Real Skill packageSource verifiedClawHub registry

rabbit-rewrites

Rewrite the prose the engine flagged using a small local model over an OpenAI-compatible endpoint, instead of spending a frontier model on it. Use when the user wants to de-slop or humanize a draft offline, on a Raspberry Pi, in CI, or in a pre-commit hook, mentions llama.cpp, llama-server, Ollama, LM Studio, vLLM, or OpenRouter for writing work, asks which local model is good enough to clean up their writing, wants rewriting that costs no API tokens, or asks to benchmark or compare models on a rewriting task. Cov…

Identity and source

Publisher attributionwhit3rabbitregistry owner unverified by skillvetai
Functional categoryWriting, Content & Translationautomatically inferred · 62% rule confidence
Package forminstruction with code54 recorded files
Canonical sourceClawHub registryclawhub:whit3rabbit:rabbit-rewrites
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-rewrites

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-rewrites

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-rewrites

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-rewrites
clawhub inspect @whit3rabbit/rabbit-rewrites --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 / 54 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
8 dependency and API indicators
  • api: clawhub.ai
  • api: github.com
  • api: huggingface.co
  • api: json.schemastore.org
  • api: openrouter.ai
  • api: schemas.openxmlformats.org
  • api: www.asd-ste100.org
  • api: x.dev
External clawhub result: suspicious

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, 5:48:29 PM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

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

Package content hashsha256:b12b8a0fc4c9bdbbc2fbca422a22c863e21c4b9750239181a36dd23da8553dfc
Show up to 30 recorded paths
  • references/models.md
  • scripts/battery.json
  • scripts/bench.py
  • scripts/claude_hook.py
  • scripts/lexicon.json
  • scripts/registers.json
  • scripts/rwlib/__init__.py
  • scripts/rwlib/API.md
  • scripts/rwlib/artifacts.py
  • scripts/rwlib/cli_error.py
  • scripts/rwlib/corpus.py
  • scripts/rwlib/docx_text.py
  • scripts/rwlib/endpoint.py
  • scripts/rwlib/facts.py
  • scripts/rwlib/findings.py
  • scripts/rwlib/fixes.py
  • scripts/rwlib/inflect.py
  • scripts/rwlib/injection.py
  • scripts/rwlib/language.py
  • scripts/rwlib/lexicon.py
  • scripts/rwlib/links.py
  • scripts/rwlib/markdown.py
  • scripts/rwlib/outputstyle.py
  • scripts/rwlib/registers.py
  • scripts/rwlib/rewrite.py
  • scripts/rwlib/sarif.py
  • scripts/rwlib/sections.py
  • scripts/rwlib/sentences.py
  • scripts/rwlib/ste.py
  • scripts/rwlib/stylometry.py

Source changelog

- Adds support for rewriting flagged prose using small local models via OpenAI-compatible endpoints, enabling offline or local model rewriting. - Introduces `.rabbit-model` configuration file and environment variable support for persistent, automatic endpoint/model settings. - Documents targeted chunking for minimal context requests, strict system prompt rules, and style presets (plain, TL;DR, 5-year-old). - Ensures safe rewrites: all completions are verified for fact preservation and required edits, with automatic retries on failure. - Provides quick setup instructions for popular local model servers (llama-server, Ollama) and benchmarking guidance.