Plugin
Skill alessiomarcone/agent-fieldbook/plugins/knowledge-pack/skills/plugin
Source-backed skills that turn official Claude and Codex training into reliable daily workflows.
npx -y skills add alessiomarcone/agent-fieldbook --skill pluginAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 17 days oldThe repository was created 17 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Designs, packages, validates, and prepares distributable plugins containing skills and optional supported extensions. Use when the user asks to build, migrate, publish, install, distribute, or troubleshoot a Claude Code, Cowork, ChatGPT, or Codex plugin or marketplace; not for creating one standalone skill.
SKILL.md
2.2 KB, as published. Nobody here has run it
Plugin
Resolve the product and distribution surface before writing any manifest.
References
Read only the selected product branch:
- Claude Code:
references/claude-code-plugins.md. - Claude Cowork:
references/plugin-building.md. - Codex:
references/codex-plugins.md.
Procedure
- Identify target product, installation model, namespace, and public or private distribution path.
- Inventory only required capabilities: skills, agents/subagents, hooks, MCP/connectors/apps, or supported assets.
- Prefer several focused skills with explicit handoffs over one broad workflow.
- Keep every declared component inside the distributable boundary.
- Use only fields supported by the selected product's current schema.
- Document install, direct invocation, permissions, provenance, update, and uninstall behavior.
- Validate source and packaged artifact; install in a clean environment; test direct and contextual activation.
- For public submission, prepare the exact listing, legal, safety, and reviewer materials required by that ecosystem.
Output contract
Return:
- Target — product, installation model, namespace, and distribution path.
- Architecture — component tree and reason for each component.
- Files — ready-to-use manifests and components when implementation is requested.
- Install and invoke — exact current commands.
- Release gate — validation, clean install, permissions audit, tests, and versioning.
Boundaries
- Do not mix fields from different plugin ecosystems.
- Do not activate for creation or revision of a single standalone skill; route that work to
skill. - Do not declare components without their companion files.
- Do not claim commands, UI paths, or submission requirements without current official support.
- Do not distribute credentials, private data, raw transcripts, or unlicensed material.
- Answer in the user's language.