.claude/skills/rabbit-writesRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
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…
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/rabbit-writesRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/rabbit-writesRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/rabbit-writesRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
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-writesclawhub inspect @whit3rabbit/rabbit-writes --version 0.5.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
ignore all previous instructionsThis 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.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:93fd3738bb8100269898d72dce1c740ce261de3976adefc2b65276a69331b5fereferences/checklist.mdreferences/citations/apa7.mdreferences/citations/chicago17.mdreferences/citations/ieee.mdreferences/citations/mla9.mdreferences/context.mdreferences/craft.mdreferences/false-positives.mdreferences/forms/abstract.mdreferences/forms/blog.mdreferences/forms/case-study.mdreferences/forms/chat.mdreferences/forms/docs.mdreferences/forms/email.mdreferences/forms/essay.mdreferences/forms/executive-summary.mdreferences/forms/incident-report.mdreferences/forms/letter.mdreferences/forms/linkedin.mdreferences/forms/literature-review.mdreferences/forms/memo.mdreferences/forms/pentest-report.mdreferences/forms/proposal.mdreferences/forms/research-paper.mdreferences/forms/security-advisory.mdreferences/forms/substack.mdreferences/forms/technical-blog.mdreferences/forms/technical-report.mdreferences/forms/thesis-chapter.mdreferences/forms/whitepaper.mdrabbit-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.