@oh-story/dsh 0.1.16 → 0.1.17
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +11 -11
- package/lib/client.js +26 -15
- package/lib/client.js.map +2 -2
- package/lib/drama/package.json +4 -0
- package/lib/index.js +42 -16
- package/lib/index.js.map +2 -2
- package/lib/novel-to-game/README.md +3 -3
- package/lib/novel-to-game/README_ZH.md +4 -4
- package/lib/novel-to-game/VERSION +1 -1
- package/lib/novel-to-game/manifest.json +25 -20
- package/lib/novel-to-game/package.json +4 -0
- package/lib/novel-to-game/skills/game-art-direction/references/art-direction-method.md +4 -0
- package/lib/novel-to-game/skills/game-build/SKILL.md +7 -1
- package/lib/novel-to-game/skills/game-build/references/baked-sprite-workflow.md +19 -0
- package/lib/novel-to-game/skills/game-concept/references/concept-method.md +4 -1
- package/lib/novel-to-game/skills/novel-to-game/SKILL.md +6 -3
- package/lib/novel-to-game/skills/novel-to-game/references/intake-method.md +1 -0
- package/lib/novel-to-game/skills/novel-to-game/references/pipeline-contract.md +13 -2
- package/lib/oh-story/manifest.json +417 -592
- package/lib/oh-story/package.json +4 -0
- package/lib/oh-story/roles/chapter-extractor.md +4 -3
- package/lib/oh-story/roles/character-designer.md +20 -85
- package/lib/oh-story/roles/consistency-checker.md +5 -5
- package/lib/oh-story/roles/narrative-writer.md +9 -9
- package/lib/oh-story/roles/story-architect.md +19 -26
- package/lib/oh-story/roles/story-explorer.md +4 -5
- package/lib/oh-story/roles/story-researcher.md +6 -7
- package/lib/oh-story/skills/browser-cdp/SKILL.md +26 -15
- package/lib/oh-story/skills/story/SKILL.md +94 -54
- package/lib/oh-story/skills/story/VERSION +1 -1
- package/lib/oh-story/skills/story-cover/SKILL.md +41 -220
- package/lib/oh-story/skills/story-cover/references/api-fallback.md +128 -0
- package/lib/oh-story/skills/story-cover/references/cover-styles.md +61 -95
- package/lib/oh-story/skills/story-deslop/SKILL.md +32 -27
- package/lib/oh-story/skills/story-deslop/references/agent-calls.md +4 -4
- package/lib/oh-story/skills/story-deslop/references/banned-words.md +7 -9
- package/lib/oh-story/skills/story-deslop/references/deslop-gates.md +12 -12
- package/lib/oh-story/skills/story-deslop/references/expression.md +10 -3
- package/lib/oh-story/skills/story-deslop/references/story-logic.md +1 -1
- package/lib/oh-story/skills/story-deslop/references/style-resolution.md +1 -1
- package/lib/oh-story/skills/story-import/SKILL.md +12 -11
- package/lib/oh-story/skills/story-import/references/benchmark-sync.md +50 -0
- package/lib/oh-story/skills/story-import/references/character-state-reverse.md +3 -4
- package/lib/oh-story/skills/story-import/references/deep-analysis.md +2 -3
- package/lib/oh-story/skills/story-import/references/import-report.md +5 -4
- package/lib/oh-story/skills/story-import/references/import-special-cases.md +6 -16
- package/lib/oh-story/skills/story-import/references/import-tracking.md +2 -2
- package/lib/oh-story/skills/story-import/references/length-routing.md +1 -43
- package/lib/oh-story/skills/story-import/references/outline-reverse-rules.md +8 -8
- package/lib/oh-story/skills/story-import/references/outline-reverse.md +2 -2
- package/lib/oh-story/skills/story-import/references/structure-mapping-long.md +113 -125
- package/lib/oh-story/skills/story-import/references/structure-mapping-short.md +77 -88
- package/lib/oh-story/skills/story-import/scripts/build_outline_brief.py +36 -59
- package/lib/oh-story/skills/story-import/scripts/check-outline-contract.js +5 -1
- package/lib/oh-story/skills/story-import/scripts/outline_view.py +286 -0
- package/lib/oh-story/skills/story-long-analyze/SKILL.md +38 -75
- package/lib/oh-story/skills/story-long-analyze/references/author-facing.md +21 -23
- package/lib/oh-story/skills/story-long-analyze/references/final-checks.md +8 -17
- package/lib/oh-story/skills/story-long-analyze/references/inspiration-library.md +18 -5
- package/lib/oh-story/skills/story-long-analyze/references/pipeline-ops.md +8 -14
- package/lib/oh-story/skills/story-long-analyze/references/stage1-golden-chapters.md +26 -27
- package/lib/oh-story/skills/story-long-analyze/references/stage2-extraction.md +74 -162
- package/lib/oh-story/skills/story-long-analyze/references/stage3-plot-rhythm.md +124 -309
- package/lib/oh-story/skills/story-long-analyze/references/stage4-characters-settings.md +49 -166
- package/lib/oh-story/skills/story-long-analyze/references/stage5-report.md +12 -15
- package/lib/oh-story/skills/story-long-analyze/references/style-profile-generator.md +110 -34
- package/lib/oh-story/skills/story-long-analyze/references/synthesis-inputs.md +12 -2
- package/lib/oh-story/skills/story-long-analyze/scripts/inspect_existing_assets.py +3 -1
- package/lib/oh-story/skills/story-long-analyze/scripts/manage_analysis_run.py +5 -1
- package/lib/oh-story/skills/story-long-scan/SKILL.md +49 -72
- package/lib/oh-story/skills/story-long-scan/references/genre-trends.md +47 -167
- package/lib/oh-story/skills/story-long-scan/references/platform-ciweimao.md +23 -8
- package/lib/oh-story/skills/story-long-scan/references/platform-fanqie.md +24 -22
- package/lib/oh-story/skills/story-long-scan/references/platform-jjwxc.md +25 -13
- package/lib/oh-story/skills/story-long-scan/references/platform-qidian.md +41 -27
- package/lib/oh-story/skills/story-long-scan/references/platform-qimao.md +24 -16
- package/lib/oh-story/skills/story-long-scan/references/topic-decision.md +31 -33
- package/lib/oh-story/skills/story-long-write/SKILL.md +5 -5
- package/lib/oh-story/skills/story-long-write/references/agent-calls.md +1 -1
- package/lib/oh-story/skills/story-long-write/references/artifact-protocols.md +51 -24
- package/lib/oh-story/skills/story-long-write/references/banned-words.md +7 -9
- package/lib/oh-story/skills/story-long-write/references/benchmark-recall.md +3 -3
- package/lib/oh-story/skills/story-long-write/references/character-basics.md +57 -95
- package/lib/oh-story/skills/story-long-write/references/character-relations.md +119 -269
- package/lib/oh-story/skills/story-long-write/references/cross-book-recall.md +2 -2
- package/lib/oh-story/skills/story-long-write/references/dialogue-mastery.md +8 -8
- package/lib/oh-story/skills/story-long-write/references/emotion-on-page.md +7 -7
- package/lib/oh-story/skills/story-long-write/references/emotional-arc-design.md +38 -298
- package/lib/oh-story/skills/story-long-write/references/emotional-methods.md +12 -53
- package/lib/oh-story/skills/story-long-write/references/female-audience-writing.md +39 -85
- package/lib/oh-story/skills/story-long-write/references/genre-readers.md +97 -163
- package/lib/oh-story/skills/story-long-write/references/long-chapter-hooks.md +39 -119
- package/lib/oh-story/skills/story-long-write/references/long-chapter-quality.md +39 -91
- package/lib/oh-story/skills/story-long-write/references/long-genre-catalog.md +81 -310
- package/lib/oh-story/skills/story-long-write/references/long-genre-mechanics.md +115 -326
- package/lib/oh-story/skills/story-long-write/references/long-reversal.md +1 -1
- package/lib/oh-story/skills/story-long-write/references/long-suspense.md +8 -8
- package/lib/oh-story/skills/story-long-write/references/opening-design.md +38 -334
- package/lib/oh-story/skills/story-long-write/references/outline-methods.md +128 -281
- package/lib/oh-story/skills/story-long-write/references/plot-core-methods.md +58 -499
- package/lib/oh-story/skills/story-long-write/references/project-files.md +10 -14
- package/lib/oh-story/skills/story-long-write/references/reference-index.md +29 -82
- package/lib/oh-story/skills/story-long-write/references/revision-diagnosis.md +31 -0
- package/lib/oh-story/skills/story-long-write/references/stop-and-fix.md +2 -2
- package/lib/oh-story/skills/story-long-write/references/style-combat-face.md +12 -19
- package/lib/oh-story/skills/story-long-write/references/style-genre-modules.md +3 -171
- package/lib/oh-story/skills/story-long-write/references/style-resolution.md +1 -1
- package/lib/oh-story/skills/story-long-write/references/workflow-chapter.md +8 -6
- package/lib/oh-story/skills/story-long-write/references/workflow-daily.md +2 -2
- package/lib/oh-story/skills/story-long-write/references/workflow-outline.md +47 -47
- package/lib/oh-story/skills/story-long-write/references/workflow-revision.md +7 -7
- package/lib/oh-story/skills/story-long-write/references/workflow-setup.md +4 -9
- package/lib/oh-story/skills/story-long-write/references/workflow-volume.md +72 -98
- package/lib/oh-story/skills/story-long-write/references/writing-craft.md +59 -115
- package/lib/oh-story/skills/story-long-write/scripts/build_architect_brief.py +38 -18
- package/lib/oh-story/skills/story-long-write/scripts/build_writer_prompt.py +23 -11
- package/lib/oh-story/skills/story-long-write/scripts/check-outline-contract.js +5 -1
- package/lib/oh-story/skills/story-long-write/scripts/outline_view.py +1 -1
- package/lib/oh-story/skills/story-review/SKILL.md +26 -24
- package/lib/oh-story/skills/story-review/references/agent-prompts.md +13 -9
- package/lib/oh-story/skills/story-review/references/banned-words.md +7 -9
- package/lib/oh-story/skills/story-review/references/expression.md +10 -3
- package/lib/oh-story/skills/story-review/references/quality-rubric.md +7 -7
- package/lib/oh-story/skills/story-review/references/review-tracking.md +2 -1
- package/lib/oh-story/skills/story-review/references/rubrics/fanqie.md +8 -9
- package/lib/oh-story/skills/story-review/references/rubrics/qidian.md +9 -11
- package/lib/oh-story/skills/story-review/references/rubrics/zhihu.md +9 -8
- package/lib/oh-story/skills/story-review/references/solo.md +6 -5
- package/lib/oh-story/skills/story-review/references/story-logic.md +1 -1
- package/lib/oh-story/skills/story-review/references/style-resolution.md +1 -1
- package/lib/oh-story/skills/story-setup/SKILL.md +24 -31
- package/lib/oh-story/skills/story-setup/references/agent-references/agent-reference-profiles.md +12 -13
- package/lib/oh-story/skills/story-setup/references/agent-references/banned-words.md +7 -9
- package/lib/oh-story/skills/story-setup/references/agent-references/benchmark-style-load.md +1 -1
- package/lib/oh-story/skills/story-setup/references/agent-references/character-basics.md +57 -95
- package/lib/oh-story/skills/story-setup/references/agent-references/character-relations.md +119 -269
- package/lib/oh-story/skills/story-setup/references/agent-references/deslop-gates.md +12 -12
- package/lib/oh-story/skills/story-setup/references/agent-references/dialogue-mastery.md +8 -8
- package/lib/oh-story/skills/story-setup/references/agent-references/emotion-on-page.md +7 -7
- package/lib/oh-story/skills/story-setup/references/agent-references/emotional-arc-design.md +38 -298
- package/lib/oh-story/skills/story-setup/references/agent-references/expression.md +10 -3
- package/lib/oh-story/skills/story-setup/references/agent-references/female-audience-writing.md +141 -0
- package/lib/oh-story/skills/story-setup/references/agent-references/genre-readers.md +96 -161
- package/lib/oh-story/skills/story-setup/references/agent-references/long-chapter-hooks.md +39 -119
- package/lib/oh-story/skills/story-setup/references/agent-references/long-emotional-methods.md +13 -54
- package/lib/oh-story/skills/story-setup/references/agent-references/long-genre-catalog.md +81 -310
- package/lib/oh-story/skills/story-setup/references/agent-references/long-genre-mechanics.md +115 -326
- package/lib/oh-story/skills/story-setup/references/agent-references/long-reversal.md +1 -1
- package/lib/oh-story/skills/story-setup/references/agent-references/long-suspense.md +8 -8
- package/lib/oh-story/skills/story-setup/references/agent-references/opening-design.md +38 -334
- package/lib/oh-story/skills/story-setup/references/agent-references/outline-methods.md +128 -281
- package/lib/oh-story/skills/story-setup/references/agent-references/plot-core-methods.md +58 -499
- package/lib/oh-story/skills/story-setup/references/agent-references/short-chapter-hooks.md +63 -171
- package/lib/oh-story/skills/story-setup/references/agent-references/short-emotional-methods.md +11 -63
- package/lib/oh-story/skills/story-setup/references/agent-references/short-genre-formulas.md +40 -50
- package/lib/oh-story/skills/story-setup/references/agent-references/short-reversal.md +14 -39
- package/lib/oh-story/skills/story-setup/references/agent-references/story-logic.md +1 -1
- package/lib/oh-story/skills/story-setup/references/agent-references/style-combat-face.md +12 -19
- package/lib/oh-story/skills/story-setup/references/agent-references/style-genre-modules.md +3 -171
- package/lib/oh-story/skills/story-setup/references/agent-references/style-resolution.md +1 -1
- package/lib/oh-story/skills/story-setup/references/agent-references/writing-craft.md +59 -115
- package/lib/oh-story/skills/story-short-analyze/SKILL.md +41 -90
- package/lib/oh-story/skills/story-short-analyze/references/analysis-characters.md +66 -0
- package/lib/oh-story/skills/story-short-analyze/references/analysis-short-genres.md +21 -20
- package/lib/oh-story/skills/story-short-analyze/references/analysis-short-hooks.md +4 -3
- package/lib/oh-story/skills/story-short-analyze/references/analysis-short-mechanics.md +4 -4
- package/lib/oh-story/skills/story-short-analyze/references/analysis-short-suspense.md +5 -5
- package/lib/oh-story/skills/story-short-analyze/references/analysis-submission.md +52 -0
- package/lib/oh-story/skills/story-short-analyze/references/optional-modules.md +23 -73
- package/lib/oh-story/skills/story-short-analyze/references/output-contract.md +25 -26
- package/lib/oh-story/skills/story-short-analyze/references/quality-checklist.md +20 -38
- package/lib/oh-story/skills/story-short-analyze/references/source-story-quality.md +9 -158
- package/lib/oh-story/skills/story-short-analyze/references/stage2-3-structure-emotion.md +39 -26
- package/lib/oh-story/skills/story-short-analyze/references/stage4-6-reversal-summary.md +42 -71
- package/lib/oh-story/skills/story-short-scan/SKILL.md +52 -62
- package/lib/oh-story/skills/story-short-scan/references/manual-rank-input.md +16 -12
- package/lib/oh-story/skills/story-short-scan/references/platform-dianzhong.md +10 -4
- package/lib/oh-story/skills/story-short-scan/references/platform-heiyan.md +15 -6
- package/lib/oh-story/skills/story-short-scan/references/real-market-data.md +34 -72
- package/lib/oh-story/skills/story-short-scan/references/topic-match.md +33 -13
- package/lib/oh-story/skills/story-short-write/SKILL.md +5 -5
- package/lib/oh-story/skills/story-short-write/references/agent-calls.md +3 -3
- package/lib/oh-story/skills/story-short-write/references/banned-words.md +7 -9
- package/lib/oh-story/skills/story-short-write/references/benchmark-recall.md +17 -22
- package/lib/oh-story/skills/story-short-write/references/cross-book-recall.md +22 -37
- package/lib/oh-story/skills/story-short-write/references/deslop-gates.md +12 -12
- package/lib/oh-story/skills/story-short-write/references/dialogue-mastery.md +8 -8
- package/lib/oh-story/skills/story-short-write/references/emotional-methods.md +11 -63
- package/lib/oh-story/skills/story-short-write/references/expression.md +10 -3
- package/lib/oh-story/skills/story-short-write/references/genre-styles//344/270/226/346/203/205/346/211/223/350/204/270.md +3 -3
- package/lib/oh-story/skills/story-short-write/references/genre-styles//345/217/214/347/224/267/344/270/273.md +6 -6
- package/lib/oh-story/skills/story-short-write/references/genre-styles//345/244/215/344/273/207/346/211/223/350/204/270.md +8 -8
- package/lib/oh-story/skills/story-short-write/references/genre-styles//345/256/205/346/226/227/345/256/253/346/226/227.md +4 -4
- package/lib/oh-story/skills/story-short-write/references/genre-styles//346/200/273/350/243/201/350/261/252/351/227/250.md +9 -9
- package/lib/oh-story/skills/story-short-write/references/genre-styles//346/202/254/347/226/221.md +10 -10
- package/lib/oh-story/skills/story-short-write/references/genre-styles//346/260/221/344/277/227/346/200/252/350/260/210.md +7 -7
- package/lib/oh-story/skills/story-short-write/references/genre-styles//346/262/231/351/233/225/350/204/221/346/264/236.md +6 -6
- package/lib/oh-story/skills/story-short-write/references/genre-styles//347/224/234/345/256/240.md +6 -6
- package/lib/oh-story/skills/story-short-write/references/genre-styles//350/277/275/345/246/273/347/201/253/350/221/254/345/234/272.md +12 -12
- package/lib/oh-story/skills/story-short-write/references/genre-writing-formulas.md +40 -50
- package/lib/oh-story/skills/story-short-write/references/hooks-chapter.md +63 -171
- package/lib/oh-story/skills/story-short-write/references/reference-index.md +13 -14
- package/lib/oh-story/skills/story-short-write/references/short-craft.md +10 -29
- package/lib/oh-story/skills/story-short-write/references/short-deslop.md +2 -2
- package/lib/oh-story/skills/story-short-write/references/short-format.md +12 -32
- package/lib/oh-story/skills/story-short-write/references/short-reversal.md +14 -39
- package/lib/oh-story/skills/story-short-write/references/story-logic.md +1 -1
- package/lib/oh-story/skills/story-short-write/references/style-resolution.md +1 -1
- package/lib/oh-story/skills/story-short-write/references/submission-craft.md +29 -19
- package/lib/oh-story/skills/story-short-write/references/villain-and-reveal.md +14 -19
- package/lib/oh-story/skills/story-short-write/references/workflow-design.md +67 -26
- package/lib/oh-story/skills/story-short-write/references/workflow-draft.md +10 -11
- package/lib/oh-story/skills/story-short-write/references/workflow-revision.md +50 -69
- package/lib/oh-story/skills/story-short-write/scripts/check-phase2-contract.js +21 -16
- package/lib/types/client/file-activity.d.ts +10 -0
- package/lib/types/client/file-activity.d.ts.map +1 -1
- package/lib/types/client/index.d.ts.map +1 -1
- package/lib/types/native-hooks.d.ts.map +1 -1
- package/lib/types/skill-provider.d.ts.map +1 -1
- package/lib/types/workspace-route.d.ts.map +1 -1
- package/lib/video-recap/package.json +4 -0
- package/package.json +23 -23
- package/lib/oh-story/skills/story-import/references/format-and-structure.md +0 -168
- package/lib/oh-story/skills/story-import/references/state-tracking.md +0 -45
- package/lib/oh-story/skills/story-import/references/tracking-transaction.md +0 -146
- package/lib/oh-story/skills/story-long-analyze/references/deconstruction-notes.md +0 -270
- package/lib/oh-story/skills/story-long-analyze/references/semantic-acceptance-fixtures.md +0 -84
- package/lib/oh-story/skills/story-long-analyze/references/style-profile-protocol.md +0 -133
- package/lib/oh-story/skills/story-long-scan/references/publishing-guide.md +0 -101
- package/lib/oh-story/skills/story-long-scan/references/reader-profiling.md +0 -92
- package/lib/oh-story/skills/story-long-write/references/character-design-methods.md +0 -428
- package/lib/oh-story/skills/story-long-write/references/commercial-core-methods.md +0 -503
- package/lib/oh-story/skills/story-long-write/references/deslop-gates.md +0 -34
- package/lib/oh-story/skills/story-long-write/references/expression.md +0 -76
- package/lib/oh-story/skills/story-long-write/references/narrative-focus.md +0 -63
- package/lib/oh-story/skills/story-long-write/references/outline-conflict.md +0 -457
- package/lib/oh-story/skills/story-long-write/references/outline-rhythm.md +0 -389
- package/lib/oh-story/skills/story-long-write/references/outline-structure-theory.md +0 -272
- package/lib/oh-story/skills/story-long-write/references/plot-emotion-system.md +0 -354
- package/lib/oh-story/skills/story-long-write/references/plot-frameworks.md +0 -710
- package/lib/oh-story/skills/story-long-write/references/plot-special-topics.md +0 -624
- package/lib/oh-story/skills/story-long-write/references/story-logic.md +0 -65
- package/lib/oh-story/skills/story-long-write/references/style-craft.md +0 -306
- package/lib/oh-story/skills/story-review/references/character-relations.md +0 -433
- package/lib/oh-story/skills/story-review/references/dialogue-mastery.md +0 -285
- package/lib/oh-story/skills/story-review/references/plot-core-methods.md +0 -522
- package/lib/oh-story/skills/story-review/references/review-quality.md +0 -243
- package/lib/oh-story/skills/story-setup/references/agent-references/character-design-methods.md +0 -428
- package/lib/oh-story/skills/story-setup/references/agent-references/outline-conflict.md +0 -457
- package/lib/oh-story/skills/story-setup/references/agent-references/outline-rhythm.md +0 -389
- package/lib/oh-story/skills/story-setup/references/agent-references/short-paragraph-hooks.md +0 -145
- package/lib/oh-story/skills/story-short-analyze/references/analysis-character-basics.md +0 -433
- package/lib/oh-story/skills/story-short-analyze/references/analysis-character-design.md +0 -426
- package/lib/oh-story/skills/story-short-analyze/references/analysis-character-relations.md +0 -384
- package/lib/oh-story/skills/story-short-analyze/references/analysis-paragraph-hooks.md +0 -144
- package/lib/oh-story/skills/story-short-analyze/references/analysis-reader-profile.md +0 -238
- package/lib/oh-story/skills/story-short-analyze/references/analysis-writing-techniques.md +0 -464
- package/lib/oh-story/skills/story-short-analyze/references/deconstruction-examples.md +0 -79
- package/lib/oh-story/skills/story-short-analyze/references/real-market-data.md +0 -89
- package/lib/oh-story/skills/story-short-analyze/references/zhihu-style.md +0 -54
- package/lib/oh-story/skills/story-short-write/references/hooks-paragraph.md +0 -145
- package/lib/oh-story/skills/story-short-write/references/output-contract.md +0 -116
- package/lib/oh-story/skills/story-short-write/references/short-prose-quality.md +0 -207
- package/lib/oh-story/skills/story-short-write/references/writing-workflow.md +0 -50
|
@@ -6,7 +6,7 @@ metadata: {"openclaw":{"source":"https://github.com/zenstory-ai/oh-story-claudec
|
|
|
6
6
|
---
|
|
7
7
|
# story-review:多视角对抗式审查
|
|
8
8
|
|
|
9
|
-
> Spawn 版本提示(不阻断 spawn):先读取项目根 `.story-deployed` 的 `agents_version`。与本版 `agents_version:
|
|
9
|
+
> Spawn 版本提示(不阻断 spawn):先读取项目根 `.story-deployed` 的 `agents_version`。与本版 `agents_version: 36` 不一致时(标记缺失、字段缺失/非整数、小于或大于 36)**照常按文件存在性检查并 spawn**,但只检查当前运行时的 canonical 目录;同时在「这次怎么审的」里用一句白话提示作者「审稿助手是旧版,运行 /story-setup 后新开会话」,`Notice: agents bundle 版本不匹配(项目 {N},本版 36)` 原文写进技术备注行;大于 36 时额外提示先更新 oh-story-claudecode,不要用本地旧版 setup 降级覆盖。版本提示本身不触发降级;文件缺失或异常、工具不可用、递归限制或调用失败按 Phase 0 处理,技术备注写 `Fallback: ... -> solo`。
|
|
10
10
|
|
|
11
11
|
你负责协调审查,找出小说的结构、角色、文字与设定问题,给出有原文依据的修改建议。
|
|
12
12
|
|
|
@@ -78,13 +78,9 @@ metadata: {"openclaw":{"source":"https://github.com/zenstory-ai/oh-story-claudec
|
|
|
78
78
|
|
|
79
79
|
| 用途 | 规范路径 |
|
|
80
80
|
|---|---|
|
|
81
|
-
| 通用质量清单 | `story-review/references/review-quality.md` |
|
|
82
81
|
| 通用内容评分 rubric | `story-review/references/quality-rubric.md` |
|
|
83
82
|
| 去 AI 味方法 | `story-review/references/expression.md` · `story-review/references/narrative-focus.md` · `story-review/references/story-logic.md` |
|
|
84
|
-
|
|
|
85
|
-
| 角色关系/好感度 | `story-review/references/character-relations.md` |
|
|
86
|
-
| 对话质量 | `story-review/references/dialogue-mastery.md` |
|
|
87
|
-
| 审查禁用词 | `story-review/references/banned-words.md` |
|
|
83
|
+
| 词句信号索引 | `story-review/references/banned-words.md` |
|
|
88
84
|
| 平台 rubric | `story-review/references/rubrics/{fanqie,qidian,zhihu}.md` |
|
|
89
85
|
| 标点预检脚本 | `story-review/scripts/normalize-punctuation.js` |
|
|
90
86
|
| AI句式预检脚本 | `story-review/scripts/check-ai-patterns.js` |
|
|
@@ -119,10 +115,10 @@ metadata: {"openclaw":{"source":"https://github.com/zenstory-ai/oh-story-claudec
|
|
|
119
115
|
- 故事:行动有什么来由、解决依据从何而来、前后改变了什么?安静场景可承载关系与认知变化,不强求冲突。
|
|
120
116
|
- 处理原则:有原文证据才输出 finding,指出阅读损失、最小建议与资料限制;只报告,不落改,不默认拆短、加动作或新增剧情。
|
|
121
117
|
|
|
122
|
-
平台 fallback
|
|
123
|
-
-
|
|
124
|
-
-
|
|
125
|
-
-
|
|
118
|
+
平台 fallback 摘要(叠加在通用 rubric 上):
|
|
119
|
+
- 番茄长篇:强开局、强冲突、高频爽点/情绪反馈、低理解门槛。
|
|
120
|
+
- 起点长篇:设定自洽、升级路径、长线期待、世界观承载力。
|
|
121
|
+
- 短篇:开头钩子、反转有铺垫、情绪兑现、信息差推进。
|
|
126
122
|
|
|
127
123
|
---
|
|
128
124
|
|
|
@@ -130,21 +126,28 @@ metadata: {"openclaw":{"source":"https://github.com/zenstory-ai/oh-story-claudec
|
|
|
130
126
|
|
|
131
127
|
1. **确定审查范围**:
|
|
132
128
|
- 用户指定了章节/文件 → 只审查指定内容。
|
|
133
|
-
- 用户未指定 →
|
|
129
|
+
- 用户未指定 → 项目是 git 仓库时审 `git diff --name-only` 里的正文/设定/大纲文件;否则长篇审 `正文/` 下最近修改的章,短篇审 `正文.md`。报告开头写明审了哪些。
|
|
134
130
|
2. **范围传递策略**:
|
|
135
131
|
- 优先把文件路径、章节名、行号范围传给 reviewer,不要把整本或大量章节完整复制进每个 prompt。
|
|
136
132
|
- 单文件或短片段可附 300-1200 字关键摘录。
|
|
137
133
|
- 多章/整卷/整本审查必须分批:按章节或文件组拆分,每批输出独立 findings,再综合;分批前先完整读 [references/batch-review.md](references/batch-review.md)(跨批状态、连续性、乱序提醒)。
|
|
138
|
-
3.
|
|
139
|
-
4.
|
|
140
|
-
-
|
|
141
|
-
-
|
|
142
|
-
-
|
|
143
|
-
-
|
|
144
|
-
|
|
145
|
-
|
|
146
|
-
|
|
147
|
-
|
|
134
|
+
3. **读取支撑材料**:solo 和分批审查时由你读正文、相关设定、角色档案、大纲、`追踪/上下文.md` 与伏笔文件;full/lean 只读定范围、定平台和分批开放项要用的文件,其余由 reviewer 按路径自己读。缺材料时在报告里标为证据不足。
|
|
135
|
+
4. **识别篇幅与目标平台,加载 rubric**:
|
|
136
|
+
- 通用 rubric 每次都加载:读 `story-review/references/quality-rubric.md`,不可读时用内置通用网文内容 rubric。平台表叠加在通用 rubric 上,不替代它。
|
|
137
|
+
- 篇幅:书目录下有 `正文/` 或 `设定/` 子目录的是长篇,有 `正文.md` 或 `设定.md` 文件的是短篇(与 `/story` 路由同一口径)。
|
|
138
|
+
- 平台:用户这次指定的优先;其次长篇读 `设定/题材定位.md`、短篇读 `设定.md` 的「目标平台」。`.active-book` 只用来定位书目录,不当平台来源。
|
|
139
|
+
- 按下表叠加平台表,文件不可读时用内置平台 fallback 摘要:
|
|
140
|
+
|
|
141
|
+
| 篇幅 | 目标平台 | 叠加的平台表 |
|
|
142
|
+
|---|---|---|
|
|
143
|
+
| 长篇 | 起点 | `story-review/references/rubrics/qidian.md` |
|
|
144
|
+
| 长篇 | 番茄 | `story-review/references/rubrics/fanqie.md` |
|
|
145
|
+
| 长篇 | 晋江、其他、未定、没写 | 不叠加 |
|
|
146
|
+
| 短篇 | 知乎盐言(也写作盐选)、番茄、七猫、黑岩、红果、小程序、未定、没写 | `story-review/references/rubrics/zhihu.md` |
|
|
147
|
+
|
|
148
|
+
- 短篇另按 `设定.md`「平台基调」核对格式、引号和导语。
|
|
149
|
+
- 技术备注行的 Rubric 写叠加的平台表(`fanqie | qidian | zhihu`),不叠加写 `generic`;括号里文件可读写 `file`,用了内置摘要写 `embedded`。
|
|
150
|
+
5. **形成审查基准包摘要**:把已加载的文件内容或内置 fallback 摘要压缩为 5-12 条审查标准,后续 solo 和子 Agent 都必须使用这份摘要。审查提示词要各保留一条剧情循环、高潮构建和关系进展的判断,审第 1-3 章时再加开头新鲜度。摘要必须保留一条句长标准:叙述默认是逗号长句,碎句和电报体与 AI 腔同级处理,不因「短」放行;本书文风另有约定时按文风。
|
|
148
151
|
6. **确定性预检(只报告,不修改)**:当审查范围包含本地正文文件路径时,运行本 skill 自带脚本:
|
|
149
152
|
```bash
|
|
150
153
|
node scripts/normalize-punctuation.js --check <正文文件...>
|
|
@@ -174,7 +177,7 @@ metadata: {"openclaw":{"source":"https://github.com/zenstory-ai/oh-story-claudec
|
|
|
174
177
|
fix: "可执行修改建议"
|
|
175
178
|
```
|
|
176
179
|
|
|
177
|
-
|
|
180
|
+
严重度定义:S1–S4 的级别与长篇写作、检测器相同;审稿报告的小节标题按级别写,S1、S2 归「必须改」,S3 归「建议改」,S4 归「可以不改」:
|
|
178
181
|
- **S1**:会破坏主线、角色动机、世界规则或读者信任,需优先修。
|
|
179
182
|
- **S2**:明显影响章节效果、留存、节奏、人物可信度,本轮要修。
|
|
180
183
|
- **S3**:局部质量问题,如措辞、轻微格式、局部节奏,可排期修。
|
|
@@ -202,7 +205,7 @@ metadata: {"openclaw":{"source":"https://github.com/zenstory-ai/oh-story-claudec
|
|
|
202
205
|
|
|
203
206
|
## 追踪文件维护
|
|
204
207
|
|
|
205
|
-
|
|
208
|
+
有 `追踪/_tracking-state.json` 的长篇工程且实际模式是 full/lean 时,收尾读 [references/review-tracking.md](references/review-tracking.md) 修订追踪;solo 不改 `追踪/`,按 solo.md 第 5 步写进报告。
|
|
206
209
|
|
|
207
210
|
## 流程衔接
|
|
208
211
|
|
|
@@ -213,4 +216,3 @@ metadata: {"openclaw":{"source":"https://github.com/zenstory-ai/oh-story-claudec
|
|
|
213
216
|
|---|---|---|
|
|
214
217
|
| 要修改查出的问题 | story-long-write / story-short-write | 返回对应写作 skill 修改 |
|
|
215
218
|
| 发现 AI 味需清理 | story-deslop | `/story-deslop` |
|
|
216
|
-
| 需要重新拆解对标书 | story-long-analyze / story-short-analyze | `/story-long-analyze` 或 `/story-short-analyze` |
|
|
@@ -2,7 +2,9 @@
|
|
|
2
2
|
|
|
3
3
|
只有实际模式仍是 full/lean 时才读本文件。
|
|
4
4
|
|
|
5
|
-
使用当前运行时的 Agent 工具并行调用(Codex 原生子代理使用 `agent_type`,Claude Code 使用 `subagent_type`,OpenCode 使用 `subagent` 工具的 `agent` 参数,Antigravity 使用 `invoke_subagent` + 同名 `TypeName`;实际字段以当前 CLI 暴露的工具为准)。每个 Agent 不继承父对话上下文,prompt 必须自包含项目路径、审查范围、文件路径、必要摘录和统一 Findings Schema。结构、角色、文字三个视角的 prompt 还要内联审查基准包摘要与 Rubric Source,使子 Agent
|
|
5
|
+
使用当前运行时的 Agent 工具并行调用(Codex 原生子代理使用 `agent_type`,Claude Code 使用 `subagent_type`,OpenCode 使用 `subagent` 工具的 `agent` 参数,Antigravity 使用 `invoke_subagent` + 同名 `TypeName`;实际字段以当前 CLI 暴露的工具为准)。每个 Agent 不继承父对话上下文,prompt 必须自包含项目路径、审查范围、文件路径、必要摘录和统一 Findings Schema。结构、角色、文字三个视角的 prompt 还要内联审查基准包摘要与 Rubric Source,使子 Agent 能直接开审;prompt 不写本 Skill 的资料路径,各 reviewer 按自己模板里的读取表加载方法资料。consistency-checker 按自己的检查项核对事实,不带内容评分基准包。所有 reviewer 只读:不改任何文件,只输出结果。
|
|
6
|
+
|
|
7
|
+
**追踪修订号**:长篇工程(有 `追踪/_tracking-state.json`)派 consistency-checker 前,先跑本 skill 的 `scripts/tracking_commit.py check --project {项目根}`,把输出的 `last_committed_chapter`、`state_revision` 填进它的 prompt;check 报错时这一栏写「check 失败,派生视图不可信:{报错首行}」,报告「没法判断的地方」用白话写明追踪记录和正文对不上、这次没据它核对。短篇不填。
|
|
6
8
|
|
|
7
9
|
**story-explorer 预查询(可选)**。仅当 `Effective Mode` 仍为 `full`/`lean`、当前允许 spawn 且当前运行时的 Agent 工具可用时,才可在对应 canonical agent 目录下确认 `story-explorer` 已部署并 spawn;Antigravity 检查 `.agents/agents/story-explorer/agent.md`,用 `invoke_subagent` + `TypeName: "story-explorer"`。`solo` 或子代理递归保护场景下不得 spawn,只能直接读取/检索。Prompt 示例:
|
|
8
10
|
|
|
@@ -34,11 +36,11 @@
|
|
|
34
36
|
4. 钩子和反转设计质量如何?
|
|
35
37
|
5. 范围控制:有无角色/设定膨胀?
|
|
36
38
|
6. 剧情循环是否存在且可重复?(参照审查基准包摘要里的剧情循环原则)
|
|
37
|
-
7.
|
|
39
|
+
7. 高潮是否有蓄能、落差与兑现?(参照审查基准包摘要里的高潮构建原则;假胜→崩解只是强反转的一种写法,不是必选)
|
|
38
40
|
8. 伏笔密度、连载期待和结构信息量是否合理?(伏笔密度通常只作为 S4 结构风险,除非已造成理解混乱)
|
|
39
|
-
9.
|
|
41
|
+
9. 按通用 rubric 和叠加的平台表逐项对照,标记 PASS/FAIL。
|
|
40
42
|
10. 继承的开放项里,本批本该兑现的钩子/伏笔是否落空?
|
|
41
|
-
11. 开头同质化(仅当本章是全书开篇/前 3 章):开局切口是不是同题材的默认套路(穿越即退婚、系统绑定、末世第一天、开场即打脸等),能不能原样换到任意同类书?"有钩子/非天气开场"
|
|
43
|
+
11. 开头同质化(仅当本章是全书开篇/前 3 章):开局切口是不是同题材的默认套路(穿越即退婚、系统绑定、末世第一天、开场即打脸等),能不能原样换到任意同类书?"有钩子/非天气开场"不等于不同质。按审查基准包摘要里的开头新鲜度判断——能整体换到同类书=同质化(撞题材模板至少 S2;套路化但有具体人物/处境微差 S3)。
|
|
42
44
|
12. 结尾总结:章尾的总结、升华或复述是否重复已有信息、削弱收束?先按本书叙述方式和原文功能复核,检测器命中也不自动判错;确认问题后按实际影响定级,与其他 reviewer 同处 findings 去重。
|
|
43
45
|
|
|
44
46
|
输出格式:
|
|
@@ -68,9 +70,9 @@
|
|
|
68
70
|
3. 人物弧线是否连贯?
|
|
69
71
|
4. 角色行为是否符合其动机?
|
|
70
72
|
5. 对话是否有潜台词和信息控制?
|
|
71
|
-
6. 爱情线好感度与 CP
|
|
73
|
+
6. 爱情线好感度与 CP 行为是否匹配?(参照审查基准包摘要里的关系进展原则)
|
|
72
74
|
7. 好感度进度是否可感知?
|
|
73
|
-
8.
|
|
75
|
+
8. 检查三类对话问题:① 机械对话/问答式/句间无情绪承接;② 角色当「科普嘴」整段讲设定原理(空转解释同样管台词);③ 说话不分场合(高压或生死场面里的玩笑、口头梗、插科打诨出戏)。命中按 S2/S3 报具体引用+改法。
|
|
74
76
|
|
|
75
77
|
输出格式:
|
|
76
78
|
VERDICT: APPROVE / CONCERNS / REJECT
|
|
@@ -92,9 +94,9 @@
|
|
|
92
94
|
style_resolution:{本次生效要求及来源、被覆盖的默认条款、事实边界;文字风格判断共用}
|
|
93
95
|
审查基准包摘要:{Phase 1 形成的 rubric / fallback 摘要,必须内联}
|
|
94
96
|
Rubric Source: file | embedded fallback
|
|
95
|
-
|
|
97
|
+
去味判据:按你模板里的读取表完整读 expression、narrative-focus、story-logic 及 banned-words、deslop-gates,三层都审;方法里的改写动作仅用作建议,不落改
|
|
96
98
|
检查项:
|
|
97
|
-
1.
|
|
99
|
+
1. 词句信号(套话、陈词滥调、“像/好像/仿佛/如同”式比喻成片堆叠)是否造成阅读损失?命中词本身不算错。
|
|
98
100
|
2. 表达是否机械、视角是否越过本书信息边界,章末是否只剩重复总结?
|
|
99
101
|
3. 格式是否合规(按戏剧单元/镜头自然断段、无机械字数切分、无空行、对话独立成行、主语节奏自然)?
|
|
100
102
|
4. 标点节奏是否匹配语气/人物声线:是否通篇句号化、随机堆砌问号/感叹号,或残留 `……`/`——` 硬造停顿?本书已明确授权且有功能的停顿不因符号本身判错。
|
|
@@ -121,6 +123,8 @@
|
|
|
121
123
|
项目路径:{项目根}
|
|
122
124
|
审查范围:{文件路径/章节/必要摘录}
|
|
123
125
|
已知角色:{从设定文件提取角色列表}
|
|
126
|
+
last_committed_chapter:{check 输出;短篇写「无追踪」}
|
|
127
|
+
state_revision:{check 输出;check 失败写「check 失败,派生视图不可信:{报错首行}」}
|
|
124
128
|
继承的开放项(分批审查必填,无则写「无」):{从 追踪/伏笔.md 提取的、预计回收章 ≤ 本批末章的已埋未回收伏笔,连同上一批未解决 findings 摘要}
|
|
125
129
|
检查项:
|
|
126
130
|
1. 角色属性是否前后一致?
|
|
@@ -153,7 +157,7 @@
|
|
|
153
157
|
<!-- author-report -->
|
|
154
158
|
```md
|
|
155
159
|
=== 《{书名}》{审查范围}审查 ===
|
|
156
|
-
这次怎么审的:{结构、人物、文字、设定一致性四个视角分头看 | 精简审:结构和设定一致性两个视角}
|
|
160
|
+
这次怎么审的:{结构、人物、文字、设定一致性四个视角分头看 | 精简审:结构和设定一致性两个视角},按通用网文标准{,加上番茄长篇 | 起点长篇 | 短篇平台的要求}。
|
|
157
161
|
|
|
158
162
|
总体判断:{可以发 | 改完下面几处再发 | 这一章需要重写}——{一句话理由,用读者感受说}
|
|
159
163
|
|
|
@@ -1,8 +1,6 @@
|
|
|
1
1
|
# AI 味词句信号索引
|
|
2
2
|
|
|
3
|
-
>
|
|
4
|
-
|
|
5
|
-
<!-- 共享副本由 scripts/shared-references.json 管理,改动后同步并跑 scripts/check-shared-files.sh -->
|
|
3
|
+
> 这里列的是需回到上下文判断的信号,不是出现即错的禁词。表达服从 [style-resolution.md](style-resolution.md);不据词频判断作者身份,不以清零为目标。具体修法由调用方加载的方法文件承担。
|
|
6
4
|
|
|
7
5
|
## 句式与组织信号
|
|
8
6
|
|
|
@@ -36,11 +34,11 @@
|
|
|
36
34
|
|
|
37
35
|
“她感到”“意识到”“知道”“原来”可以准确表达感受、判断和发现;“仿佛/好像/似乎”可以限定视角置信度;“坚定/冰冷/深邃”可以是准确描述。“突然/瞬间/猛地”也可能承担真实突发或时间压缩。只凭这些词不能认定告知式心理、模板比喻或偷懒。
|
|
38
36
|
|
|
39
|
-
##
|
|
37
|
+
## 复合样本
|
|
40
38
|
|
|
41
|
-
|
|
39
|
+
例句展示组合风险,不是合格与不合格的标准答案;判断及改法仍按三层方法,不能照例句新增动作、改变人物态度或一律拆短。
|
|
42
40
|
|
|
43
|
-
| 观察对象 |
|
|
41
|
+
| 观察对象 | 例句或模板 | 回到语境核对 |
|
|
44
42
|
|---|---|---|
|
|
45
43
|
| 否定、状语与声线 | “他不是冷漠,而是绝望”“他笑了一下,带着一丝不易察觉的嘲讽”“他说,带着一丝无奈”“她声音不大,却带着不容置疑的力量”“好的,他说道” | 对比是否有纠错对象,状语与标签是否机械复现;普通“说”不用替换成动作 |
|
|
46
44
|
| 跨段铺排与预告 | “不是嚎啕大哭。/也不是扯着嗓子喊不舍。/只是一个人走远了……”“他不知道的是,更大的风暴即将来临”“命运终于露出獠牙;属于他的反击才刚刚开始”“早已布好的棋局” | 是否反复铺垫同一意思、空泛宣告或越过揭露边界;排除猜测与题材承诺另判 |
|
|
@@ -54,10 +52,10 @@
|
|
|
54
52
|
| 温和请求、完整解释与笼统反应 | “我觉得你这样做不太合适,能不能考虑一下我的感受?”“其实我这样做是有原因的,因为当时的情况非常复杂……”“所有人都震惊了,不敢相信自己的耳朵。”“她很害怕,不知道该怎么办,只能等着事情过去。” | 是否所有人都用同一套说法,关键交锋或选择是否被概括;不能把请求改辱骂、解释改挑衅,或凭空补锁门、录音与群体动作 |
|
|
55
53
|
| 比喻的功能边界 | “像一头被抛弃的野狗”“像一把刀”“脸色惨白得像这漫天的雪”“力道大得像是要把骨头捏碎” | 生活化、物品、环境与身体感知比喻均可能有效;看是否传递角色特有信息,不按类别全删 |
|
|
56
54
|
| 二修伪自然 | “手里拿着刀,他冲了上去”;连续“伸手拿起、取过、挑开、放下、转身”;强加口误、脏话、每句换行或对话占比 | 一次伴随动作前置不等于油腻;检查是否机械套用另一种句法、流程或格式 |
|
|
57
|
-
|
|
|
55
|
+
| 替换的误改风险 | “美丽动人的笑容”“白色的药片”“手里那截链子”“飞驰的汽车”“他因为害怕而……”;垂下眼、目光微沉、攥拳 | 修饰、指示与原因可能承担区分、承接或动作条件;不能仅为去词删成信息残缺,也不能把每个情绪词换成同一微动作 |
|
|
58
56
|
|
|
59
|
-
##
|
|
57
|
+
## 使用边界
|
|
60
58
|
|
|
61
|
-
|
|
59
|
+
脚本提示只供定位,不能替代语义结论。是否构成问题、如何修复及获准保留,由本次方法与文风裁决确定。
|
|
62
60
|
|
|
63
61
|
标点、句长、段落疏密和对话占比均不在此设置统一指标。不通过同义词轮换、错误用字、英文点省略号或机械补动作规避提示。
|
|
@@ -57,19 +57,26 @@
|
|
|
57
57
|
|
|
58
58
|
| 已知事实与原句 | 可采用的表达 | 看似去味却改坏了 |
|
|
59
59
|
|---|---|---|
|
|
60
|
-
| 钥匙忘在家里,明天归还;无人指责她拒还。“她不是不肯还钥匙,而是忘在家里了。‘我明天带来。’她说。” |
|
|
60
|
+
| 钥匙忘在家里,明天归还;无人指责她拒还。“她不是不肯还钥匙,而是忘在家里了。‘我明天带来。’她说。” | “她把钥匙忘在家里了。‘我明天带来。’她说。”删无用靶子;若在回应拒还指责,保留纠错功能,原句保留按 [style-resolution.md](style-resolution.md) 登记白名单 | “‘爱等就等。’她说。”改变承诺与态度 |
|
|
61
61
|
| 她进了没开灯的屋子,摸到桌边拿药盒。“她推门。屋里没开灯。她摸到桌边。把药盒拿起来。” | “进屋后,她摸黑走到桌边,拿起药盒。”将光线嵌入行动;紧张镜头若原断句有效也可留 | “她摸黑吞了两片药。”从取药改成服药,新增数量与后果 |
|
|
62
62
|
|
|
63
63
|
## 脚本提示怎样进入语义判断
|
|
64
64
|
|
|
65
|
-
检测器是定位工具。密度提示不是词频配额,advisory 不作完成门槛。表达有功能不等于 blocking
|
|
65
|
+
检测器是定位工具。密度提示不是词频配额,advisory 不作完成门槛。表达有功能不等于 blocking 可以不改:作者已明确选择的原句按白名单保留;其余保留叙事功能自然改写,由调用方复扫,不能以保留说明代替验收。指定原句不能改又不在白名单时报告剩余阻塞。不靠错字或拆句躲检测;确定性的事实、字数、截断与占位问题仍交调用方验收,不能靠文风豁免。
|
|
66
|
+
|
|
67
|
+
下表索引检测器全部提示类别,加粗的是 blocking。
|
|
66
68
|
|
|
67
69
|
| 提示 | 人工判断对象 |
|
|
68
70
|
|---|---|
|
|
71
|
+
| **`not-is-comparison`**、**`reverse-not-is`**、**`negation-parade`**、`negation-pair-tic` | 见上文「否定铺垫后肯定翻转」 |
|
|
72
|
+
| **`voice-contrast`** | 见上文「万能状语与套式声线」 |
|
|
73
|
+
| **`em-dash`** | 按功能改成动作、停顿或完整句,不只换符号 |
|
|
74
|
+
| **`trailer-ending`**、**`trailer-summary`** | 章末预告与状态总结,见上文「解释与叙述者」;收尾分量转 narrative-focus |
|
|
69
75
|
| `formulaic-parallelism`、`quote-emphasis-tic` | 对比与强调是否有真实意义,是否机械复述 |
|
|
70
76
|
| `cliche-density-tic`、`metaphor-density-tic` | 套词与比喻是否聚成同一腔调,功能是否重复 |
|
|
71
77
|
| `stock-reaction-tic`、`micro-action-tic`、`action-list-tic` | 反应与动作是否只是标注或清单;用笔分配转 narrative-focus |
|
|
72
|
-
| `overcompressed-prose-tic`、`low-connective-density-tic` | 是否真缺连接、对象和连续思路,不按计数拉长 |
|
|
78
|
+
| `period-stutter`、`overcompressed-prose-tic`、`low-connective-density-tic` | 是否真缺连接、对象和连续思路,不按计数拉长 |
|
|
79
|
+
| `long-paragraph` | 一段是否跨了几个镜头,按镜头断开 |
|
|
73
80
|
| `abstract-summary-tic`、`reasoning-chain-tic` | 总结是否重复,解释是否必要;因果缺口转 story-logic |
|
|
74
81
|
| `system-notice-formality-tic` | 语域是否合乎载体,角色能否理解其当下作用 |
|
|
75
82
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# 通用网文内容审查 Rubric
|
|
2
2
|
|
|
3
|
-
>
|
|
3
|
+
> 每次审查都用本表评估故事文本质量,再叠加平台表;表达默认值先按 `style-resolution.md` 与本书文风裁决。
|
|
4
4
|
|
|
5
5
|
## 评分方法
|
|
6
6
|
|
|
@@ -24,7 +24,7 @@
|
|
|
24
24
|
| 对话质量 | 对话有潜台词、信息控制和角色差异 | 有信息堆叠或声音略同质 | 对话像说明书,人人同腔 |
|
|
25
25
|
| 设定一致性 | 不违背既有规则、时间线和角色属性 | 有轻微模糊点需补证据 | 与已写设定或前文事实冲突 |
|
|
26
26
|
| 文字自然度 | 具体、可感、动作承载信息 | 偶有套话或抽象总结 | AI 腔、陈词滥调、总结体明显 |
|
|
27
|
-
| 句长节奏 |
|
|
27
|
+
| 句长节奏 | 叙述默认是逗号长句,短句只作偶尔的孤立重拍、用完回到逗号长句;本书文风另有约定时按文风 | 局部碎句或电报体,或偶发机械长短交替 | 逗号之间连着都是几个字的碎块、通篇读着像提纲,或审改把逗号长句拆碎 |
|
|
28
28
|
| 标点节奏 | 标点跟语气、人物声线和情绪功能匹配 | 局部标点单调或略有堆砌 | 通篇句号化、随机堆砌问号/感叹号,或用 `……`/`——` 硬造停顿 |
|
|
29
29
|
| 具体字数表达校验 | 「这五个字」「短短四字」类表达的字数经核对属实,且有叙事必要 | 字数属实但换成「那几个字」更自然 | 字数与实际不符,或无法确认统计口径 |
|
|
30
30
|
| 格式可读性 | 段落按戏剧单元/镜头自然断开,对话独立,无多余空行,主语节奏自然 | 局部段落偏长/偏碎或主语重复略多 | 大段堆叠、机械切段、对话/叙述难读、主语过密 |
|
|
@@ -41,11 +41,11 @@
|
|
|
41
41
|
|
|
42
42
|
## 发布建议门槛
|
|
43
43
|
|
|
44
|
-
| 综合情况 | Verdict |
|
|
45
|
-
|
|
46
|
-
| 无 S1/S2,S3 可快速处理 | APPROVE |
|
|
47
|
-
| 有 S2,或 S3 数量多影响阅读 | CONCERNS |
|
|
48
|
-
| 有 S1,或核心卖点/动机/规则崩坏 | REJECT |
|
|
44
|
+
| 综合情况 | Verdict | 报告「总体判断」 |
|
|
45
|
+
|---|---|---|
|
|
46
|
+
| 无 S1/S2,S3 可快速处理 | APPROVE | 可以发 |
|
|
47
|
+
| 有 S2,或 S3 数量多影响阅读 | CONCERNS | 改完下面几处再发 |
|
|
48
|
+
| 有 S1,或核心卖点/动机/规则崩坏 | REJECT | 局部能改好写「改完下面几处再发」,卖点、动机或规则整体崩坏写「这一章需要重写」 |
|
|
49
49
|
|
|
50
50
|
## 输出要求
|
|
51
51
|
|
|
@@ -1,10 +1,11 @@
|
|
|
1
1
|
# story-review:审查收尾的追踪文件维护
|
|
2
2
|
|
|
3
|
-
追踪维护通过本 skill 的 `scripts/tracking_commit.py`
|
|
3
|
+
追踪维护通过本 skill 的 `scripts/tracking_commit.py` 提交事务;[tracking-transaction.md](tracking-transaction.md) 只在报错或字段拿不准时读。**full / lean 模式只允许通过该工具修改 `追踪/`;solo 模式不修改任何 `追踪/` 文件。**不得直接 Edit/Write/追加 `伏笔.md`、角色快照、时间线视图、摘要或 `上下文.md`。
|
|
4
4
|
|
|
5
5
|
1. **先检查状态**:执行 `tracking_commit.py check --project {项目根}`,确认 `_tracking-state.json` 与全部派生视图一致。失败时按 tracking-transaction.md 的错误类型处理;提交后派生视图不一致,用新的同章 revision 事务重建,不重跑已清理的旧输入,也不手改 Markdown。
|
|
6
6
|
2. **判定是否需要修订**:只有正文证据表明现有追踪事实错误或缺失时才维护。过期伏笔、漏登记开放钩子、角色当前状态、客观时间线、读者认知都归入其证据所在章的 `mode=revision` 事务。审查意见与未来写作建议不进事实追踪。
|
|
7
7
|
3. **构造完整同章事务**:先跑 `tracking_commit.py draft --project {项目根} --chapter {N}`,草稿已按该章现有记录预填;保留该章原记录中仍成立的内容,只修改有正文证据的变化;核心角色变化同时提交截至当前最后已写章的完整 `character_snapshots`。伏笔对同一 ID `upsert` 当前状态,不增加重复行;时间线同时提交客观事实、读者当前认知和实际揭示状态。
|
|
8
8
|
4. **提交并复检**:执行 `tracking_commit.py commit --project {项目根} --input {事务文件}`,再执行 `tracking_commit.py check --project {项目根}`。确认逐章记录规范且未超限、`上下文.md` 恰好固定 7 栏且 ≤12288 字节、作者/读者时间线及全部派生视图与 state 一致。
|
|
9
|
+
5. **正文改过时的出口**:commit 报「第N章正文已改」「字数目标已改」并要求改用 story-long-write 时,不重试、不改字数记录,因为本 skill 没有重新计数工具。把这章要修的追踪事实写进报告「需要你决定」,请作者在 `/story-long-write` 说「修改第N章」,并告诉它正文已经改过、要重新提交追踪。
|
|
9
10
|
|
|
10
11
|
例如审查 demo 第 10 章时,若正文明确显示周薄森说专业重拍版“缺了灵魂”、张耀祖拍板继续用江晨手机原版,修订事务可以把该结果写进客观事实和读者已知;钟嘉嘉“只猜对了一半”背后的培养安排如果正文尚未揭示,只能留在作者真相,不能写入读者视图。
|
|
@@ -1,19 +1,18 @@
|
|
|
1
|
-
#
|
|
1
|
+
# 番茄长篇 Quality Rubric
|
|
2
2
|
|
|
3
3
|
## 评分标准
|
|
4
4
|
|
|
5
|
-
|
|
5
|
+
叠加在通用 rubric 上,只用于番茄长篇。下列数字是快节奏、强情绪写法的参考,不代表平台算法;先对照本书题材与已定节奏。
|
|
6
6
|
|
|
7
7
|
| 指标 | PASS 标准 | FAIL 标准 |
|
|
8
8
|
|------|----------|----------|
|
|
9
|
-
| 开头吸引力 | 前 3
|
|
10
|
-
| 读者留存 | 每章结尾有"翻页动力"(悬念/反转/新信息) |
|
|
11
|
-
| 题材匹配 | 内容符合标签类型(如甜宠/逆袭/重生) |
|
|
9
|
+
| 开头吸引力 | 前 3 段包含冲突/悬念/钩子,前 3 章节奏不拖 | 前 3 段纯描写/背景介绍,或前 3 章连续拖沓;完读率须用实际数据验证 |
|
|
10
|
+
| 读者留存 | 每章结尾有"翻页动力"(悬念/反转/新信息) | 连续几章结尾都没有翻页动力 |
|
|
11
|
+
| 题材匹配 | 内容符合标签类型(如甜宠/逆袭/重生) | 长时间偏离标签类型 |
|
|
12
12
|
| 阅读节奏 | 段落便于手机阅读,节奏和信息量支撑核心卖点 | 机械切段或拖沓,信息不足以支撑阅读期待 |
|
|
13
|
-
| 情绪节点 |
|
|
14
|
-
| 完读风险 | 前 3 章 Hook 有效,节奏不拖 | 前 3 章无 Hook 或连续拖沓;完读率须用实际数据验证 |
|
|
13
|
+
| 情绪节点 | 情绪起伏密,读者隔不久就有反馈(参考:约每千字一次) | 大段情绪平直,读者等不到反馈 |
|
|
15
14
|
|
|
16
15
|
## 使用方式
|
|
17
16
|
|
|
18
|
-
-
|
|
19
|
-
-
|
|
17
|
+
- 审查开局、节奏与情绪交付时对照本表。
|
|
18
|
+
- 本表只作参考项,不单独定为必须改;具体判断须有原文证据。
|
|
@@ -1,20 +1,18 @@
|
|
|
1
|
-
#
|
|
1
|
+
# 起点长篇 Quality Rubric
|
|
2
2
|
|
|
3
3
|
## 评分标准
|
|
4
4
|
|
|
5
|
-
|
|
5
|
+
叠加在通用 rubric 上,只用于起点长篇。成长与金手指项用于对应题材;没有等级或金手指的作品不据此判缺失。数字是参考,按本书节奏选用。
|
|
6
6
|
|
|
7
7
|
| 指标 | PASS 标准 | FAIL 标准 |
|
|
8
8
|
|------|----------|----------|
|
|
9
|
-
| 爽点密度 |
|
|
10
|
-
| 升级节奏 |
|
|
11
|
-
| 金手指使用 |
|
|
12
|
-
|
|
|
13
|
-
|
|
|
14
|
-
| 角色存在感 | 主角每章出场并推进 | 连续 2 章主角不出场或无推进 |
|
|
15
|
-
| 追读风险 | 章尾钩子与情绪连续性支撑后续期待 | 连续 3 章无钩子或情绪断裂;追读比须用实际数据验证 |
|
|
9
|
+
| 爽点密度 | 情绪节点(升级/打脸/获宝)间隔与本书节奏相符(参考:约每 3000 字一次) | 长段落没有情绪节点,读者等不到兑现 |
|
|
10
|
+
| 升级节奏 | 实力突破的间隔与本书成长线一致 | 长期没有任何成长或突破 |
|
|
11
|
+
| 金手指使用 | 金手指在推进中起作用,出场有理由 | 长期搁置到读者忘了它,或每章硬提一句 |
|
|
12
|
+
| 追读钩子 | 章尾有悬念或钩子,情绪连续支撑后续期待 | 连续几章结尾无钩子或情绪断裂;追读比须用实际数据验证 |
|
|
13
|
+
| 角色存在感 | 主角每章出场并推进 | 连续多章主角不出场或无推进 |
|
|
16
14
|
|
|
17
15
|
## 使用方式
|
|
18
16
|
|
|
19
|
-
-
|
|
20
|
-
-
|
|
17
|
+
- 审查成长线、金手指和连载期待时对照本表。
|
|
18
|
+
- 本表只作参考项,不单独定为必须改;作者可按本书目标调整。
|
|
@@ -1,19 +1,20 @@
|
|
|
1
|
-
#
|
|
1
|
+
# 短篇 Quality Rubric
|
|
2
2
|
|
|
3
3
|
## 评分标准
|
|
4
4
|
|
|
5
|
+
叠加在通用 rubric 上,用于所有短篇(知乎盐言、番茄、七猫、黑岩、红果、小程序及未定平台)。各平台的格式、引号和导语要求以 `设定.md`「平台基调」为准。
|
|
6
|
+
|
|
5
7
|
| 指标 | PASS 标准 | FAIL 标准 |
|
|
6
8
|
|------|----------|----------|
|
|
7
9
|
| 第一人称 | 采用「我」视角时,所知信息与叙述姿态一致 | 已定第一人称却无依据换视角;明确采用其他视角不据此判错 |
|
|
8
|
-
| 情绪拉扯 | 关键场景有期待→失望→惊喜等情绪变化,承接段服务于变化 |
|
|
9
|
-
| 反转设计 |
|
|
10
|
+
| 情绪拉扯 | 关键场景有期待→失望→惊喜等情绪变化,承接段服务于变化 | 连续几段重复同一情绪且无新信息或行动 |
|
|
11
|
+
| 反转设计 | 有反转的篇目,反转前文有伏笔 | 反转无伏笔支撑;本篇设计为无反转的,看报应或关系兑现是否落地 |
|
|
10
12
|
| 结尾余韵 | 兑现本篇情绪目标,收口有具体后果或情感余韵 | 只有空泛总结,或承诺的情绪没有落点 |
|
|
11
|
-
| 格式合规 |
|
|
12
|
-
| 开头钩子 |
|
|
13
|
+
| 格式合规 | 段落以短为主(有长短/疏密变化)、无空行、对话格式符合平台基调 | 通篇同长度或连续超长段落/空行/对话标签 |
|
|
14
|
+
| 开头钩子 | 第一句用动作、冲突或悬念建立阅读理由 | 第一句纯描写/背景;跳失率须用实际数据验证 |
|
|
13
15
|
| 字数控制 | 全文在本次锁定的字数范围内,并符合已核实的投稿要求 | 超出或不足,且作者未变更范围 |
|
|
14
|
-
| 开头跳失风险 | 第一句用动作、冲突或悬念建立阅读理由 | 纯描写/背景未建立阅读理由;跳失率须用实际数据验证 |
|
|
15
16
|
|
|
16
17
|
## 使用方式
|
|
17
18
|
|
|
18
|
-
-
|
|
19
|
-
-
|
|
19
|
+
- 审查钩子、反转和情绪交付时对照本表。
|
|
20
|
+
- 本表只作参考项,不单独定为必须改;叙述视角与收口按本篇已定文风检查。
|
|
@@ -1,20 +1,21 @@
|
|
|
1
1
|
# story-review:solo 模式
|
|
2
2
|
|
|
3
|
-
当前会话直接审查,不 spawn Agent。先按 Phase 1 第 4
|
|
3
|
+
当前会话直接审查,不 spawn Agent。先按 Phase 1 第 4 步加载通用 rubric 并叠加平台表;文件不可读用内置基准包。
|
|
4
4
|
|
|
5
5
|
逐项完成基础检查:
|
|
6
6
|
1. 格式合规性检查:按戏剧单元/画面分段而非机械按字数切分(偶发稍长的完整推理、氛围或情绪链不算违规,通篇同阈值切段或碎成提纲才算);段首建立主语、段中用代词或省略,连续无必要重复同一角色名才算主语过密;无段间空行;对话独立成行;正文评价台词、题字等所用的具体字数,须确认统计正确且有叙事必要。
|
|
7
7
|
2. 简单的设定一致性 grep(角色名、属性、关键设定、伏笔关键词)+ 推理型一致性检查(规则边界、设定层级、跨章因果链、可滥用漏洞、代价一致性)。
|
|
8
|
-
3. AI 味按表达、用笔、故事三层检查:完整读 `story-review/references/expression.md`、`story-review/references/narrative-focus.md`、`story-review/references/story-logic.md`,以及信号索引 `story-review/references/banned-words.md
|
|
9
|
-
4.
|
|
10
|
-
5.
|
|
8
|
+
3. AI 味按表达、用笔、故事三层检查:完整读 `story-review/references/expression.md`、`story-review/references/narrative-focus.md`、`story-review/references/story-logic.md`,以及信号索引 `story-review/references/banned-words.md`。表层脚本只给候选,不替代三层诊断;词句干净也检查关键过程、详略失衡、行为依据与事件后果。每项报告原文位置、读者损失、建议与依据;缺少动机或事件设计时明确指出,不能以补动作代替。功能性写法按本书文风保留;只报告,不执行这些方法中的改写动作。参考不可读时用 SKILL.md 内置的三层去味 fallback 速查,并在「没法判断的地方」写明诊断受限。
|
|
9
|
+
4. 按通用 rubric 加叠加的平台表评估内容。
|
|
10
|
+
5. 长篇工程里,正文证据显示 `追踪/` 的事实错了或漏了,如伏笔过期、开放钩子漏登记,不改 `追踪/`,把要修的事实写进「需要你决定」,告诉作者:这次单人审不改追踪文件;装好审稿助手后用 `/story-review lean` 修,或在 `/story-long-write` 改到该章时一并提交。
|
|
11
|
+
6. 按统一 Findings Schema 整理问题,再按下方模板写给作者。
|
|
11
12
|
|
|
12
13
|
### solo 模式输出格式
|
|
13
14
|
|
|
14
15
|
<!-- author-report -->
|
|
15
16
|
```md
|
|
16
17
|
=== 《{书名}》{审查范围}审查(单人审)===
|
|
17
|
-
这次怎么审的:我一个人审{;原因一句话,如"审稿助手还没装,运行 /story-setup 后可以四个视角审"}
|
|
18
|
+
这次怎么审的:我一个人审{;原因一句话,如"审稿助手还没装,运行 /story-setup 后可以四个视角审"},按通用网文标准{,加上番茄长篇 | 起点长篇 | 短篇平台的要求}。
|
|
18
19
|
|
|
19
20
|
总体判断:{可以发 | 改完下面几处再发 | 这一章需要重写}——{一句话理由}
|
|
20
21
|
|
|
@@ -36,7 +36,7 @@
|
|
|
36
36
|
| 展开已定交锋、权衡和反馈,调整同场详略 | 改变人物决定、胜负、关系走向、代价或事件顺序 |
|
|
37
37
|
| 在既定揭露边界内呈现已知信息 | 提前揭底、搬动伏笔,或改变读者与人物获知顺序 |
|
|
38
38
|
|
|
39
|
-
|
|
39
|
+
对白措辞和必要微连接可以为既定内容服务;不能借一句台词或一个顺带动作新增威胁、承诺、拿到证据或改变人物策略。改换视角时只叙述该视角有依据的感知与认知,不能添加“进门时发现”“后来听说”等新经历来保留信息。
|
|
40
40
|
|
|
41
41
|
作者已明确要求重写或允许调整剧情时,直接执行被授权部分,保留其余已定事实;不用再次请求同一授权。仍缺少关键选择依据时,提出可审阅的最小选项。修法要写到哪次行为、什么条件或什么结果上,说明会牵动哪些后文,不只说“加强冲突”。建议与推测放在报告,不悄悄成为正文事实。
|
|
42
42
|
|
|
@@ -24,4 +24,4 @@
|
|
|
24
24
|
- 本书文风明确允许某种停顿标点时,可登记 `——` 或 `……`;具体修辞登记完整的获准原句,不能登记“不是”“没有”等泛词来关闭整类检查。
|
|
25
25
|
- 每项用上一行 `# 来源:…;用途:…` 说明当前请求或文风依据。只为执行作者已明确的选择登记,不因脚本报警自动放行。当前请求禁止某写法时移除相冲突的豁免;一次性保留只登记该句,不推断长期习惯。
|
|
26
26
|
- 深扫、标点整理和写后/下一章检查读取同一白名单。豁免只影响对应字面片段的风格检查;同一行其他问题照报,事实、字数、占位、工程词、截断和文件结构检查不豁免。
|
|
27
|
-
-
|
|
27
|
+
- 调用方限定的检查范围仍执行,检查重复、冗余、节奏和信息边界问题。裁决与发现写在交付报告中,不写进小说正文。
|