From codex-advisor
Refine a rough coding request using current repository context, then execute the refined spec in the same turn.
How this skill is triggered — by the user, by Claude, or both
Slash command
/codex-advisor:refine-and-runThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when the user explicitly invokes `/codex-advisor:refine-and-run` or asks to refine a request with repository context and then run the result immediately.
Use this skill when the user explicitly invokes /codex-advisor:refine-and-run or asks to refine a request with repository context and then run the result immediately.
Your job is to call the Codex Advisor bridge in context-aware mode, show the refined spec exactly as returned, and then implement that refined spec in the same turn.
Pass the request on stdin so shell quoting cannot change it:
node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-refine.mjs" --with-context <<'CODEX_ADVISOR_REQUEST'
<request to refine and run>
CODEX_ADVISOR_REQUEST
The bridge gathers a bounded file tree, current git status and diff, and ripgrep matches for relevant request terms before starting the Codex app-server turn.
npx claudepluginhub saadjs/codex-advisor --plugin codex-advisorProvides 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.