OpenSkillIndex← back to search
claude-codedevops

Claude-skill-registry lcp-openai-serve

Develop apps/openai-serve (Go). Keep OpenAI gateway behavior correct and avoid logging prompts/outputs.

install
source · Clone the upstream repo
git clone https://github.com/majiayu000/claude-skill-registry
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/lcp-openai-serve" ~/.claude/skills/majiayu000-claude-skill-registry-lcp-openai-serve && rm -rf "$T"
manifest: skills/data/lcp-openai-serve/SKILL.md
tags
#api-gateway#model-serving#openai-compat#http-server#go-lang
source content

You are working on the OpenAI-compatible HTTP gateway in 

apps/openai-serve/
.

Scope

  • Module: 
    apps/openai-serve/
  • Runtime contract: 
    apps/openai-serve/README.md

Development principles

These are the consolidated rules that previously lived in 

apps/openai-serve/AGENTS.md
:

  1. Design for robustness. Keep modules aligned with SRP.
  2. Use a ubiquitous language. Keep terminology consistent across code and docs.
  3. Test-first. Prefer TDD when changing behavior.
  4. Run golangci-lint v2. When changing code, run 
    make lint
    and fix findings.
  5. Use 
    cmp.Diff
    in tests. Compare expected vs actual with 
    github.com/google/go-cmp/cmp.Diff
    .
  6. Make logging diagnosable. Logging level MUST be configurable (for example via env vars).
  7. Prefer lnd libraries. Use lnd-provided APIs/libraries before re-implementing.

Non-negotiables

  • Logging is sensitive: do not log raw prompts (
    messages[].content
    ) or raw model outputs.
  • Keep behavior stable and explicit: JSON decoding is strict, unsupported fields must be rejected as documented.

Workflow

  1. Read 
    apps/openai-serve/README.md
    before changing behavior.
  2. When adding config/env vars, document them in 
    apps/openai-serve/README.md
    and keep defaults sane.
  3. When changing request/response structures, update tests and ensure the documented constraints still hold.

Validation (run from 
apps/openai-serve/
)

  • make test
  • make lint
  • make fmt