Designs safe, source-grounded Cowork workflows with folders, connectors, skills, schedules, approval gates, and human verification. Use when the user asks how to delegate operational work in Cowork, automate recurring briefs, customize Cowork, or design a multi-source legal, sales, marketing, finance, or small-business workflow.
Scanned 9/4/2026
Install to Claude Code
npx -y skills add alessiomarcone/agent-fieldbook --skill cowork --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Cowork?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/alessiomarcone-cowork)More formats (shields.io, HTML) on the badges page.
---
name: cowork
description: Designs safe, source-grounded Cowork workflows with folders, connectors, skills, schedules, approval gates, and human verification. Use when the user asks how to delegate operational work in Cowork, automate recurring briefs, customize Cowork, or design a multi-source legal, sales, marketing, finance, or small-business workflow.
---
# Cowork
Turn an operational objective into a Cowork workflow that stays reviewable and under human control.
## References
- Always read `references/knowledge-base.md` for product selection.
- Read `references/sources.md` before making a time-sensitive product claim.
- Read `references/cowork.md` and `references/desktop-app.md` for delegated desktop workflows.
- Read `references/claude-code-estensioni.md` for Claude Code extensions.
- Read `references/plugin-building.md` only for customization or distribution.
## Procedure
1. Resolve the outcome, source context, cadence, collaborators, risk, and required external systems.
2. Confirm Cowork is the right surface: use normal Chat/Projects for conversation and shared knowledge, and Claude Code for repository engineering.
3. Define the one-time setup: working folder, connected sources, stable instructions, and any reusable skill.
4. Write the brief with expected output, freshness window, missing-data behavior, boundaries, and success checks.
5. Add approval gates before messages, publishing, sensitive edits, purchases, or irreversible actions.
6. Require source-linked verification and a human first-run review for consequential workflows.
7. Verify current plans, UI paths, connectors, scheduling, and availability before stating them as current.
## Output contract
Return:
1. **Fit** — why Cowork is the right surface.
2. **Setup** — folders, permissions, connectors, and reusable guidance.
3. **Ready brief** — the exact on-demand or scheduled request.
4. **Approval and verification** — required human gates and checks.
5. **Reuse** — what should become persistent instructions, a skill, or a plugin.
## Boundaries
- Do not assume unconnected data is accessible.
- Do not send, publish, approve, or schedule external work without authority.
- Do not transfer Codex configuration into Claude products.
- Answer in the user's language.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!