Claude-skill-registry gpt
Use GPT-5.2 for long-running coding tasks: large refactors, feature implementation etc.
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 "$T/skills/data/gpt" ~/.claude/skills/majiayu000-claude-skill-registry-gpt && rm -rf "$T"
manifest:
skills/data/gpt/SKILL.mdsource content
GPT-5.2 (via ocw)
Long-context coding. Best for: large refactors, feature implementation.
Prompt Guidelines
GPT strictly follows instructions. Provide as much high-level design context as possible:
- Architecture decisions, data flow, component responsibilities
- Constraints, edge cases, expected behaviors
Avoid:
- Contradictory requirements (GPT will struggle to reconcile conflicts)
- Code snippets — GPT writes code well on its own; use tokens for design info instead
Create Session (with worktree for code edits)
ocw new gpt --worktree
Returns:
- Line 1: 6-char hash
- Line 2: worktree path (e.g.,
)/path/to/ocw-abc123
The worktree is an isolated git branch. Work there freely.
Create Session (read-only, no worktree)
ocw new gpt
Chat
ocw chat <hash> << 'EOF' your prompt EOF
Chat with File
ocw chat <hash> -f /path/to/spec.md << 'EOF' implement based on this EOF
Worktree Workflow
→ get hash + pathocw new gpt --worktree- Work in worktree:
cd /path/to/ocw-{hash} - Edit, commit, push as needed
- When done:
git worktree remove /path/to/ocw-{hash}
List Sessions
ocw list