Writing & Content text-rewritingchinese-writingde-ai-tonetechnical-writingprompt-engineeringstyle-editingfidelity-preserving

Shuorenhua: Chinese AI-Tone Cleanup Skill

A Chinese-first rewrite skill that strips AI boilerplate and translation-ese while preserving facts, attribution, and numbers — output ready to publish.

FollowSkills review · FSRS-2.0
Recommended
65/ 100 5-point scale 3.3 / 5
1 2 3 4 5 6
1Trust20 / 25 · 4.0/5

SKILL.md is pure text-editing rules: no external calls, no dependencies, no sensitive-data handling; minimal edits by default, code blocks preserved verbatim, transparent data flow. Deducted for: no rollback mechanism stated, unverified publisher identity.

2Reliability10 / 20 · 2.5/5

High internal consistency: explicit edit-action list, scope parameter table, pre-delivery verification, defined failure behavior (revert uncertain edits, state no remaining content). Deducted for: static review cannot execute; abnormal-input behavior rests only on rule text, capped at 10.

3Adaptability12 / 15 · 4.0/5

Clear scenarios (READMEs, release notes, work syncs, personal writing), declared non-fit boundaries (not an AI detector, no fact-checking), precise semantic triggers, Chinese-first and fully local with no overseas service dependency. Deducted for: boundaries conveyed via long prose rather than structured trigger conditions; English is secondary.

4Convention12 / 15 · 4.0/5

MIT license explicit, thorough CHANGELOG honestly recording failures and unreleased candidates, README install instructions, runtime-files. defining runtime boundary, maintenance path described. Deducted for: future-dated 2026 changelog entries are questionable; release gates partly rest on maintainer's unilateral judgment.

5Effectiveness6 / 15 · 2.0/5

Clear value claim with inline example showing directly usable output. Deducted for: static review cannot verify actual output quality; improvement evidence (5/7) is self-reported, capped at 7.

6Verifiability5 / 10 · 2.5/5

Repository provides detailed eval records, failure archives, criteria files and a CI workflow; negative results honestly recorded. Deducted for: all evidence is author-reported; key result files not present in the reviewed sources; cannot independently reproduce, capped at 5.

Evidence confidence:Low Reviewed Sep 18, 2026 Reviewed revision 5a9eafefe038
Before you use it
  • All eval results are self-reported; no independently executable verification is included in this review — spot-check before adopting.
  • CHANGELOG uses future 2026 dates; treat timeline with care.
  • Grok covered only 11/58 normal-text false-edit checks; full false-edit rate unknown.
  • Release gating partly depends on maintainer's unilateral decisions; second-model coverage is incomplete.
See the full review method →

What does this skill do, and when should you use it?

Shuorenhua (说人话) is a rewrite skill for Chinese text that removes templated AI phrasing, marketing packaging, engineer-posturing, translation-ese, and unsupported claims. Its core rule is to lock down facts before editing: metrics, versions, commands, paths, causal conditions, and attribution are always preserved; only excess flourish is removed. It works with Claude Code, Codex, Cursor, and ChatGPT, and ships scene packs (README, Release Notes, Issue replies) plus long-form scope controls. The repo includes a 120-case benchmark plus 20 scenario samples, with the latest release at v2.4.0.

After reading the input text, it applies minimal edits per SKILL.md rules: deletes pure greetings, empty teasers, and exact duplicates; simplifies nominalizations, bloated function words, and stiff syntax; removes unsupported credential claims. Facts, terminology, attribution, numbers, commands, and quotations stay intact throughout. It supports structural / bounded / in-place scopes, minimal / standard / aggressive intensities, and an annotation mode that only flags problems without rewriting. Pure prompt-based skill — no scripts or network needed.

  1. A developer publishing release notes who wants PR-style declarations removed while keeping concrete p95 latency figures
  2. A maintainer replying to an issue who wants empathy-padding and credential claims gone, leaving reproduction status and next steps
  3. A technical writer drafting a README who wants the first screen to explain the project without empty slogans
  4. An engineer de-translation-ese-ing a long AI-drafted document without altering conditions, negations, or intensity
  5. A user who wants problems flagged but no edits, using annotation mode

What are this skill's strengths and limitations?

Pros
  • Strict fidelity design: numbers, commands, attribution, conditions, and quotations are preserved by default, avoiding over-generalizations like "clearly optimized"
  • Backed by a 120-case benchmark with an L1 hard-constraint gate (fabricated facts and protected-span drift must be zero)
  • Multi-platform install paths and tiered scope control; pure prompt with zero dependencies
  • Explicitly distinguishes quoting a claim from endorsing it, so discussed wording is not deleted as boilerplate
Limitations
  • Chinese-first; English rules cover only common stock phrases and mixed-language redundancy
  • Effectiveness depends on how well each model follows the rules; cleanup rates vary by model (tracked separately in the repo)
  • Positions itself as rule-driven redundancy cleanup and does not mimic a specific author's personal voice
  • v2.4.0 evals cover two models; false-positive rates for other models lack public data

How do you install this skill?

Claude Code: run /plugin marketplace add MrGeDiao/shuorenhua, then /plugin install shuorenhua@shuorenhua. Codex: clone the repo and run codex exec -C . "Read ./SKILL.md and rewrite the following text per its rules: …". Agents supporting the skills protocol: npx skills add MrGeDiao/shuorenhua. A web version, the 说人话 GPT, is also available (requires ChatGPT Plus / Pro).

How do you use this skill?

After install, type something like "remove the AI tone from this passage" and paste your text. Optional parameters: annotation mode (flag only), scope (structural / bounded / in-place), intensity (minimal / standard / aggressive), and rewrite-safe (delete unsourced claims). Default output is one publish-ready rewritten draft, with no scores attached.

How does this skill compare with similar options?

The README lists related projects: stop-slop (English AI-redundancy rules and evaluation), humanizer (English AI-pattern taxonomy), and speak-human-tw (Traditional Chinese). For mainly English text those are better fits; for Simplified Chinese this skill is more complete.

FAQ

Can it bypass AI content detection?
No, and that is not the goal. The project focuses on cleaning templated phrasing, PR tone, and stiff syntax to improve readability and accuracy.
Will it alter key numbers or commands?
By design, no. Numbers, versions, commands, paths, interface names, and quotations are preserved verbatim; protected-span drift is an L1 hard constraint that must be zero in evals.
Is there a risk of breaking technical docs?
Stricter protection applies in docs, status, and code-context scenarios, locking commands, paths, versions, errors, and performance data; the author also collects sanitized bad cases to improve this.
Does it handle English?
Yes, both Chinese and English, but it is Chinese-first; English rules mainly target common stock phrases and structural redundancy in mixed Chinese-English text.

Related skills