lucassantana-dev/forgekit/create-subagent
Claude Code and agent skill by lucassantana-dev/forgekit
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Design and author reusable subagents for specialized AI tasks. Use when the task needs an isolated agent persona, scoped system prompt, or reusable domain-specific assistant rather than a general skill.
Install
npx vskill@latest install lucassantana-dev/forgekit/create-subagentSKILL.md
The same SKILL.md was published earlier as majiayu000/claude-skill-registry-data/create-subagent.
Create Subagent
Use this skill to decide whether a subagent is the right abstraction and to author it correctly.
Use When
- The task needs an isolated prompt and context boundary.
- A reusable specialist agent would be clearer than one large skill or one-off prompt.
- The user wants a named assistant for repeat work such as review, debugging, or domain analysis.
Do Not Use When
- A skill is the better abstraction because the behavior is procedural and tool-driven.
- The user only needs one temporary prompt, not a reusable subagent.
- The request is about orchestrating many agents together. Use
agent-teams.
Inputs / Prereqs
- The subagent's job, scope, and success criteria.
- Target location and priority rules.
- Example prompts or tasks the subagent must handle.
references/subagent-examples.md,references/location-rules.md, orreferences/troubleshooting.mdwhen needed.
Workflow
- Decide whether the behavior belongs in a subagent, a skill, or a one-off prompt.
- Define the subagent's scope, boundaries, and expected outputs.
- Pick the correct storage location and naming convention.
- Author the prompt and configuration with one clear responsibility.
- Validate the subagent against one representative task and report the expected invocation pattern.
Outputs / Evidence
- A subagent brief with role, scope, prompt shape, and storage location.
- The criteria that make a subagent preferable to a skill or one-off prompt.
- One representative invocation example.
Failure / Stop Conditions
- Stop if the behavior is too broad for one subagent.
- Stop if the request would be better served by a skill or plain prompt.
- Do not create overlapping subagents with unclear ownership.
Load These Resources
references/location-rules.mdreferences/subagent-examples.mdreferences/troubleshooting.md
Memory Hooks
- Read memory when existing project-specific agent conventions matter.
- Write memory only if the session establishes a durable subagent standard or naming rule.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpackages/catalog/catalog/skills/create-subagent/SKILL.md
Popularity
- Repository stars
- 1
- Repository forks
- 1
- 7-day trend score
- 8
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/lucassantana-dev/forgekit/create-subagent)