layered-recall
From the author
Progressive memory recall with 4 scope layers AND 3 depth layers. Scope: identity > project > room > deep. Depth: IDs only > summary > full. 10-50x token savings through fetch-on-confirmation pattern.
Install
npx skills add vibeeval/vibecosystem --skill layered-recall -a claude-code
Installs to .claude/skills/layered-recall/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
Want your agent to suggest skills while you type? See how to use skills from your IDE.
Safety checks on SKILL.md
No warnings.
Why 84
aiqbench computes the trust score from public signals. It is not a security audit, so read a skill before you install it.
Similar skills
Closest to this one by what they do and when they are used.
- folded-memory-implementationsimbajigege/book2skillsDeveloper implementation guide for building hierarchical (folded) memory into an Agent. Three-layer architecture where recent turns stay detailed, older content compresses into episodes, and the oldest distills into durable semantic facts. Use when compact-memory-implementation is not retaining enough, or when agents need to recall decisions from many sessions ago.Productivity★ 198
- cm-skill-indextody-agent/codymasterProgressive Disclosure skill index — efficient skill loading in 3 layers. Layer 1 (index, ~100 tokens) always loaded. Layer 2 (summary, ~300 tokens) loaded on context need. Layer 3 (full SKILL.md) loaded on execution only.Productivity★ 56
- agent-recallskillmds/skillmdPersistent compounding memory for AI agents. 5 default MCP tools: session_start, session_end, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (session_start) and exhale (session_end). Correction-first memory with decision trail tracking, watch_for warnings, palace rooms with salience scoring, cross-project insight matching, same-day journal merging, ambient recall hooks. Local markdown only. Zero cloud, zero telemetry, Obsidian-compatible. Optional Supabase backend: when configured via `ar setup supabase`, recall() uses pgvector cosine similarity on OpenAI/Voyage embeddings instead of keyword search — same API, semantic understanding. Gracefully degrades to local search if not configured.Engineering★ 191
- memory-systemwasintoh/toh-frameworkTiered, low-token project memory protocol for .toh/memory/ — 7 files across 3 tiers (Tier 1 active.md + summary.md always read, ~800 tokens; Tier 2 architecture/components for build work and changelog for debug work; Tier 3 decisions/agents-log only on demand). Auto-saves after task completion with zero user effort; delegated agents receive context from the orchestrator instead of re-reading. Use at every session start and whenever loading or saving project memory or resuming context across sessions and IDEs.Productivity★ 98
- total-recallskillmds/skillmdThe only memory skill that watches on its own. No database. No vectors. No manual saves. Just an LLM observer that compresses your conversations into prioritised notes, consolidates when they grow, and recovers anything missed. Five layers of redundancy, zero maintenance. ~$0.00/month (using free-tier models). While other memory skills ask you to remember to remember, this one just pays attention.Data★ 191
- recalldavepoon/buildwithclaudeSearch Origin's local memory by query. Targeted lookup, not orientation. Invoked as `/recall <query>`. Use when the user asks "do you remember", "what do you know about", "look up".Productivity★ 3.7K
Ratings & reviews
—
no reviews
Tried this skill? Rate it to help others. Sign in
Discussion
Join the discussion. Sign in