Kiln AI
Official@kiln-ai
Build AI Products
Agent Skills by Kiln AI
Showing 10 vetted skills indexed across 1 GitHub repositories.
escalation-and-reply-tone
Determines when support tickets require human review and guides first-reply tone.
ticket-routing-playbook
Assigns owning teams and priority levels to inbound support tickets.
release-digest
Generate and post a Slack recap of merged PRs since the last release tag.
claude-maintain-models
Add new LLM models to Kiln's ml_model_list.py and open a tested pull request.
qa
Orchestrates multi-agent browser-driven QA passes over branches and PRs with severity-ranked reports.
playwright
Drive Kiln's web UI in a real browser and run its Playwright end-to-end test suite.
kiln-check-finetune-deprecation
Audit Kiln's fine-tunable model list for deprecated or unsupported base models across providers.
kiln-prerelease-check
Runs Kiln prerelease smoke tests and CI checks, then diagnoses failures into a report.
kiln-check-deprecation
Audit Kiln's model list for deprecated or sunset models across all providers.
kiln-add-model
Add LLM models to Kiln's registry and draft Discord release posts.
Frequently Asked Questions About Kiln AI
FAQPage SchemaWhat specific tasks does Kiln AI enable for model management?▼
Kiln AI enables the registration of new models into a centralized registry and facilitates the drafting of release announcements. It streamlines the process of tracking model updates and communicating these changes directly to Discord community members.
Which personas benefit most from using these registry capabilities?▼
Product managers, community leads, and technical engineers managing model lifecycles benefit from these capabilities. It is designed for teams that prioritize rapid model iteration and require consistent, timely communication with their user base on Discord.
What are the prerequisites for integrating new models into the registry?▼
To integrate models, users must have access to the Kiln registry interface and the necessary model metadata. The process requires defining the model specifications within the registry to enable the subsequent generation of release documentation.