Menú
Manage project memory — add, list, prune cross-session knowledge. Use when asked to remember conventions, gotchas, or decisions.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
| name | Qmemory |
| description | Manage project memory — add, list, prune cross-session knowledge. Use when asked to remember conventions, gotchas, or decisions. |
| user_invocable | true |
| recommendedModel | haiku |
Manages .qe/project-memory.json for persistent cross-session knowledge. Stores conventions, gotchas, decisions, and patterns with TTL-based expiry.
/Qmemory add "content" [--type TYPE] [--priority PRIORITY] [--tags tag1,tag2]Add a memory entry.
convention | gotcha | decision | pattern (default: convention)permanent | high | normal | low (default: normal)TTL by priority:
| Priority | TTL |
|---|---|
| permanent | never expires |
| high | 30 days |
| normal | 7 days |
| low | 1 day |
/Qmemory list [--type TYPE] [--tag TAG]List active (non-expired) memories. Optionally filter by type or tag. Display as a table with id, type, priority, content, and expiry.
/Qmemory pruneRemove expired entries. Report how many were pruned.
/Qmemory clearClear all entries. Confirm with the user before executing.
Extract the subcommand (add, list, prune, clear) and any flags from the user input.
Use hooks/scripts/lib/project-memory.mjs functions:
addMemory(cwd, content, type, { priority, source: 'user', tags }). Print the created entry.getActiveMemories(cwd), or getMemoriesByType/getMemoriesByTag if filtered. Display as a formatted table.pruneExpired(cwd). Report count.clearAll(cwd).Show a concise confirmation or table. No verbose explanations.
.qe/analysis/ files (those are for codebase structure)Project memory: {count} active entries ({permanent} permanent, {expiring} expiring)
Use when collecting verified project-local coding guidance into .claude/skills based on the project tech stack, with TTL and user-edit protection.
Shows QE Framework usage overview. With no arg, prints the full catalog. With a skill name arg (e.g., /Qhelp Qcommit), reads that skill's SKILL.md and summarizes it in the user's language. Also supports find/search skills mode via reference/find-skills.md.
QE framework (Query Executor) initial setup. Creates the QE state directory, client-specific instruction/config artifacts, and .gitignore entries in a new project, then auto-analyzes the project. Use when the user wants to initialize a project or set up the framework.
Diagnoses and repairs QE installation health across qe-framework, MCP client config, and the project .qe directory. Use for 'doctor', 'check QE health', dependency verification, corrupted .qe state, or repair guidance. Distinct from Qupdate, which updates installed assets.
Use when executing a TASK_REQUEST/VERIFY_CHECKLIST or when already-changed code needs the test-review-fix quality loop. With no flag it auto-selects sequential or parallel-wave execution; `-verify` runs verification. Use Qautoresearch for iterative code-optimization loops and Qscenario-test for scenario/E2E.
Use when a plan or task needs spec documents: TASK_REQUEST and VERIFY_CHECKLIST. Use Qplan for roadmap/phases; use Qexecute after the spec exists.