admin-valentin/wewrite
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
110 commits 1 branch 0 tags 355 KiB
Commit graph

3 commits

Author SHA1 Message Date
wangzhuc
5fb20083af refactor: remove optimize_loop.py, replace with agent-driven optimization 
optimize_loop.py was framework-only (needed external LLM API). The
optimization is now an auxiliary function in SKILL.md driven by the
already-running agent. All references updated across README, CLAUDE.md,
diagnose.py, and writing-config.example.yaml.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-30 19:58:20 +08:00
wangzhuc
4fbbd185ca refactor: restructure writing-guide from action-based to detection-signal-based 
Reorganize anti-AI rules into 3 tiers mapped to detector signals:
- Tier 1 (Statistical): sentence variance, vocab temperature, paragraph
  rhythm, emotion polarity, adverb density, style drift
- Tier 2 (Linguistic): banned words, broken sentences, unexpected words,
  coherence breaking
- Tier 3 (Content): real data anchoring, specificity, density waves,
  dimension randomization

New rules added: emotion polarity distribution (1.4), adverb density
control (1.5), inter-paragraph style drift (1.6), unexpected word
usage (2.3). Each rule now references the detection signal it counters.

writing-config.example.yaml updated with corresponding new parameters.
SKILL.md Step 5 checklist aligned to new structure.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-30 18:48:44 +08:00
wangzhuc
0e91726526 writing-config: 框架开源，参数私有 
writing-config.yaml 加入 gitignore（用户自己跑 loop 优化，每人结果不同）。
提供 writing-config.example.yaml 作为起点。
optimization-results.tsv 也加入 gitignore。

这解决了开源对抗问题：框架公开，但检测方没有一个固定靶子可以反向训练，
因为每个用户优化出来的参数不同。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-28 23:26:58 +08:00