chapter-drafter
完全なアウトラインをもとに、複数の編集スキルを組み合わせた反復的なブラッシュアップを経て、章の初稿を自律的に作成・仕上げます。アウトラインが揃っており、精度の高い初稿を効率よく仕上げたい場合に使用してください。
description の原文を見る
Autonomously draft and polish chapters through multi-skill editorial passes. Use when you have a complete outline and want to produce a polished first draft with iterative refinement.
SKILL.md 本文
Chapter Drafter: Orchestrator Skill
You autonomously draft and polish chapter scenes through iterative editorial passes. Given an outline, you produce polished first-draft prose by drafting each scene, evaluating it against editorial criteria, and revising until quality thresholds are met.
Core Principle
Orchestration is iteration with hierarchy. Fix structure before character, character before originality, originality before dialogue, dialogue before prose. Don't polish what might be cut; don't revise dialogue in a scene that needs structural rework.
Prerequisites
Before invoking this skill, ensure:
- Complete outline exists - Scene beats with goals, conflicts, and intended outcomes
- Characters defined - Lie/want/need, voice patterns, arc positions
- World established - Setting details sufficient for scene work
- Story-sense diagnosis complete - No structural story problems remaining
Do NOT use this skill if:
- Outline is still in flux
- Character arcs undefined
- Story-sense would diagnose structural problems
The Orchestration Loop
FOR each scene in chapter outline:
1. BUILD CONTEXT
- Load character voices from previous scenes
- Load open plot threads
- Load cliche avoidances
- Extract scene purpose from outline
2. DRAFT SCENE
- Generate initial prose from outline beat
- Apply character voices
- Maintain plot thread continuity
3. EVALUATION LOOP (max 5 cycles)
│
├─► Pass 1: scene-sequencing (35%)
│ └─► If FAIL: REWRITE scene
├─► Pass 2: character-arc (25%)
├─► Pass 3: cliche-transcendence (15%)
├─► Pass 4: dialogue (15%)
└─► Pass 5: prose-style (10%)
│
Calculate composite score
│
├─► >= 80: ACCEPT
├─► 60-79: TARGETED FIX → re-evaluate
├─► 40-59: REWRITE → return to draft
└─► <40: REJECT → full re-draft from outline
4. POST-ACCEPT
- Extract character voice patterns → update context
- Track plot thread changes → update registry
- Record cliche transcendences → update avoidances
- Write scene to output
- Update progress tracker
END FOR
Pass Criteria
Pass 1: Scene-Sequencing (35% weight)
Evaluates Goal-Conflict-Disaster structure and pacing.
| Criterion | PASS | WARN | FAIL |
|---|---|---|---|
| Goal clarity | POV goal clear in opening beats | Goal exists but buried | No discernible goal |
| Conflict escalation | Opposition intensifies | Conflict static but present | No real opposition |
| Disaster quality | "Yes, but..." or "No, and..." | Simple "No" | Clean "Yes" or no resolution |
| Sequel presence | Reaction-dilemma-decision present | Abbreviated sequel | Missing after high-tension |
| Scene-sequel ratio | Matches intended pacing | Slight mismatch | Severely mismatched |
Critical: If scene-sequencing FAILS, do NOT proceed to other passes. Structural problems invalidate downstream evaluation.
Pass 2: Character-Arc (25% weight)
Evaluates transformation consistency and arc progress.
| Criterion | PASS | WARN | FAIL |
|---|---|---|---|
| Lie visibility | False belief evident in choices | Lie present but unstated | No lie operative |
| Want/Need gap | Clear tension between stated/actual | Gap exists but unclear | Want = Need (no tension) |
| Arc progress | Scene advances or challenges arc | Arc static but consistent | Character contradicts arc |
| Transformation markers | Choices reflect arc position | Position unclear | Acts against personality |
Pass 3: Cliche-Transcendence (15% weight)
Evaluates originality via orthogonality test.
| Criterion | PASS | WARN | FAIL |
|---|---|---|---|
| Form axis | Non-default form | Slight variation | Exactly genre default |
| Knowledge axis | Own concerns, accidental intersection | Some plot awareness | Fully story-serving |
| Goal axis | Own agenda that collides | Goal connected to plot | Purely protagonist-serving |
| Role axis | Own story that intersects | Somewhat independent | Exists only for hero |
| Orthogonality test | 2+ axes orthogonal | 1 axis orthogonal | All axes match default |
Pass 4: Dialogue (15% weight)
Evaluates voice distinctiveness, subtext, and function.
| Criterion | PASS | WARN | FAIL |
|---|---|---|---|
| Voice distinctiveness | Characters distinguishable without tags | Some overlap | Identical voices (D1) |
| Subtext presence | Gap between said and meant | Occasional direct statements | Everything on-the-nose (D4) |
| Double-duty test | 3+ functions per exchange | 2 functions | Single function only (D5) |
| Naturalness | Contractions, interruptions, rhythm | Slightly formal | Wooden/stilted (D2) |
| Exposition handling | Information through conflict | Minor "as you know" | Exposition dump (D3) |
Pass 5: Prose-Style (10% weight)
Evaluates sentence-level craft.
| Criterion | PASS | WARN | FAIL |
|---|---|---|---|
| Sentence variety | Length and structure vary | Some variation | Monotonous (P4) |
| Clarity | Concrete, clear antecedents | Occasional abstraction | Unclear writing (P2) |
| Voice consistency | Diction level consistent | Minor shifts | Random shifts (P6) |
| Economy | Words earn place | Minor redundancy | Overwrought (P3) |
| Active voice | Passive intentional | Some default passive | Passive overuse (P5) |
Composite Scoring
Each pass produces a score from 0-100:
- All PASS = 100
- Each WARN = -15
- Each FAIL = -40
Composite = SUM(pass_score × pass_weight)
| Composite | Outcome | Action |
|---|---|---|
| >= 80 | ACCEPT | Scene complete, proceed to next |
| 60-79 | REVISE | Fix lowest-scoring pass, re-evaluate |
| 40-59 | REWRITE | Regenerate with failure constraints |
| < 40 | REJECT | Full re-draft from outline |
Iteration Limits
| Level | Limit | On Exceed |
|---|---|---|
| Per-pass | 3 | Escalate to rewrite |
| Per-scene | 12 | Accept at threshold 50, flag for review |
| Per-chapter | 50 | Stop, report remaining issues |
Diminishing returns detection: If improvement < 10% between iterations, accept current state or escalate.
Context Accumulation
Maintain across scenes:
Character Voices
After each scene, extract and store:
- Vocabulary patterns per character
- Sentence rhythm patterns
- Directness level
- Verbal tics and avoidances
Use as constraint for subsequent scenes: "Character X speaks like [markers]"
Plot Threads
Track:
- Open threads - Introduced, not resolved
- Closed threads - Resolved this chapter
- Foreshadowing - Planted for future payoff
Each scene checks:
- No contradiction with established facts
- Open threads acknowledged or advanced
- At least one element progresses
Cliche Avoidances
After cliche-transcendence pass, record:
- Which defaults were avoided
- How they were transcended
- New elements that feel fresh
Use as constraint: "Already transcended [X], maintain freshness"
Progress Tracker
Use the progress tracker template to persist state:
## Chapter Progress: [Title]
Started: [timestamp]
Current: Scene [N], Pass [M], Iteration [K]
### Scenes
| Scene | Status | Pass | Iterations | Score | Issues |
|-------|--------|------|------------|-------|--------|
### Context
- Character Voices: [accumulated]
- Plot Threads: [open/closed]
- Cliche Avoidances: [list]
### Change Log
- [timestamp] [change]
Revision Strategy
Targeted Fix (score 60-79)
- Identify lowest-scoring pass
- Extract specific failure criteria
- Generate minimal fix addressing that criterion
- Re-evaluate that pass + downstream passes
- If pass improves, recalculate composite
Rewrite (score 40-59)
- Preserve scene goal from outline
- Generate new draft with explicit constraints:
- "Must include clear goal in opening"
- "Conflict must escalate"
- etc. based on failures
- Re-run full evaluation loop
Reject (score < 40)
- Return to outline beat
- Re-draft from scratch
- Treat as new scene (reset iterations)
Conflict Resolution
When fixing one pass breaks another:
- Detect: Re-run all passes after any fix
- Compare: Did any pass regress?
- Prioritize: Higher-weight pass wins ties
- Seek synthesis: Can fix satisfy both?
- Accept trade-off: If irreconcilable, accept per hierarchy
Escalation: If conflict persists after 2 attempts, flag scene for human review.
Anti-Patterns
The Infinite Polisher
Pattern: Keeps iterating because one criterion is at WARN. Fix: WARN is acceptable. Accept at threshold after iteration limit.
The Pass Skipper
Pattern: Jumps to prose-style when scene-sequencing failed. Fix: Hard gate on structural passes. FAIL blocks progression.
The Context Amnesiac
Pattern: Each scene drafted in isolation, losing voice and threads. Fix: Explicit context loading before each scene draft.
The Cascade Blind Spot
Pattern: Fixes dialogue, doesn't check if prose-style regressed. Fix: Always re-evaluate current pass + downstream after any fix.
The Silent Failer
Pattern: Hits iteration limit, proceeds without documentation. Fix: Log all limit exits with categorized remaining issues.
Output Persistence
Progress Tracker
- Location:
context/chapter-drafter/[chapter]-progress.md - Update: After each scene acceptance
- Purpose: Resume point if interrupted
Scene Output
- Location:
drafts/[story]/[chapter]/scene-[N].md - Update: On scene acceptance
- Purpose: Accumulated draft prose
Context State
- Location:
context/chapter-drafter/[chapter]-context.md - Update: After each scene
- Purpose: Character voices, threads, avoidances
Integration
Inbound (feeds into chapter-drafter)
| Skill | What it provides |
|---|---|
| outline-collaborator | Scene beats with goal-conflict-disaster |
| character-arc | Lie/want/need for each character |
| worldbuilding | Setting details for scene work |
| story-sense | Confirmation structure is solid |
Outbound (chapter-drafter produces)
| Output | Next step |
|---|---|
| Draft chapter | revision (for full manuscript revision) |
| Flagged scenes | Human review |
| Context state | Next chapter drafting |
Example Invocation
Input: Chapter outline with 5 scene beats
Process:
- Load outline, confirm prerequisites
- Initialize progress tracker
- For each scene:
- Build context from prior scenes
- Draft initial prose
- Run evaluation loop
- On ACCEPT: extract context, write output
- Complete: 5 polished scenes, flagged issues documented
Output:
- 5 scene files in
drafts/[story]/[chapter]/ - Progress tracker showing all iterations
- Context file for next chapter
- List of any flagged issues for human review
ライセンス: MIT(寛容ライセンスのため全文を引用しています) · 原本リポジトリ
詳細情報
- 作者
- jwynia
- リポジトリ
- jwynia/agent-skills
- ライセンス
- MIT
- 最終更新
- 不明
Source: https://github.com/jwynia/agent-skills / ライセンス: MIT
関連スキル
superfluid
Superfluidプロトコルおよびそのエコシステムに関するナレッジベースです。Superfluidについて情報を検索する際は、ウェブ検索の前にこちらを参照してください。対応キーワード:Superfluid、CFA、GDA、Super App、Super Token、stream、flow rate、real-time balance、pool(member/distributor)、IDA、sentinels、liquidation、TOGA、@sfpro/sdk、semantic money、yellowpaper、whitepaper
civ-finish-quotes
実質的なタスクが真に完了した際に、文明風の儀式的な引用句を追加します。ユーザーやエージェントが機能追加、リファクタリング、分析、設計ドキュメント、プロセス改善、レポート、執筆タスクといった実際の成果物を完成させるときに、明示的な依頼がなくても使用します。短い返信や小さな修正、未完成の作業には適用しません。
nookplot
Base(Ethereum L2)上のAIエージェント向け分散型調整ネットワークです。エージェントがオンチェーンアイデンティティを登録する、コンテンツを公開する、他のエージェントにメッセージを送る、マーケットプレイスで専門家を雇う、バウンティを投稿・請求する、レピュテーションを構築する、共有プロジェクトで協業する、リサーチチャレンジを解くことでNOOKをマイニングする、キュレーションされたナレッジを備えたスタンドアロンオンチェーンエージェントをデプロイする、またはアグリーメントとリワードで収益を得る場合に利用できます。エージェントネットワーク、エージェント調整、分散型エージェント、NOOKトークン、マイニングチャレンジ、ナレッジバンドル、エージェントレピュテーション、エージェントマーケットプレイス、ERC-2771メタトランザクション、Prepare-Sign-Relay、AgentFactory、またはNookplotが言及された場合にトリガーされます。
web3-polymarket
Polygon上でのPolymarket予測市場取引統合です。認証機能(L1 EIP-712、L2 HMAC-SHA256、ビルダーヘッダー)、注文発注(GTC/GTD/FOK/FAK、バッチ、ポストオンリー、ハートビート)、市場データ(Gamma API、Data API、オーダーブック、サブグラフ)、WebSocketストリーミング(市場・ユーザー・スポーツチャネル)、CTF操作(分割、統合、償却、ネガティブリスク)、ブリッジ機能(入金、出金、マルチチェーン)、およびガスレスリレイトランザクションに対応しています。AIエージェント、自動マーケットメーカー、予測市場UI、またはPolygraph上のPolymarketと統合するアプリケーション構築時に活用できます。
ethskills
Ethereum、EVM、またはブロックチェーン関連のリクエストに対応します。スマートコントラクト、dApps、ウォレット、DeFiプロトコルの構築、監査、デプロイ、インタラクションに適用されます。Solidityの開発、コントラクトアドレス、トークン規格(ERC-20、ERC-721、ERC-4626など)、Layer 2ネットワーク(Base、Arbitrum、Optimism、zkSync、Polygon)、Uniswap、Aave、Curveなどのプロトコルとの統合をカバーします。ガスコスト、コントラクトのデシマル設定、オラクルセキュリティ、リエントランシー、MEV、ブリッジング、ウォレット管理、オンチェーンデータの取得、本番環境へのデプロイ、プロトコル進化(EIPライフサイクル、フォーク追跡、今後の変更予定)といったトピックを含みます。
xxyy-trade
このスキルは、ユーザーが「トークン購入」「トークン売却」「トークンスワップ」「暗号資産取引」「取引ステータス確認」「トランザクション照会」「トークンスキャン」「フィード」「チェーン監視」「トークン照会」「トークン詳細」「トークン安全性確認」「ウォレット一覧表示」「マイウォレット」「AIスキャン」「自動スキャン」「ツイートスキャン」「オンボーディング」「IP確認」「IPホワイトリスト」「トークン発行」「自動売却」「損切り」「利益確定」「トレーリングストップ」「保有者」「トップホルダー」「KOLホルダー」などをリクエストした場合、またはSolana/ETH/BSC/BaseチェーンでXXYYを経由した取引について言及した場合に使用します。XXYY Open APIを通じてオンチェーン取引とデータ照会を実現します。