菜单
First-time setup or upgrade for the learning-loop plugin. Configures vault path, persona voice, CLAUDE.md integration, and verifies the installation. Hands federation off to /learning-loop:federation. Safe to re-run: detects existing state and skips completed steps.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | init |
| description | First-time setup or upgrade for the learning-loop plugin. Configures vault path, persona voice, CLAUDE.md integration, and verifies the installation. Hands federation off to /learning-loop:federation. Safe to re-run: detects existing state and skips completed steps. |
| disable-model-invocation | true |
Eight-phase detect-confirm-apply flow. One question at a time. Safe to re-run: detects existing state and skips completed steps.
All operations use Node.js APIs (fs, path, child_process). No bash find, no shell globbing for detection.
Resolve PLUGIN_DATA, VAULT, and the plugin root per ${CLAUDE_PLUGIN_ROOT}/skills-shared/paths-preamble.md (read it and apply). Use those resolved values for ALL path references in the phase files.
Read each phase file in order and execute its instructions. After Phase 1's dashboard, only enter the phases the dashboard reports as needing work.
${CLAUDE_PLUGIN_ROOT}/skills/init/phases/01-detect.md -- detect state, present dashboard. If everything is configured, stop here.${CLAUDE_PLUGIN_ROOT}/skills/init/phases/02-vault.md -- vault path, folders, system files.${CLAUDE_PLUGIN_ROOT}/skills/init/phases/03-binary.md -- binary, vendor deps, orphan cleanup, index, shims, plugin deps.${CLAUDE_PLUGIN_ROOT}/skills/init/phases/04-federation.md -- single yes/no, hands off to /learning-loop:federation for the full flow.${CLAUDE_PLUGIN_ROOT}/skills/init/phases/05-claudemd.md -- CLAUDE.md integration.${CLAUDE_PLUGIN_ROOT}/skills/init/phases/06-cache-health.md -- optional cache-health statusline.${CLAUDE_PLUGIN_ROOT}/skills/init/phases/07-librarian.md -- optional librarian background agent (incl. 7d: optional GLM Verify-offload provider for /learning-loop:research).${CLAUDE_PLUGIN_ROOT}/skills/init/phases/08-seed-restore.md -- restore a seed bundle if present and seed the harvest deny-list.After all phases complete, present the summary below.
Learning loop configured.
Vault: [path] ([N] notes)
Folders: [N]/7 present
Binary: ll-search vX.Y
Search: [N] notes indexed
Federation: [configured | deferred to /learning-loop:federation | not requested]
CLAUDE.md: [status]
Cache health: [installed | skipped: oh-my-claude not found]
Librarian: [enabled | skipped: ollama/hardware not available]
Seed restore: [restored from bundle | no bundle present]
Harvest list: [seeded | empty (personal instance)]
Shims: ll-watch + ll-search installed in ~/.local/bin
Start the watcher with: ll-watch
Run /learning-loop:help to see available commands.
find, no shell globbing.Deep research with the local librarian doing the token-heavy middle. Scope on Claude, Search+Fetch+Extract on the local Ollama model, adversarial Verify + Synthesize back on Claude. Usage: /learning-loop:research "<question>". Falls back to Claude-native WebSearch when the librarian is unavailable or sub-tier.
End-of-session consolidation. Usage: /learning-loop:reflect (no args). Reviews conversation, extracts learnings, routes to auto-memory or vault, cross-links projects, promotes inbox notes. Run after substantial work sessions.
measure whether a /dream pass helps, hurts, or ties against no consolidation. usage: /learning-loop:dream-eval --mode={single|control|repeated} [--passes=N] [--mine]. single scores pre/post on the live corpus; control forks two clones and dreams one; repeated dreams a clone N times and plots the drift + content-survival curve.
Consolidate auto-memory between sessions. Usage: /learning-loop:dream (no args). Four-phase cycle: Orient, Gather Signal, Consolidate, Prune Index. Seven operators: MERGE, RESOLVE, ABSTRACT, COMPRESS, PRUNE, LINK, DATE NORMALIZE. Rebuilds MEMORY.md.
Cross-store correction for a retracted or updated belief. Usage: /learning-loop:rewrite "old pattern" "new pattern" [reason]. Searches vault, auto-memory, and episodic history; presents an impact map for triage; executes user-approved changes; records a supersession so future episodic searches get annotated.
Diagnose your learning-loop installation. Runs health checks, presents issues, offers per-fix remediation, re-runs each check after the fix to confirm. Safe to run anytime; only makes changes you approve. Pass --redact to scan plugin data files for leaked credentials instead.