From project-long-memory
This packaged skill delegates to the canonical repository instructions in [`../../SKILL.md`](/Users/smac/codex-workspace/brain/project-long-memory/SKILL.md).
How this skill is triggered — by the user, by Claude, or both
Slash command
/project-long-memory:project-long-memoryThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This packaged skill delegates to the canonical repository instructions in [`../../SKILL.md`](/Users/smac/codex-workspace/brain/project-long-memory/SKILL.md).
This packaged skill delegates to the canonical repository instructions in ../../SKILL.md.
Treat the root SKILL.md as the source of truth for:
Minimal packaged entrypoints:
<skill-root>/scripts/codex_memory_workflow.sh summary-pane <project-root>
<skill-root>/scripts/codex_memory_workflow.sh work-on <project-root> --spec <spec-id> --task <task-id> --task-title "<task title>"
<skill-root>/scripts/codex_memory_workflow.sh checkpoint <project-root> --label "known-good"
<skill-root>/scripts/codex_memory_workflow.sh doctor <project-root>
<skill-root>/scripts/codex_memory_workflow.sh close <project-root>
Codex package metadata lives in .codex-plugin/plugin.json, but automatic runtime entry still depends on repo-local .codex/hooks.json.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub larryppgg/project-long-memory-skill --plugin project-long-memory