Real Skill packageSource verifiedClawHub registry

rabbit-writes

Write, edit, or audit prose in a specific person's saved voice, or strip machine-writing patterns when there is no voice to apply. Use whenever the user will send or publish text as themselves (emails, Slack and chat messages, reports, incident writeups, reviews, proposals, documentation, personal correspondence), and whenever the user asks to humanize text, remove AI-isms or AI slop, de-slop a draft, check whether writing sounds AI-generated, make a draft sound less like a chatbot, rewrite something in their voic…

Identity and source

Publisher attributionwhit3rabbitregistry owner unverified by skillvetai
Functional categorySearch, Research & Knowledgeautomatically inferred · 63% rule confidence
Package forminstruction with code88 recorded files
Canonical sourceClawHub registryclawhub:whit3rabbit:rabbit-writes
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/31/2026.claude/skills/rabbit-writes

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/31/2026.agents/skills/rabbit-writes

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/31/2026skills/rabbit-writes

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @whit3rabbit/rabbit-writes
clawhub inspect @whit3rabbit/rabbit-writes --version 0.5.0

Security evidence

SkillVetAI static result: medium signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
partial text content
Files
40 / 88 inspected as text
Checked
8/31/2026, 5:39:44 AM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
mediumPrompt-override language requires reviewscripts/rwlib/suppress.py:148 · confidence 62%ignore all previous instructions
5 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
5 dependency and API indicators
  • api: doi.org
  • api: github.com
  • api: json.schemastore.org
  • api: schemas.openxmlformats.org
  • api: x.dev
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
8/30/2026, 5:41:47 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:93fd3738bb8100269898d72dce1c740ce261de3976adefc2b65276a69331b5fe
Show up to 30 recorded paths
  • references/checklist.md
  • references/citations/apa7.md
  • references/citations/chicago17.md
  • references/citations/ieee.md
  • references/citations/mla9.md
  • references/context.md
  • references/craft.md
  • references/false-positives.md
  • references/forms/abstract.md
  • references/forms/blog.md
  • references/forms/case-study.md
  • references/forms/chat.md
  • references/forms/docs.md
  • references/forms/email.md
  • references/forms/essay.md
  • references/forms/executive-summary.md
  • references/forms/incident-report.md
  • references/forms/letter.md
  • references/forms/linkedin.md
  • references/forms/literature-review.md
  • references/forms/memo.md
  • references/forms/pentest-report.md
  • references/forms/proposal.md
  • references/forms/research-paper.md
  • references/forms/security-advisory.md
  • references/forms/substack.md
  • references/forms/technical-blog.md
  • references/forms/technical-report.md
  • references/forms/thesis-chapter.md
  • references/forms/whitepaper.md

Source changelog

rabbit-writes 0.5.0 - Expanded and clarified skill description and operating principles in SKILL.md. - Defined four separate audit bands: safety, voice, fingerprints, and craft. - Added explicit editing guardrails to prevent fact invention, voice fabrication, over-editing, and loss of original human signals. - Detailed matrix of supported modes (detect, deslop, voice) with clear allowed operations for each. - Specified never to rewrite certain elements (code, tables, legal, etc.) and outlined safety checks before running rewrites. - Included MIT-0 license and metadata for integration.