external/creative-writing-skills/cw-style-skill-creator/SKILL.md
Creative writing skill for creating style skills that teach Claude to write in specific styles. Use when you want to create style guides that the cw-prose-writing skill can follow. Creates either simple markdown files or full .skill packages. Audience is AI (Claude), format is directive and example-based.
npx skillsauth add seikaikyo/dash-skills cw-style-skill-creatorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create style skills that teach Claude your writing style.
This creates AI instructions (for Claude to read), NOT human documentation (for authors to read).
| AI Instructions | Human Documentation | |-----------------|---------------------| | "When writing X, do Y" | "The story uses X because Y" | | Directive commands | Explanatory descriptions | | Pattern + examples | Analysis + reasoning |
Always ask first:
Would you like me to create:
1. Simple markdown file (.md)
- Quick, lightweight
- Single file with style instructions
2. Full skill package (.skill)
- Properly structured and validated
- Can include reference files with examples
- Better for complex styles
Which format would you prefer?
---
description: [What this style covers]
alwaysApply: false
---
# [Style Name]
[Brief intro]
## [Category]
[Directive instructions with examples]
Location: .cursor/rules/styles/[name].md or user-specified
python /mnt/skills/examples/skill-creator/scripts/init_skill.py [skill-name] --path [output-dir]
Creates directory structure with SKILL.md, references/, scripts/, assets/
SKILL.md structure:
---
name: [skill-name]
description: Style skill for [specific writing type]
---
# [Style Name]
## Purpose
Teaches Claude to write [X] in the author's style.
## [Style Instructions]
[Directive instructions organized by category]
Add reference files if helpful:
references/examples.md - Good/bad examplesreferences/patterns.md - Detailed pattern libraryDelete unused directories (scripts/, assets/ if not needed)
python /mnt/skills/examples/skill-creator/scripts/package_skill.py [path-to-skill] [output-dir]
Creates validated .skill file ready to distribute.
Use imperative/command form:
✅ "Use short sentences during action"
✅ "Avoid dialogue tags"
✅ "Show emotion through action"
❌ "The author tends to use short sentences" (that's analysis, not instruction)
Always include examples:
**Emotional beats:**
- Use action instead of emotional labels
- Example: "Her hands trembled" not "She felt nervous"
Pattern + Example format:
**[Pattern name]:**
- [Instruction about the pattern]
- Example: [Concrete example]
- Avoid: [What NOT to do]
Master Prose: Overall writing voice, sentence structure, tone
Dialogue: Tag usage, action beats, subtext, character voice
Action: Sentence length, detail level, pacing
Description: Sensory detail, metaphors, level of detail
Character Voice: Per-character speech patterns and vocabulary
Formatting: Em dashes, ellipsis, scene breaks, thought formatting
From user description:
From existing prose:
Simple .md or full .skill package?
.cursor/rules/styles/ or specified locationinit_skill.pypackage_skill.py---
description: Dialogue writing conventions
alwaysApply: false
---
# Dialogue Style
## Dialogue Tags
**Minimize "said":**
- Use action beats instead
- Example: She crossed her arms. "Fine."
- When using tags, prefer "said" to fancy verbs
## Interruptions
**Use em dashes:**
- For interrupted speech: "I thought we could—"
- Example: "Wait, I—" He grabbed her arm.
## Subtext
**Characters avoid directness:**
- Show tension through what's NOT said
- Example: "That's nice." (flat, clearly upset)
- Avoid: "I'm angry!" (too direct)
---
name: character-amber-voice
description: Amber's voice and speech patterns
---
# Character Voice: Amber
## Speech Patterns
**Careful word choice:**
- Adult consciousness = measured speech
- Avoids contractions when stressed
- Example: "I do not want to go" not "I don't wanna go"
**Politeness as defense:**
- Overly formal when uncomfortable
- Uses "please" and "thank you" excessively
## Internal Monologue
**Analytical:**
- Observes and categorizes
- Example: "Dr. Fuji's hands trembled—stress response, possibly guilt."
The workflow:
tools
Conduct comprehensive GDPR compliance assessments by evaluating data processing activities against EU Regulation 2016/679, including Article 30 records of processing, lawful basis validation, data subject rights implementation, Data Protection Impact Assessments (DPIAs) under Article 35, breach notification procedures, international transfer safeguards (SCCs, adequacy decisions), and technical/organizational measures under Article 32. Use when processing personal data of EU residents, preparing for supervisory authority audits, implementing privacy-by-design for new systems, scoping compliance gaps for M&A due diligence, assessing third-party processors, or responding to data subject access requests at scale. Incorporates 2026 guidance from ICO, EDPB, and post-Data (Use and Access) Act 2025 UK-GDPR considerations. Do not use for implementing specific Article 32 controls — use implementing-gdpr-data-protection-controls; or for DSAR automation — use implementing-gdpr-data-subject-access-request.
tools
Parse Windows forensic artifacts—$MFT/$J (MFTECmd), Prefetch (PECmd), registry hives (RECmd), shellbags, and Amcache—into normalized CSV/JSON with Eric Zimmerman's EZ Tools, then load results into Timeline Explorer for analysis. Use during DFIR/incident-response investigations, after triage collection (e.g. with KAPE), to establish program execution, file/folder access, and persistence evidence from acquired forensic images.
development
Build automated multi-turn adversarial attacks against conversational LLM targets using Microsoft PyRIT's RedTeamingOrchestrator, CrescendoOrchestrator (gradual escalation), and TreeOfAttacksWithPruningOrchestrator (adaptive branching), with scorer feedback loops and persisted conversation memory. Use when single-shot LLM scanning is insufficient and you need multi-turn, scorer-driven AI red-team campaigns against a chatbot or agent.
testing
Stand up MISP, enable and cache curated threat feeds (CIRCL, abuse.ch, Feodo Tracker), apply warninglists to suppress false positives, query indicators with PyMISP, and export attributes as auto-generated Suricata/Sigma/Wazuh detection rules. Use when maturing a MISP instance to actively drive detection, curating threat feeds with quality controls, or automating IOC-to-detection pipelines for the SIEM/IDS.