
33
34	## Detailed Topics
35
36	### Topic 1
37
38	Provide detailed explanation of the first major topic. Include specific techniques, patterns, or approaches. Use examples to illustrate concepts.
39
40	### Topic 2
41
42	Provide detailed explanation of the second major topic. Continue with additional topics as needed.
43
44	For longer topics, consider moving content to `references/` and linking:
45	- See [detailed reference](./references/topic-details.md) for complete implementation
46
47	## Practical Guidance
48
49	Provide actionable guidance for applying the skill. Include common patterns, anti-patterns to avoid, and decision frameworks for choosing between approaches.
50
51	Match the level of specificity to the task's fragility:
52	- High freedom: Multiple approaches are valid, decisions depend on context
53	- Medium freedom: Preferred pattern exists, some variation acceptable
54	- Low freedom: Operations are fragile, specific sequence must be followed
55
56	Practical guidance should be executable by an agent: a workflow, checklist, decision table, or concrete operating rule. If a section only explains history or motivation, move it to `references/`.
57
58	## Examples
59
60	Provide concrete examples that illustrate skill application. Examples should show before/after comparisons, demonstrate correct usage, or show how to handle edge cases.
61
62	Use input/output pairs for clarity:
63
64	Example:
65	```
66	Input: [describe input]
67	Output: [show expected output]
68	```
69
70	## Guidelines
71
72	List specific guidelines to follow when applying this skill. These should be actionable rules that can be checked or verified.
73
74	1. Guideline one with specific, verifiable criteria
75	2. Guideline two with clear success conditions
76	3. Continue as needed
77
78	## Gotchas
79
80	List experience-derived failure modes, common mistakes, and counterintuitive behaviors. These are the highest-signal content in any skill. Each gotcha should be specific, actionable, and non-overlapping with guidance already in the skill body. Use numbered format:
81
82	1. Short descriptive title: One to two sentences explaining what goes wrong and how to prevent it.
83	2. Another gotcha title: Description of the failure mode and what to do instead.
84
85	## Integration
86
87	Explain how this skill integrates with other skills in the collection. List related skills as plain text (not links) to avoid cross-directory reference issues:
88
89	- skill-name-one - Brief description of relationship
90	- skill-name-two - Brief description of relationship
91
92	## References
93
94	Internal reference (use relative path to skill's own reference files):
95	- [Reference Name](./references/reference-file.md) - Description
96
97	Related skills in this collection:
98	- skill-name - Relationship description
99
100	External resources:
101	- Research papers, documentation, or guides
102
103	Numeric, benchmark, volatile, or vendor-performance claims need an inline `claim-*` ID backed by `researcher/claims/index.jsonl`, or they should be softened and moved to

muratcankoylanPublisher · 69 listings

Preview

muratcankoylan/Agent-Skills-for-Context-Engineering

# Skill Name

Provide a clear, concise description of what this skill covers and when to use it. This description appears in skill discovery and should help agents (and human

**Important**: Keep the total SKILL.md body under 500 lines for optimal performance. Move detailed reference material to separate files in the `references/` dir

Every skill body must make its ownership boundary explicit. The description and `When to Activate` section should say what the skill owns and which adjacent ski

Repomuratcankoylan/Agent-Skills-for-Context-Engineering

LicenseMIT

TypeSkills

CategoryGeneral

UpdatedJul 2026

Repo stars17k

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type

template

17kstars1.4kforks

View on GitHub

How to install template?

muratcankoylan/agent-skills-for-context-engineering/template

$npx -y skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill template

Installs into the current project.

Summary

Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.

Files · 1

View on GitHub

SKILL.md

1	# Skill Name
2
3	Provide a clear, concise description of what this skill covers and when to use it. This description appears in skill discovery and should help agents (and humans) determine when this skill is relevant.
4
5	Important: Keep the total SKILL.md body under 500 lines for optimal performance. Move detailed reference material to separate files in the `references/` directory.
6
7	Every skill body must make its ownership boundary explicit. The description and `When to Activate` section should say what the skill owns and which adjacent skills own nearby work. This prevents broad skills from stealing activation from narrower skills.
8
9	## When to Activate
10
11	Describe specific situations, tasks, or contexts where this skill should be activated. Include both direct triggers (specific keywords or task types) and indirect signals (broader patterns that indicate skill relevance).
12
13	Write in third person. The description is injected into the system prompt, and inconsistent point-of-view can cause discovery problems.
14
15	- Good: "Processes Excel files and generates reports"
16	- Avoid: "I can help you process Excel files"
17
18	Include a short "Do not activate" block for adjacent skills. Example:
19
20	- Do not activate for project-level pipeline shape: `project-development`.
21	- Do not activate for individual tool schema design: `tool-design`.
22
23	## Core Concepts
24
25	Explain the fundamental concepts covered by this skill. These are the mental models, principles, or frameworks that the skill teaches.
26
27	Default assumption: Claude is already very smart. Only add context Claude does not already have. Challenge each piece of information:
28	- "Does Claude really need this explanation?"
29	- "Can I assume Claude knows this?"
30	- "Does this paragraph justify its token cost?"
31
32	Prefer behavior-changing mechanisms over general background. If a concept should be reusable across the corpus, add or update a record in `researcher/mechanisms/registry.jsonl`.
33
34	## Detailed Topics
35
36	### Topic 1
37
38	Provide detailed explanation of the first major topic. Include specific techniques, patterns, or approaches. Use examples to illustrate concepts.
39
40	### Topic 2
41
42	Provide detailed explanation of the second major topic. Continue with additional topics as needed.
43
44	For longer topics, consider moving content to `references/` and linking:
45	- See [detailed reference](./references/topic-details.md) for complete implementation
46
47	## Practical Guidance
48
49	Provide actionable guidance for applying the skill. Include common patterns, anti-patterns to avoid, and decision frameworks for choosing between approaches.
50
51	Match the level of specificity to the task's fragility:
52	- High freedom: Multiple approaches are valid, decisions depend on context
53	- Medium freedom: Preferred pattern exists, some variation acceptable
54	- Low freedom: Operations are fragile, specific sequence must be followed
55
56	Practical guidance should be executable by an agent: a workflow, checklist, decision table, or concrete operating rule. If a section only explains history or motivation, move it to `references/`.
57
58	## Examples
59
60	Provide concrete examples that illustrate skill application. Examples should show before/after comparisons, demonstrate correct usage, or show how to handle edge cases.
61
62	Use input/output pairs for clarity:
63
64	Example:
65	```
66	Input: [describe input]
67	Output: [show expected output]
68	```
69
70	## Guidelines
71
72	List specific guidelines to follow when applying this skill. These should be actionable rules that can be checked or verified.
73
74	1. Guideline one with specific, verifiable criteria
75	2. Guideline two with clear success conditions
76	3. Continue as needed
77
78	## Gotchas
79
80	List experience-derived failure modes, common mistakes, and counterintuitive behaviors. These are the highest-signal content in any skill. Each gotcha should be specific, actionable, and non-overlapping with guidance already in the skill body. Use numbered format:
81
82	1. Short descriptive title: One to two sentences explaining what goes wrong and how to prevent it.
83	2. Another gotcha title: Description of the failure mode and what to do instead.
84
85	## Integration
86
87	Explain how this skill integrates with other skills in the collection. List related skills as plain text (not links) to avoid cross-directory reference issues:
88
89	- skill-name-one - Brief description of relationship
90	- skill-name-two - Brief description of relationship
91
92	## References
93
94	Internal reference (use relative path to skill's own reference files):
95	- [Reference Name](./references/reference-file.md) - Description
96
97	Related skills in this collection:
98	- skill-name - Relationship description
99
100	External resources:
101	- Research papers, documentation, or guides
102
103	Numeric, benchmark, volatile, or vendor-performance claims need an inline `claim-*` ID backed by `researcher/claims/index.jsonl`, or they should be softened and moved to

muratcankoylanPublisher · 69 listings

Preview

muratcankoylan/Agent-Skills-for-Context-Engineering

# Skill Name

Provide a clear, concise description of what this skill covers and when to use it. This description appears in skill discovery and should help agents (and human

**Important**: Keep the total SKILL.md body under 500 lines for optimal performance. Move detailed reference material to separate files in the `references/` dir

Every skill body must make its ownership boundary explicit. The description and `When to Activate` section should say what the skill owns and which adjacent ski

Repomuratcankoylan/Agent-Skills-for-Context-Engineering

LicenseMIT

TypeSkills

CategoryGeneral

UpdatedJul 2026

Repo stars17k

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type