seikaikyo/cw-prose-writing
external/creative-writing-skills/cw-prose-writing/SKILL.md
Creative writing skill for drafting and editing narrative fiction prose. Use when writing new scenes, chapters, or dialogue, or when editing existing prose. Discovers and follows project-specific style guides, character voice conventions, and formatting preferences.
$ install --global
skillsauthnpx skillsauth add seikaikyo/dash-skills cw-prose-writingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 5, 2026, 5:11 PM4.6s1 file scanned
SKILL.md
- name:
- cw-prose-writing
- description:
- Creative writing skill for drafting and editing narrative fiction prose. Use when writing new scenes, chapters, or dialogue, or when editing existing prose. Discovers and follows project-specific style guides, character voice conventions, and formatting preferences.
Prose Writing
Write narrative fiction following your project's established style and conventions.
Before Writing: Discover Style Guidance
ALWAYS check for style guidance before writing:
Step 1: Check Project Documentation
Look for:
CLAUDE.md- Often explains project structureWRITING.md,CONVENTIONS.md,STYLE.mdREADME.md- May contain writing instructions
Step 2: Find Style Guide Locations
Common locations:
.cursor/rules/styles/- Style files (.mdor.skillpackages).cursor/rules/- May contain style files.ai/styles/,.ai/rules/docs/style/,style/,writing/- Installed Claude skills
Style guides can be:
- Simple markdown files (
.md) - Full skill packages (
.skill) created by cw-style-skill-creator - Both work - read and follow their instructions
Step 3: Identify Relevant Guides
Different types:
- Master prose guide (overall writing style)
- Scene-type guides (dialogue, action, description)
- Character voice guides (how specific characters speak/think)
- POV guides (perspective and tense)
- Formatting guides (em dashes, ellipsis, scene breaks)
Read relevant guides BEFORE writing. If writing dialogue-heavy scene, read both master and dialogue guides.
Step 4: Check Reference Materials
Also look for:
- Character profiles (voice consistency, canon facts)
- Location wikis (setting details)
- Timeline docs (chronology)
- Lore pages (worldbuilding accuracy)
If No Style Guides Exist
When NO style guides found:
Inform user:
I don't see any style guides in your project yet. I can write in
competent default prose, but you'll get better results by creating
style guides first using the cw-style-skill-creator skill.
Would you like me to:
1. Write in default style for now
2. Help you create style guides first
3. Search your project for existing style documentation
If user wants you to proceed anyway:
- Write in clean, competent prose
- Look for patterns in existing chapters if available
- Use neutral narrative voice
- Follow basic conventions
Using Web Search
Search when helpful for:
- Research for scenes (locations, historical details, technical accuracy)
- Verifying facts mentioned in prose
- Finding inspiration or reference examples
- Genre convention research
- Cultural accuracy verification
Writing Workflow
While Writing:
- Apply discovered style conventions
- Match character voices to profiles
- Respect established canon
- Use project formatting conventions
- Maintain consistent POV and tense
Self-Check After:
- Does this match the project's voice?
- Is POV/tense consistent?
- Do characters sound like themselves?
- Are canon facts accurate?
Output Format
Claude.ai Chat
Markdown artifact with proper formatting
Claude Code
- Check project structure for chapter organization
- Match existing naming conventions
- Use appropriate directory
- Include proper frontmatter if project uses it
Integration with Style Skills
The workflow:
- User writes chapters naturally
- User uses cw-style-skill-creator to create style skills
- This skill loads and follows those style skills
- Result: AI writes in user's established style
Without style guides: Generic competent prose
With style guides: YOUR specific voice
Skills are Composable
Feel free to combine with other skills - e.g., using cw-official-docs to check character details while writing.
Related Skills
seikaikyo/conducting-gdpr-compliance-assessment
tools
VerifiedTrustedCommunity
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.
2SKILL.mdUpdated Sep 11, 2026
seikaikyo/parsing-artifacts-with-eric-zimmerman-tools
tools
VerifiedTrustedCommunity
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.
2SKILL.mdUpdated Jun 23, 2026
seikaikyo/orchestrating-llm-attacks-with-pyrit
development
VerifiedTrustedCommunity
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.
2SKILL.mdUpdated Jun 23, 2026
seikaikyo/operationalizing-misp-threat-feeds
testing
VerifiedTrustedCommunity
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.
2SKILL.mdUpdated Jun 23, 2026