agent-creator

Name: agent-creator
Author: krzysztofsurdy

20installs1forks

How to install agent-creator?

krzysztofsurdy/code-virtuoso/agent-creator

$npx -y skills add krzysztofsurdy/code-virtuoso --skill agent-creator

Installs into the current project.

Summary

Interactive tool to design a well-scoped sub-agent definition - specialist, role, or team-lead - with the right frontmatter, tool permissions, isolation, memory, and system prompt. Use when the user asks to create a sub-agent, write an agent file, design a specialized worker, sca

Files · 1

View on GitHub

SKILL.md

1	# Agent Creator
2
3	Create a sub-agent that earns its context window. Most agents fail not because the model is weak but because the definition is vague - unclear trigger, sprawling tool list, a body that mixes persona and procedure, and no output contract. This skill walks you through a six-phase design so the resulting agent is focused, least-privileged, and predictable.
4
5	## Core Principles
6
7	\| Principle \| Meaning \|
8	\|---\|---\|
9	\| One job, one agent \| An agent that does two things does neither well. Split the responsibility before writing. \|
10	\| Least privilege \| Grant the smallest tool set that lets the agent finish its job. Read-only by default. \|
11	\| Trigger-first description \| The `description` field is the only thing read before delegation. Pack it with keywords and "when to use". \|
12	\| Contract over conversation \| Define explicit input, process, and output. Agents are not chat sessions. \|
13	\| Isolation when writing \| If the agent edits files, run it in a worktree so the orchestrator can review before merging. \|
14	\| Portable body, platform frontmatter \| Keep the system prompt agent-agnostic. Adapt frontmatter fields per target platform. \|
15
16	---
17
18	## Agent vs Skill - Quick Disambiguation
19
20	Before creating an agent, confirm it is the right primitive.
21
22	\| Use a Skill \| Use an Agent \|
23	\|---\|---\|
24	\| Reference material (patterns, checklists, schemas) \| Work to perform (investigate, review, implement) \|
25	\| Loaded into an existing session \| Runs in its own context window \|
26	\| Passive knowledge \| Active actor with tools and a workflow \|
27	\| "Where do I learn about X" \| "Do X for me and return a result" \|
28
29	If the answer is reference material, stop and use the `skill-creator` skill instead. If the answer is work, continue.
30
31	---
32
33	## Archetype Selection
34
35	Agents fall into three archetypes. Pick one before designing.
36
37	\| Archetype \| Scope \| Memory \| Modifies files \| Typical examples \|
38	\|---\|---\|---\|---\|---\|
39	\| Specialist \| Single, repeatable task type \| Stateless \| Rarely (doc writer, implementer) \| Investigator, Reviewer, Refactor Scout, Dependency Auditor, Test Gap Analyzer \|
40	\| Role \| Entire domain of responsibility \| Often persistent (project-level) \| Dev roles yes, others no \| Product Manager, Architect, Backend Dev, QA Engineer, Project Manager \|
41	\| Team-Lead \| Coordinates multiple workers in parallel \| Shared task list \| No (delegates) \| Orchestrator, release-train lead, review dispatcher \|
42
43	### Decision tree
44
45	1. Does the agent do one repeatable task type (review this PR, investigate this area, audit dependencies)? -> Specialist
46	2. Does the agent own a domain across many task types and benefit from remembering context across sessions (requirements, architecture decisions, risk register)? -> Role
47	3. Does the agent need to spawn and coordinate other agents working in parallel (research teams, multi-layer refactors)? -> Team-Lead
48
49	If the user provided an archetype as an argument, use it. Otherwise present a selectable menu using `AskUserQuestion` (or the platform's equivalent interactive prompt) with the three options from the table above.
50
51	See [references/archetypes.md](references/archetypes.md) for worked examples of each archetype and the anti-patterns to avoid.
52
53	---
54
55	## Workflow
56
57	This skill uses guided phases - each phase is a separate file loaded one at a time. Every phase ends with a gate where you must wait for user confirmation before proceeding. Do not skip phases or merge them.
58
59	\| Phase \| File \| What it covers \|
60	\|---\|---\|---\|
61	\| 1 \| [Purpose and Trigger](phases/01-purpose-and-trigger.md) \| What the agent does, when to delegate, out-of-scope, output shape, archetype \|
62	\| 2 \| [Name and Identity](phases/02-name-and-identity.md) \| Kebab-case name, collision check, user confirmation \|
63	\| 3 \| [Capabilities](phases/03-capabilities.md) \| Tool permissions, isolation, memory, preloaded skills \|
64	\| 4 \| [System Prompt](phases/04-system-prompt.md) \| Five-section contract: Input, Process, Rules, Output \|
65	\| 5 \| [Placement and Scope](phases/05-placement-and-scope.md) \| Where the file lives: project, personal, plugin, session \|
66	\| 6 \| [Validate and Write](phases/06-validate-and-write.md) \| Checklist, file creation, marketplace registration \|
67
68	Start by loading Phase 1. After the user confirms each phase, load the next. Never load multiple phases at once. Never skip a pha

People who liked this also viewed

6 picks

Type

agent-creator

20installs1forks

View on GitHub

How to install agent-creator?

krzysztofsurdy/code-virtuoso/agent-creator

$npx -y skills add krzysztofsurdy/code-virtuoso --skill agent-creator

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Agent Creator
2
3	Create a sub-agent that earns its context window. Most agents fail not because the model is weak but because the definition is vague - unclear trigger, sprawling tool list, a body that mixes persona and procedure, and no output contract. This skill walks you through a six-phase design so the resulting agent is focused, least-privileged, and predictable.
4
5	## Core Principles
6
7	\| Principle \| Meaning \|
8	\|---\|---\|
9	\| One job, one agent \| An agent that does two things does neither well. Split the responsibility before writing. \|
10	\| Least privilege \| Grant the smallest tool set that lets the agent finish its job. Read-only by default. \|
11	\| Trigger-first description \| The `description` field is the only thing read before delegation. Pack it with keywords and "when to use". \|
12	\| Contract over conversation \| Define explicit input, process, and output. Agents are not chat sessions. \|
13	\| Isolation when writing \| If the agent edits files, run it in a worktree so the orchestrator can review before merging. \|
14	\| Portable body, platform frontmatter \| Keep the system prompt agent-agnostic. Adapt frontmatter fields per target platform. \|
15
16	---
17
18	## Agent vs Skill - Quick Disambiguation
19
20	Before creating an agent, confirm it is the right primitive.
21
22	\| Use a Skill \| Use an Agent \|
23	\|---\|---\|
24	\| Reference material (patterns, checklists, schemas) \| Work to perform (investigate, review, implement) \|
25	\| Loaded into an existing session \| Runs in its own context window \|
26	\| Passive knowledge \| Active actor with tools and a workflow \|
27	\| "Where do I learn about X" \| "Do X for me and return a result" \|
28
29	If the answer is reference material, stop and use the `skill-creator` skill instead. If the answer is work, continue.
30
31	---
32
33	## Archetype Selection
34
35	Agents fall into three archetypes. Pick one before designing.
36
37	\| Archetype \| Scope \| Memory \| Modifies files \| Typical examples \|
38	\|---\|---\|---\|---\|---\|
39	\| Specialist \| Single, repeatable task type \| Stateless \| Rarely (doc writer, implementer) \| Investigator, Reviewer, Refactor Scout, Dependency Auditor, Test Gap Analyzer \|
40	\| Role \| Entire domain of responsibility \| Often persistent (project-level) \| Dev roles yes, others no \| Product Manager, Architect, Backend Dev, QA Engineer, Project Manager \|
41	\| Team-Lead \| Coordinates multiple workers in parallel \| Shared task list \| No (delegates) \| Orchestrator, release-train lead, review dispatcher \|
42
43	### Decision tree
44
45	1. Does the agent do one repeatable task type (review this PR, investigate this area, audit dependencies)? -> Specialist
46	2. Does the agent own a domain across many task types and benefit from remembering context across sessions (requirements, architecture decisions, risk register)? -> Role
47	3. Does the agent need to spawn and coordinate other agents working in parallel (research teams, multi-layer refactors)? -> Team-Lead
48
49	If the user provided an archetype as an argument, use it. Otherwise present a selectable menu using `AskUserQuestion` (or the platform's equivalent interactive prompt) with the three options from the table above.
50
51	See [references/archetypes.md](references/archetypes.md) for worked examples of each archetype and the anti-patterns to avoid.
52
53	---
54
55	## Workflow
56
57	This skill uses guided phases - each phase is a separate file loaded one at a time. Every phase ends with a gate where you must wait for user confirmation before proceeding. Do not skip phases or merge them.
58
59	\| Phase \| File \| What it covers \|
60	\|---\|---\|---\|
61	\| 1 \| [Purpose and Trigger](phases/01-purpose-and-trigger.md) \| What the agent does, when to delegate, out-of-scope, output shape, archetype \|
62	\| 2 \| [Name and Identity](phases/02-name-and-identity.md) \| Kebab-case name, collision check, user confirmation \|
63	\| 3 \| [Capabilities](phases/03-capabilities.md) \| Tool permissions, isolation, memory, preloaded skills \|
64	\| 4 \| [System Prompt](phases/04-system-prompt.md) \| Five-section contract: Input, Process, Rules, Output \|
65	\| 5 \| [Placement and Scope](phases/05-placement-and-scope.md) \| Where the file lives: project, personal, plugin, session \|
66	\| 6 \| [Validate and Write](phases/06-validate-and-write.md) \| Checklist, file creation, marketplace registration \|
67
68	Start by loading Phase 1. After the user confirms each phase, load the next. Never load multiple phases at once. Never skip a pha

People who liked this also viewed

6 picks

Type