.agents/skills/internal-comms/SKILL.md
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
npx skillsauth add G858-debug/No-Safe-Word internal-commsInstall 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.
To write internal communications, use this skill for:
To write any internal communication:
examples/ directory:
examples/3p-updates.md - For Progress/Plans/Problems team updatesexamples/company-newsletter.md - For company-wide newslettersexamples/faq-answers.md - For answering frequently asked questionsexamples/general-comms.md - For anything else that doesn't explicitly match one of the aboveIf the communication type doesn't match any existing guideline, ask for clarification or more context about the desired format.
3P updates, company newsletter, company comms, weekly update, faqs, common questions, updates, internal comms
development
# SDXL Character LoRA Training — Pipeline Reference ## Overview Character LoRAs are trained using Kohya sd-scripts (`sdxl_train_network.py`) on RunPod GPU pods. Training runs as a fire-and-forget batch job — the orchestrator creates the pod, the pod trains, uploads the result, and POSTs a webhook on completion. **Base model for training:** SDXL 1.0 base (NOT Juggernaut Ragnarok). Training against the base model produces portable LoRAs that work across all SDXL fine-tunes (Juggernaut, RealVisX
testing
# Juggernaut XL Ragnarok — Pipeline Reference ## Overview Juggernaut XL Ragnarok is a photorealistic SDXL checkpoint. It is the most downloaded SDXL model (520K+ downloads) and the final SDXL release from KandooAI / RunDiffusion. **Key characteristics:** - Photorealistic output with cinematic quality - NSFW capability baked into training (trained with Booru tags on an NSFW dataset, merged with a Lustify-based NSFW pass for anatomical stability) - Supports BOTH natural language prompts AND Boo
tools
# Image Editing Workflows — Pipeline Reference ## Overview After initial image generation, the user has access to several post-generation editing tools. These are ComfyUI workflow variants that modify an existing generated image rather than generating from scratch. All editing workflows run on the same RunPod serverless infrastructure as generation, using the same Juggernaut Ragnarok checkpoint. ## Inpainting **Purpose:** Fix a specific region of a generated image without regenerating the w
testing
When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing strategies,' 'marketing tactics,' 'ways to promote,' 'ideas to grow,' 'what else can I try,' 'I don't know how to market this,' 'brainstorm marketing,' or 'what marketing should I do.' Use this as a starting point whenever someone is stuck or looking for inspiration on how to grow. For specific channel execution, see the relevant skill (paid-ads, social-content, email-sequence, etc.).