Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

$pwd:

create-agent

Name: Create Agent
Author: alexanderop

// Scaffold a new custom agent — reviewers, researchers, or workflow agents. Use when asked to create, scaffold, or add a new agent.

In Manus ausführen

$ git log --oneline --stat

stars:0

forks:0

updated:4. April 2026 um 13:49

SKILL.md

readonly

name	create-agent
description	Scaffold a new custom agent — reviewers, researchers, or workflow agents. Use when asked to create, scaffold, or add a new agent.
argument-hint	Describe the agent to create (e.g., 'Vue reviewer', 'Python linter')

Create Agent

Scaffold a new .agent.md file with correct VS Code Copilot frontmatter and structure.

Workflow

Step 1: Determine Agent Type

Ask the user what kind of agent they want to create:

Reviewer — a code review subagent (dispatched by the creview orchestrator)
Researcher — a read-only codebase exploration agent
Workflow — a user-facing agent for specific tasks

Step 2: Gather Details

Based on agent type, ask:

Name — lowercase, hyphenated (e.g., vue-reviewer, python-linter)
Description — what it does in one sentence
Domain — what file types or patterns it targets (for reviewers)

Step 3: Generate the Agent File

For Reviewers

Reviewers are subagents dispatched by the creview orchestrator. They:

Are hidden from the user dropdown
Cannot be auto-invoked by other agents
Have read-only tools only
Follow the standard finding output format

---
name: [name]-reviewer
description: "[What it reviews] — [specific focus areas]"
user-invocable: false
disable-model-invocation: true
tools: ['search/codebase', 'search/usages']
---

The body should include:

Clear role description
What to look for (specific patterns, smells, or violations)
Confidence calibration (High/Medium/Low with definitions)
What NOT to flag (to avoid noise)
Standard output format (Finding with Severity, Confidence, File, Category, Description, Suggestion)

For Researchers

Researchers are read-only subagents used by other agents for codebase exploration.

---
name: [name]
description: "[What it researches]"
user-invocable: false
disable-model-invocation: true
tools: ['search/codebase', 'search/usages', 'search/changes', 'web/fetch']
---

For Workflow Agents

Workflow agents are user-facing and can have full tool access.

---
name: [name]
description: "[What it does]"
argument-hint: "[Expected input]"
tools: ['*']
---

Step 4: Place the File

Write the agent file to .github/agents/[name].agent.md.

Step 5: Explain Auto-Discovery

For reviewers, explain:

The creview orchestrator uses agents: ['*'] and auto-discovers all *-reviewer.agent.md files
It reads the reviewer's description to determine if it's relevant to the current diff
The reviewer will be dispatched automatically when files matching its domain are changed
No configuration needed — just create the file and it's active

VS Code Copilot Frontmatter Reference

Field	Type	Notes
`name`	string	Agent identifier (lowercase, hyphenated)
`description`	string	Shown in chat input; used for smart routing
`argument-hint`	string	Guidance text for input
`tools`	string[]	Tool/tool-set names
`agents`	string[] or `*`	Subagent availability
`user-invocable`	boolean	Show in dropdown (default: true)
`disable-model-invocation`	boolean	Prevent auto-invocation (default: false)
`handoffs`	object[]	Workflow transitions

Banned fields (Claude Code only — must not appear): color, context, allowed-tools, disallowedTools

Deprecated fields: infer — use user-invocable and disable-model-invocation instead

related-skills.json

gleiches Repository

brainstorm.md

from "alexanderop/oteleexample"

Explore requirements and approaches through collaborative dialogue before writing a right-sized requirements document and planning implementation. Use for feature ideas, problem framing, when the user says 'let's brainstorm', or when they want to think through options before deciding what to build.

2026-04-040

compound.md

from "alexanderop/oteleexample"

Document a solved problem as reusable institutional knowledge with parallel research. Use when the user says 'document this', 'compound', 'save learnings', or wants to capture a solution for future reference.

2026-04-040

cplan.md

from "alexanderop/oteleexample"

Research the codebase and create a structured implementation plan. Use when the user says 'plan this', 'create a plan', 'how should we implement', or wants to turn a feature description into a structured implementation plan.

2026-04-040

deepen.md

from "alexanderop/oteleexample"

Enhance an existing plan with parallel research agents for depth, best practices, and implementation details. Use when the user says 'deepen the plan', 'research more', or when a plan has high-risk dimensions that need more investigation.

2026-04-040

document-review.md

from "alexanderop/oteleexample"

Review requirements or plan documents using parallel persona agents that surface role-specific issues. Use when a requirements document or plan document exists and the user wants to improve it, or when invoked by /cplan for quality gating.

2026-04-040

git-commit-push-pr.md

from "alexanderop/oteleexample"

Commit, push, and open a PR with an adaptive, value-first description. Use when the user says "commit and PR", "push and open a PR", "ship this", "create a PR", "open a pull request", or wants to go from working changes to an open pull request in one step. Also handles "update the PR description" or "refresh the PR description".

2026-04-040

package.json

"author": "alexanderop"

"repository": "alexanderop/oteleexample"

GitHub-Repository öffnen Creator-Repositorys ansehen

$ install --global

$ download --local

In Manus ausführen

$ useful --forSOC

SoftwareentwicklerInformatik- und Mathematikberufe15-1252L4

name	create-agent
description	Scaffold a new custom agent — reviewers, researchers, or workflow agents. Use when asked to create, scaffold, or add a new agent.
argument-hint	Describe the agent to create (e.g., 'Vue reviewer', 'Python linter')

Create Agent

Scaffold a new .agent.md file with correct VS Code Copilot frontmatter and structure.

Workflow

Step 1: Determine Agent Type

Ask the user what kind of agent they want to create:

Reviewer — a code review subagent (dispatched by the creview orchestrator)
Researcher — a read-only codebase exploration agent
Workflow — a user-facing agent for specific tasks

Step 2: Gather Details

Based on agent type, ask:

Name — lowercase, hyphenated (e.g., vue-reviewer, python-linter)
Description — what it does in one sentence
Domain — what file types or patterns it targets (for reviewers)

Step 3: Generate the Agent File

For Reviewers

Reviewers are subagents dispatched by the creview orchestrator. They:

Are hidden from the user dropdown
Cannot be auto-invoked by other agents
Have read-only tools only
Follow the standard finding output format

---
name: [name]-reviewer
description: "[What it reviews] — [specific focus areas]"
user-invocable: false
disable-model-invocation: true
tools: ['search/codebase', 'search/usages']
---

The body should include:

Clear role description
What to look for (specific patterns, smells, or violations)
Confidence calibration (High/Medium/Low with definitions)
What NOT to flag (to avoid noise)
Standard output format (Finding with Severity, Confidence, File, Category, Description, Suggestion)

For Researchers

Researchers are read-only subagents used by other agents for codebase exploration.

---
name: [name]
description: "[What it researches]"
user-invocable: false
disable-model-invocation: true
tools: ['search/codebase', 'search/usages', 'search/changes', 'web/fetch']
---

For Workflow Agents

Workflow agents are user-facing and can have full tool access.

---
name: [name]
description: "[What it does]"
argument-hint: "[Expected input]"
tools: ['*']
---

Step 4: Place the File

Write the agent file to .github/agents/[name].agent.md.

Step 5: Explain Auto-Discovery

For reviewers, explain:

The creview orchestrator uses agents: ['*'] and auto-discovers all *-reviewer.agent.md files
It reads the reviewer's description to determine if it's relevant to the current diff
The reviewer will be dispatched automatically when files matching its domain are changed
No configuration needed — just create the file and it's active

VS Code Copilot Frontmatter Reference

Field	Type	Notes
`name`	string	Agent identifier (lowercase, hyphenated)
`description`	string	Shown in chat input; used for smart routing
`argument-hint`	string	Guidance text for input
`tools`	string[]	Tool/tool-set names
`agents`	string[] or `*`	Subagent availability
`user-invocable`	boolean	Show in dropdown (default: true)
`disable-model-invocation`	boolean	Prevent auto-invocation (default: false)
`handoffs`	object[]	Workflow transitions

Banned fields (Claude Code only — must not appear): color, context, allowed-tools, disallowedTools

Deprecated fields: infer — use user-invocable and disable-model-invocation instead

create-agent

Create Agent

Workflow

Step 1: Determine Agent Type

Step 2: Gather Details

Step 3: Generate the Agent File

For Reviewers

For Researchers

For Workflow Agents

Step 4: Place the File

Step 5: Explain Auto-Discovery

VS Code Copilot Frontmatter Reference

Mehr aus diesem Repository

Mehr aus diesem Repository

Create Agent

Workflow

Step 1: Determine Agent Type

Step 2: Gather Details

Step 3: Generate the Agent File

For Reviewers

For Researchers

For Workflow Agents

Step 4: Place the File

Step 5: Explain Auto-Discovery

VS Code Copilot Frontmatter Reference