crucible-editor
Revision and editing assistant for Crucible-drafted novels. Use when author has completed a first draft and wants to revise, edit, or polish their manuscript. Handles developmental editing, line editing, copy editing, and final polish. Triggers on "edit my novel," "revise chapter X," "polish my manuscript," "help me edit," or when user has completed draft chapters and wants to improve them.
What this skill does
# Crucible Editor
Revision and editing assistant for Crucible-drafted novels, handling developmental editing through final polish.
## Overview
The Crucible Editor provides structured editing support at four levels:
1. **Developmental Editing** — Structure, pacing, character arcs, plot coherence
2. **Line Editing** — Scene-level prose improvement, voice consistency
3. **Copy Editing** — Grammar, consistency, style guide adherence
4. **Final Polish** — Micro-level refinement, word choice, rhythm
## Before Starting
**Read these references based on editing phase:**
- `references/developmental-checklist.md` — Structure and story issues
- `references/line-editing-guide.md` — Prose improvement techniques
- `references/copy-editing-standards.md` — Grammar and style rules
- `references/polish-techniques.md` — Final refinement methods
## Questioning Rules
1. **ALWAYS use AskUserQuestion tool** for all user questions (provides interactive UI)
2. **Max 4 options per question** (tool limit) + "Other" is automatic
3. **Max 4 questions per AskUserQuestion call**
4. **Reference specific issues** by location (chapter, scene, paragraph)
5. **Batch similar decisions** when possible
**CRITICAL: Use the AskUserQuestion tool, NOT plain text A/B/C options.**
## Required Inputs
Before editing can begin, gather:
1. **Draft Chapter(s)** (required) — The crucible-writer output to edit
2. **Chapter Outline** (recommended) — For developmental editing verification
3. **Style Profile** (recommended) — For voice consistency checking
4. **Story Bible** (as needed) — For continuity verification
5. **Review Reports** (if available) — From bi-chapter review agents
## Workflow
```
Phase 1: ASSESSMENT → Load draft, identify editing level needed
Phase 2: DEVELOPMENTAL → Structure and story issues (if needed)
Phase 3: LINE EDITING → Prose improvement scene-by-scene
Phase 4: COPY EDITING → Grammar and consistency pass
Phase 5: POLISH → Final refinement
Phase 6: COMPILE → Generate edited manuscript
```
---
## Phase 1: Assessment
### Load Draft Material
Request the draft material:
```
To begin editing, I need:
1. **The chapter(s) to edit** — paste or specify file location
2. **Any specific concerns?** (Optional)
- Areas you feel need work
- Feedback from readers/critique partners
- Issues flagged in bi-chapter reviews
```
Then use AskUserQuestion for editing scope:
```json
{
"questions": [
{
"header": "Edit Scope",
"question": "What level of editing do you want?",
"options": [
{"label": "Full edit", "description": "All levels: developmental, line, copy, and polish"},
{"label": "Developmental only", "description": "Structure, pacing, character arcs, plot coherence"},
{"label": "Line editing only", "description": "Scene-level prose improvement, voice consistency"},
{"label": "Copy/Polish only", "description": "Grammar, consistency, final refinement"}
],
"multiSelect": false
}
]
}
```
### Initial Assessment
After loading, provide:
```
**EDITING ASSESSMENT: Chapter [X]**
Word Count: [X,XXX]
Overall Quality: [Draft/Rough/Polished]
**Developmental Issues Found:**
- [ ] None / [List specific issues]
**Line Editing Needs:**
- [ ] Minimal / Moderate / Significant
**Copy Editing Level:**
- [ ] Clean / Some errors / Needs attention
**Recommended Editing Path:**
[Specific recommendation based on assessment]
```
Use AskUserQuestion:
```json
{
"questions": [
{
"header": "Edit Path",
"question": "How would you like to proceed?",
"options": [
{"label": "Recommended path", "description": "Follow the suggested editing sequence"},
{"label": "Specific level", "description": "Focus on one particular editing level"},
{"label": "Discuss first", "description": "Talk through the issues before deciding"}
],
"multiSelect": false
}
]
}
```
---
## Phase 2: Developmental Editing
Focus: Structure, story, character, pacing
### Structural Checks
Verify against outline (if available):
- [ ] All required scenes present
- [ ] Scene order makes sense
- [ ] No unplanned additions that derail structure
- [ ] Chapter accomplishes its story purpose
### Character Arc Verification
- [ ] Character motivations clear
- [ ] Emotional beats land
- [ ] Character voice consistent
- [ ] Relationship dynamics accurate
### Pacing Analysis
```
**PACING REPORT: Chapter [X]**
Opening hook: [Strong/Adequate/Weak]
Middle momentum: [Good/Drags/Rushed]
Ending turn: [Effective/Flat/Confusing]
Specific pacing issues:
- [Scene X] drags because [reason]
- [Scene Y] rushes past [important moment]
Recommendations:
1. [Specific structural change]
2. [Specific pacing adjustment]
```
### Developmental Fixes
For each issue identified:
```
**DEVELOPMENTAL FIX [X]**
Issue: [Description]
Location: [Scene/paragraph reference]
Impact: [How this affects the story]
Proposed fix:
[Specific change or rewrite recommendation]
```
Use AskUserQuestion:
```json
{
"questions": [
{
"header": "Fix",
"question": "How would you like to handle this developmental issue?",
"options": [
{"label": "Apply fix", "description": "Implement the proposed change"},
{"label": "Skip", "description": "Will address differently or later"},
{"label": "Discuss", "description": "Talk through the approach first"}
],
"multiSelect": false
}
]
}
```
---
## Phase 3: Line Editing
Focus: Prose quality scene-by-scene
### Scene-by-Scene Analysis
For each scene, check:
- **Clarity** — Is meaning clear on first read?
- **Economy** — Any wasted words or repetition?
- **Voice** — Does it match the style profile?
- **Sensory Detail** — Appropriate level for scene type
- **Dialogue** — Natural, distinct voices, effective tags
### Line Editing Report Format
```
**LINE EDIT: Scene [X.Y]**
Strengths:
- [What's working well]
Issues Found:
1. [Issue type]: "[specific passage]" — [explanation]
2. [Issue type]: "[specific passage]" — [explanation]
Suggested Revisions:
[Show original vs revised for key passages]
```
Use AskUserQuestion:
```json
{
"questions": [
{
"header": "Revisions",
"question": "How would you like to handle these line edits?",
"options": [
{"label": "Accept all", "description": "Apply all suggested revisions"},
{"label": "Review each", "description": "Go through revisions one by one"},
{"label": "Skip scene", "description": "Move to the next scene"}
],
"multiSelect": false
}
]
}
```
### Common Line Edit Categories
- **Show vs Tell** — Convert telling to showing
- **Filter Words** — Remove "felt," "saw," "heard" etc.
- **Weak Verbs** — Strengthen verb choices
- **Redundancy** — Cut repeated information
- **Passive Voice** — Convert to active where appropriate
- **Dialogue Tags** — Simplify or remove unnecessary tags
- **Pacing** — Adjust sentence rhythm
---
## Phase 4: Copy Editing
Focus: Grammar, consistency, style
### Grammar Check
- Sentence structure
- Subject-verb agreement
- Tense consistency
- Pronoun clarity
- Punctuation
### Consistency Check
- Character name spellings
- Place name spellings
- Magic/world terminology
- Timeline references
- Physical descriptions match story bible
### Style Adherence
- Point of view consistency
- Narrative distance consistent
- Dialogue formatting
- Scene break formatting
### Copy Edit Report
```
**COPY EDIT REPORT: Chapter [X]**
Errors Found: [Count]
By Category:
- Grammar: [X]
- Spelling: [X]
- Consistency: [X]
- Style: [X]
Critical Fixes (must address):
1. [Issue with correction]
Minor Fixes (recommended):
1. [Issue with correction]
```
Use AskUserQuestion:
```json
{
"questions": [
{
"header": "Copy Fixes",
"question": "How would you like to handle these copy edits?",
"options": [
{"label": "Apply all", "description": "Apply all fixes (critical and minor)"},
{"label": Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.