Menu

#243 by GitHub stars

larashero3-dotcom/lieflat-less-ai-tone

三层去 AI 味：脚本检测出分级报告（A 机械改/B 建议改/C 只报告/X 已否决/F 指纹）+ 语义层判读（同义重命名/衔接连环/结论冒号/同构三连），先向用户交付专业、可读的改前报告，列出本篇指标、研究显著性、原文例句和具体改法；收到用户回复后按白名单规则改写，复测并生成前后对比报告（默认 Markdown，与文稿同格式）。规则基于两轮实测（629 篇对照 + 270 对同题同事实配对复测）整理。适用于写作完成后的成稿清理。

Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

fe13f1a0712c → 42ee3b60b281

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → fe13f1a0712c

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 42ee3b60b281a7fdab4ca4f920ff4dcef828a3ab

6.1kGitHub stars
1.5kstars in 7 days
1skill in this repository
13commits in 30 days

Heat

8.4
  • Star growth, last 7 daysAhead of 100% of tracked repositories
  • Star growth, last 24 hoursAhead of 100% of tracked repositories
  • Rank movement, last 7 daysAhead of 97% of tracked repositories
  • Commits, last 30 daysAhead of 80% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 16, 2026Nov 6, 20266,106

Individual skills in this repository

How it works

lieflat-less-ai-tone

When your agent uses it

三层去 AI 味：脚本检测出分级报告（A 机械改/B 建议改/C 只报告/X 已否决/F 指纹）+ 语义层判读（同义重命名/衔接连环/结论冒号/同构三连），先向用户交付专业、可读的改前报告，列出本篇指标、研究显著性、原文例句和具体改法；收到用户回复后按白名单规则改写，复测并生成前后对比报告（默认 Markdown，与文稿同格式）。规则基于两轮实测（629 篇对照 + 270 对同题同事实配对复测）整理。适用于写作完成后的成稿清理。

What it loads into context

Frontmatter

177 tokens

Always available to the agent

SKILL.md

8,347 tokens

When the skill is activated

Reference documents

35,029 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. 工作流（必须按顺序）
  2. 改写原则（解决「AI 改写不好」）
  3. 不改的情况
  4. 改写规则（按优先级排序）
  5. X 级清单（永不改，防误改）
  6. 只能人审的（skill 明确不碰）
  7. 最终验收

Scripts executed separately

  • scripts/check-structure.py
  • scripts/check-translationese.py
  • scripts/compare-human-ai.py
  • scripts/detect.py
  • scripts/report.py

Files

  • .gitignoreasset151 bytes
  • DETECT.mddoc6,947 bytes
  • LICENSEasset1,739 bytes
  • README.en.mddoc5,580 bytes
  • README.mddoc18,636 bytes
  • RESEARCH.en.mddoc25,333 bytes
  • RESEARCH.mddoc24,986 bytes
  • SKILL.mdcore27,856 bytes
  • SKILL.mdcore27,856 bytes
  • SKILL.mdcore27,856 bytes
  • SKILL.mdcore27,856 bytes
  • examples/agent-memory-case/00-原稿.mddoc9,552 bytes
  • examples/agent-memory-case/01-改前检测与修改建议.mddoc5,380 bytes
  • examples/agent-memory-case/02-改后全文.mddoc9,514 bytes
  • examples/agent-memory-case/03-左右对照.htmlasset53,131 bytes
  • examples/agent-memory-case/04-复测结论.mddoc1,777 bytes
  • examples/agent-memory-case/README.mddoc1,463 bytes
  • examples/agent-memory-case/数据-改前检测.jsonasset3,442 bytes
  • examples/agent-memory-case/数据-改后复测.jsonasset2,551 bytes
  • examples/agent-memory-case/数据-语义判读.jsonasset43,691 bytes
  • references/semantic-criteria.mddoc8,540 bytes
  • scripts/check-structure.pyruns4,350 bytes
  • scripts/check-translationese.pyruns4,810 bytes
  • scripts/compare-human-ai.pyruns6,529 bytes
  • scripts/detect.pyruns25,176 bytes
  • scripts/report.pyruns22,037 bytes

No excerpt is shown for this license. Read the source on GitHub.

View the complete source on GitHub

Skills included

  • lieflat-less-ai-tone

Repository facts

License
No license detected
Created
Aug 20, 2026
Last pushed
Nov 5, 2026
Forks
362
Open issues
3
Project activity
Active

Rank over the last 12 weeks

Now #243 · best #243 · up 151 in 30 days

  1. #281 from Oct 30 to Oct 31
  2. #280 on Nov 1
  3. #277 on Nov 2
  4. #276 from Nov 3 to Nov 4
  5. #270 on Nov 5
  6. #243 since Nov 6
68 earlier periods
  1. #906 on Aug 16
  2. #904 on Aug 20
  3. #914 on Aug 21
  4. #856 on Aug 22
  5. #908 on Aug 23
  6. #917 on Aug 24
  7. #920 on Aug 25
  8. #891 on Aug 26
  9. #888 on Aug 27
  10. #923 on Aug 28
  11. #832 on Aug 29
  12. #830 on Aug 30
  13. #868 on Aug 31
  14. #895 on Sep 1
  15. #864 on Sep 2
  16. #857 on Sep 3
  17. #813 on Sep 4
  18. #785 on Sep 5
  19. #811 on Sep 6
  20. #812 on Sep 7
  21. #825 on Sep 8
  22. #799 on Sep 9
  23. #808 on Sep 10
  24. #779 on Sep 11
  25. #770 on Sep 12
  26. #760 on Sep 13
  27. #787 on Sep 14
  28. #538 on Sep 15
  29. #489 on Sep 16
  30. #467 from Sep 17 to Sep 18
  31. #438 on Sep 19
  32. #448 on Sep 20
  33. #447 on Sep 21
  34. #449 on Sep 22
  35. #439 on Sep 23
  36. #426 from Sep 24 to Sep 25
  37. #420 on Sep 26
  38. #432 on Sep 27
  39. #433 on Sep 28
  40. #438 on Sep 29
  41. #429 on Sep 30
  42. #421 on Oct 1
  43. #420 on Oct 2
  44. #407 on Oct 3
  45. #403 on Oct 4
  46. #410 on Oct 5
  47. #407 on Oct 6
  48. #394 on Oct 7
  49. #393 on Oct 8
  50. #391 on Oct 9
  51. #378 on Oct 10
  52. #379 on Oct 11
  53. #384 on Oct 12
  54. #382 on Oct 13
  55. #383 on Oct 14
  56. #378 on Oct 15
  57. #381 on Oct 16
  58. #374 on Oct 17
  59. #361 on Oct 18
  60. #331 on Oct 19
  61. #314 on Oct 20
  62. #300 on Oct 21
  63. #296 on Oct 22
  64. #291 on Oct 23
  65. #290 on Oct 24
  66. #294 on Oct 25
  67. #281 on Oct 28
  68. #282 on Oct 29

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 5, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 3 notes
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 11 signals by file

LICENSE

  • Network accessline 1
    Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)
  • Network accessline 4
    This work is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by-nc/4.0/ or send a letter to
  • Network accessline 5
    International License. To view a copy of this license, visit http://creativecommons.org/licenses/by-nc/4.0/ or send a letter to Creative Commons, PO Box 1866, Mountain View, CA 94042, USA.
  • Network accessline 6
    http://creativecommons.org/licenses/by-nc/4.0/ or send a letter to

README.en.md

  • Network accessline 54
    **License** [CC BY-NC 4.0](./LICENSE)

README.md

  • Network accessline 210
    **许可** [CC BY-NC 4.0](./LICENSE)（署名-非商业性使用 4.0；商用授权联系作者）

scripts/check-structure.py

  • Executable scriptline 1
    Executable file

scripts/check-translationese.py

  • Executable scriptline 1
    Executable file

scripts/compare-human-ai.py

  • Executable scriptline 1
    Executable file

scripts/detect.py

  • Executable scriptline 1
    #!/usr/bin/env python3

scripts/report.py

  • Executable scriptline 1
    #!/usr/bin/env python3

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 7 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

mattpocock/skills

Skills for Real Engineers. Straight from my .agents directory.

316kGitHub stars

obra/superpowers

An agentic skills framework & software development methodology that works.

313.3kGitHub stars

NousResearch/hermes-agent

The agent that grows with you

261kGitHub stars

multica-ai/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions,…

230kGitHub stars

anthropics/skills

Public repository for Agent Skills

187.9kGitHub stars

DietrichGebert/ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

185.5kGitHub stars

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

larashero3-dotcom/lieflat-less-ai-tone: #243 on hotskills, 6.1k stars

[![larashero3-dotcom/lieflat-less-ai-tone on hotskills](https://hotskills.dev/badge/larashero3-dotcom-lieflat-less-ai-tone.svg)](https://hotskills.dev/skill/larashero3-dotcom-lieflat-less-ai-tone/)