Write

Plan, draft, version, and refine written content with enforced versioning and quality audits.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "Write" with this command: npx skills add ivangdavila/write

Setup

On first use, create workspace:

./scripts/init-workspace.sh ~/writing

Workflow

Request → Plan → Draft → Audit → Refine → Deliver

Rules:

  • Delegate all writing to sub-agents — main stays free
  • NEVER edit files directly — use ./scripts/edit.sh (enforces versioning)
  • Run quality audit before delivering anything long (see audit.md)
  • Offer cleanup only after user confirms piece is final

Configuration

Set in config.json:

  • depth: "quick" | "standard" | "thorough" — controls research and revision passes
  • auto_audit: true/false — run audits automatically after drafts

Scripts (Enforced)

ScriptPurpose
init-workspace.shCreate project structure
new-piece.shStart new writing piece with ID
edit.shEdit with automatic version backup
audit.shRun quality audit, generate report
list.shShow all pieces and versions
restore.shRestore previous version
cleanup.shRemove old versions (with confirmation)

References: brief.md for planning, execution.md for drafting, verification.md for quality checks, state.md for tracking, research.md for investigation, versioning.md for version rules, audit.md for dimensions, criteria.md for preferences. Scripts in scripts/: scripts/init-workspace.sh, scripts/new-piece.sh, scripts/edit.sh, scripts/audit.sh, scripts/list.sh, scripts/restore.sh, scripts/cleanup.sh.


Preferences

<!-- User's writing preferences -->

Never

<!-- Things that don't work for this user -->

Empty sections = observe and fill.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Security

Session Password

Provides secure session authentication using bcrypt-hashed passwords, security questions, email recovery, and lockout protection with audit logging.

Registry SourceRecently Updated
Security

agent-bom registry

MCP server security registry and trust assessment — look up servers in the 427+ server security metadata registry, run pre-install marketplace checks, batch...

Registry SourceRecently Updated
Security

agent-bom scan

Security scanner for AI infrastructure — discovers MCP clients and servers, checks packages for CVEs (OSV, NVD, EPSS, KEV), maps blast radius, and generates...

Registry SourceRecently Updated
0128
Profile unavailable