Stats
Actions
Tags
Expert guidance for turning the DevOpser self-evolving software template into a real product. Covers the two chat surfaces (stateless `/` preview vs stateful `/chat`), the publicPaths route-visibility rule, adding a fourth LLM provider, and productization patterns from DevOpser Lite / Fairytale Genie / Language Bazaar / Stores. Triggers on "edit the chat system prompt", "add a /pricing page", "add Mistral as a provider", "build something like Fairytale Genie", "my endpoint 302s to /auth/login".
How this skill is triggered — by the user, by Claude, or both
Slash command
/devopser-agent-skills:devopser-customizeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Expert guidance for reshaping the template into an actual product. The deliberately-left-blank spots — **your actual product**, deployment target, billing — are where forkers spend most of their time; this skill covers the first of the three. Canonical playbook: [`AGENTS.md`](../../AGENTS.md) → **"Core extension points"**, **"The two chat surfaces"**, and **"Public vs authenticated routes"**.
Expert guidance for reshaping the template into an actual product. The deliberately-left-blank spots — your actual product, deployment target, billing — are where forkers spend most of their time; this skill covers the first of the three. Canonical playbook: AGENTS.md → "Core extension points", "The two chat surfaces", and "Public vs authenticated routes".
| Rule | Description |
|---|---|
| chat-surfaces | The critical distinction: / stateless preview vs /chat stateful multi-turn |
| public-routes | The publicPaths array in backend/server.js is the single source of truth for anonymous access |
| llm-providers | Adding a fourth provider to backend/services/llm/; the Converse-API caveat |
| productize | How Lite / Fairytale Genie / Language Bazaar / Stores were built on this template |
| troubleshooting | Expanded troubleshooting — Bedrock access, MFA expiry, harmless warnings |
AGENTS.md. If this skill contradicts it, AGENTS.md wins — report the contradiction to DevOpser./ (landing / signup funnel / anonymous preview) or /chat (authenticated multi-turn product)?" — never guess. See chat-surfaces.md.NODE_ENV === 'production', never on feature flags or fork-specific files.publicPaths in backend/server.js:411. Missing the second step is the most common self-inflicted bug.| Situation | Go to |
|---|---|
| "Change the chat system prompt" (which chat?) | chat-surfaces.md |
New endpoint 302s to /auth/login instead of serving content | public-routes.md |
| Add Mistral / Cohere / Together.ai / local vLLM | llm-providers.md |
| "Make this a Fairytale Genie / Language Bazaar clone" | productize.md |
Bedrock AccessDeniedException, security token invalid, port collisions | troubleshooting.md |
If AGENTS.md contradicts this skill, AGENTS.md wins — report the contradiction to DevOpser.
npx claudepluginhub devopser-io/self-evolving-software-template --plugin devopser-agent-skillsProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.