원클릭으로
kimi-writing
Kimi-K2.5 Writing Skill.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Kimi-K2.5 Writing Skill.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Map of the Tailscale network (tailnet) and how to reach, operate, and deploy to remote machines over it via SSH. Use for any cross-machine task — remote install, deploy, restart, log-check, or file transfer.
Operate nano-core coding delegation. Use for /coder or /coding execution, /coder-plan or /coder_plan planning, natural-language coding approval prompts, delegated runs, run IDs, progress, cancellation, and final-result handling; not for direct coding or automatic delegation.
Diagnose nano-core runtime failures. Use for provider/model errors, Pi launch or skill-discovery failures, Telegram/WhatsApp routing, singleton locks, service state, IPC, SQLite state, scheduler behavior, or per-group logs; not for installation or feature work.
Install or onboard nano-core on a host. Use for first-time installation, prerequisites, runtime selection, provider/channel configuration, daemon setup, upgrades, or doctor checks; not for diagnosing an already-running incident.
Understand and operate nano-core itself. Use for questions about nano-core architecture, behavior, configuration, capabilities, skills, installation, troubleshooting, Telegram administration, or coding delegation; route focused work to the matching nano-core skill.
Configure and operate nano-core through Telegram. Use for bot enablement, main/admin chat claims, trigger routing, command authorization, delivery modes, media intake, polling conflicts, and Telegram-first operation; not for WhatsApp-only or general runtime incidents.
| name | kimi-writing |
| description | Kimi-K2.5 Writing Skill. |
Professional and creative writing assistant powered by Moonshot AI's Kimi-K2.5 model via OpenRouter. Built for thoughtful, domain-aware content that avoids generic AI slop.
moonshotai/kimi-k2.5Baked-in system prompt that prevents generic content farm output:
Automatically detects and adapts to:
Can parallelize long-form writing:
cd /Users/username/clawdbot/skills/kimi-writing
uv pip install openai pydantic python-dotenv
Set your OpenRouter API key:
export OPENROUTER_API_KEY="your-key-here"
Or create .env file:
OPENROUTER_API_KEY=sk-or-v1-...
uv run scripts/write.py "write a landing page for farm tech SaaS" \
--mode thinking \
--style marketing \
--audience "farmers, agronomists"
uv run scripts/write.py "create whitepaper on precision irrigation" \
--domain agriculture \
--format pdf \
--tone authoritative
uv run scripts/write.py refine draft.md \
--style professional \
--make-human \
--reduce-corporate-speak
uv run scripts/write.py plan "technical documentation series" \
--agent-swarm
Professional:
Creative:
Website Copy:
Technical:
Marketing:
Research:
| Option | Description | Default |
|---|---|---|
--mode | thinking or instant | auto |
--style | business, creative, technical, marketing | Auto-detect |
--domain | Industry/niche | Auto-detect |
--audience | Target audience | General |
--tone | formal, casual, authoritative, friendly | Neutral |
--format | markdown, plain, html | markdown |
--max-tokens | Output length | 8192 |
--temperature | Creativity level | Mode-dependent |
--refine | Refine existing file instead | - |
--make-human | Humanize output flag | false |
--agent-swarm | Enable parallel execution | false |
--dry-run | Show plan without writing | false |
uv run scripts/write.py \
"Write a blog post about drought-resistant corn varieties" \
--domain agriculture \
--audience "small-scale farmers" \
--tone practical \
--mode thinking
uv run scripts/write.py \
"Create API documentation for user authentication endpoints" \
--style technical \
--format markdown \
--mode thinking
uv run scripts/write.py \
"Write Instagram captions for new farm equipment launch" \
--style marketing \
--audience "farm owners" \
--tone enthusiastic \
--mode instant
kimi-writing/
├── SKILL.md # This file
├── README.md # Quick start
├── scripts/
│ ├── write.py # Main CLI entry
│ ├── modes.py # Mode selection logic
│ ├── style_enforcer.py # Anti-slop validation
│ └── domain_analyzer.py # Niche detection
├── prompts/
│ ├── system.md # Core system prompt
│ ├── metaprompt.md # Writing metaprompt
│ └── styles/ # Domain-specific guides
│ ├── agriculture.md
│ ├── business.md
│ ├── creative.md
│ ├── marketing.md
│ └── technical.md
└── tools/
├── openrouter_client.py # API wrapper
└── writing_assistant.py # Core logic
All generated content passes through:
Generic-sounding output:
--make-human flag usagethinking mode for more nuanceToo technical/simplified:
--audience parameter--tone flag to calibrateSlow response:
instant mode--max-tokens--dry-run to preview first✅ Production Ready
Last Updated: February 4, 2026