Claude-skill-registry lcp-repo

Repository orientation and which Codex skills to use for each area (go-lcpd, protocol spec, docs, openai-serve, ExecPlans).

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 "$T/skills/data/lcp-repo" ~/.claude/skills/majiayu000-claude-skill-registry-lcp-repo && rm -rf "$T"

manifest: skills/data/lcp-repo/SKILL.md

Repository map (high level)

```
docs/protocol/
```
: LCP wire protocol spec (BOLT-style)
```
go-lcpd/
```
: reference implementation (daemon + tools)
```
apps/openai-serve/
```
: OpenAI-compatible HTTP gateway (forwards to
```
lcpd-grpcd
```
)
```
docs/
```
: Mintlify docs site

Which skill to use

Protocol spec edits: use
```
$lcp-protocol-spec
```
```
go-lcpd/
```
code changes: use
```
$lcp-go-lcpd
```
```
apps/openai-serve/
```
code changes: use
```
$lcp-openai-serve
```
Mintlify docs edits: use
```
$lcp-mintlify-docs
```
WYSIWID-style design docs in
```
go-lcpd/
```
: use
```
$lcp-wysiwid-spec
```
Complex feature/refactor planning: use
```
$lcp-execplan
```
Creating commits (only when asked): use
```
$lcp-git-commit
```

Default operating rule

If a directory has an

AGENTS.md

, treat it as a pointer to the authoritative skill(s) for that scope.