Mem Search Skill for Claude
Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/thedotmack/claude-mem --skill mem-searchThe instruction itself
9 sections, as written by the authorMemory Search
Search past work across all sessions. Simple workflow: search -> filter -> fetch.
When to Use
Use when users ask about PREVIOUS sessions (not current conversation):
- "Did we already fix this?"
- "How did we solve X last time?"
- "What happened last week?"
3-Layer Workflow (ALWAYS Follow)
NEVER fetch full details without filtering first. 10x token savings.
Step 1: Search - Get Index with IDs
Use the search MCP tool:
search(query="authentication", limit=20, project="my-project")
Returns: Table with IDs, timestamps, types, titles (~50-100 tokens/result)
| ID | Time | T | Title | Read |
|----|------|---|-------|------|
| #11131 | 3:48 PM | 🟣 | Added JWT authentication | ~75 |
| #10942 | 2:15 PM | 🔴 | Fixed auth token expiration | ~50 |
Parameters:
query(string) - Search termlimit(number) - Max results, default 20, max 100project(string) - Project name filtertype(string, optional) - "observations", "sessions", or "prompts"obs_type(string, optional) - Comma-separated: bugfix, feature, decision, discovery, changedateStart(string, optional) - YYYY-MM-DD or epoch msdateEnd(string, optional) - YYYY-MM-DD or epoch msoffset(number, optional) - Skip N resultsorderBy(string, optional) - "date_desc" (default), "date_asc", "relevance"
Step 2: Timeline - Get Context Around Interesting Results
Use the timeline MCP tool:
timeline(anchor=11131, depth_before=3, depth_after=3, project="my-project")
Or find anchor automatically from query:
timeline(query="authentication", depth_before=3, depth_after=3, project="my-project")
Returns: depth_before + 1 + depth_after items in chronological order with observations, sessions, and prompts interleaved around the anchor.
Parameters:
anchor(number, optional) - Observation ID to center aroundquery(string, optional) - Find anchor automatically if anchor not provideddepth_before(number, optional) - Items before anchor, default 5, max 20depth_after(number, optional) - Items after anchor, default 5, max 20project(string) - Project name filter
Step 3: Fetch - Get Full Details ONLY for Filtered IDs
Review titles from Step 1 and context from Step 2. Pick relevant IDs. Discard the rest.
Use the get_observations MCP tool:
get_observations(ids=[11131, 10942])
ALWAYS use get_observations for 2+ observations - single request vs N requests.
Parameters:
ids(array of numbers, required) - Observation IDs to fetchorderBy(string, optional) - "date_desc" (default), "date_asc"limit(number, optional) - Max observations to returnproject(string, optional) - Project name filter
Returns: Complete observation objects with title, subtitle, narrative, facts, concepts, files (~500-1000 tokens each)
Examples
Find recent bug fixes:
search(query="bug", type="observations", obs_type="bugfix", limit=20, project="my-project")
Find what happened last week:
search(type="observations", dateStart="2025-11-11", limit=20, project="my-project")
Understand context around a discovery:
timeline(anchor=11131, depth_before=5, depth_after=5, project="my-project")
Batch fetch details:
get_observations(ids=[11131, 10942, 10855], orderBy="date_desc")
Why This Workflow?
- Search index: ~50-100 tokens per result
- Full observation: ~500-1000 tokens each
- Batch fetch: 1 HTTP request vs N individual requests
- 10x token savings by filtering before fetching
Knowledge Agents
Want synthesized answers instead of raw records? Use /knowledge-agent to build a queryable corpus from your observation history. The knowledge agent reads all matching observations and answers questions conversationally.
Other skills for the same job
different authors, same section of the catalogue
Build agent-facing web experiences with ATXP-based authentication, following the ClawDirect pattern. Use this skill when building websites that AI agents interact with via MCP tools, implementing cookie-based agent auth, or creating agent skills for web apps. Provides templates using @longrun/turtle, Express, SQLite, and ATXP.
Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use as a fallback when LangSmith trace tooling is unavailable, for offline or untraced sessions, or when asked to identify or summarize a local dcode thread, inspect checkpoint metadata, list recent local threads, or parse ~/.deepagents/.state/sessions.db and a thread UUID or prefix.
Use when you need state across calls — building env vars, navigating with cd, driving REPLs (python -i, mysql, psql, node), or responding to interactive prompts (sudo password, ssh host-key confirmation, mysql connection). Teaches the prompt-sentinel exec pattern (default mode), raw I/O for REPLs (raw_send=True then read_only=True), the one-in-flight-per-session rule, and the close-or-leak-against-the-cap discipline. Bash on macOS — never zsh; explicit shell=/bin/zsh is rejected. Read before calling terminal_pty_open.
Help developers build third-party tools that import, inspect, migrate, or analyze DeepChat data. Use when Codex needs to work with DeepChat provider configuration, model configuration, MCP/app settings, sessions, messages, legacy chat data, `agent.db`, `chat.db`, SQLCipher encrypted SQLite, Electron safeStorage wrapped passwords, Tauri importers, or native macOS/Windows/Linux data access.
统一管理多智能体角色的团队协作框架，支持智能体动态组合、灵活协作和扩展新角色。智能体本质上是"角色定义"，可以根据任务需求灵活组建团队，实现从会议决策到系统构建的完整能力。智能体角色明确分工：有干活的、有指挥的、有挑毛病的，能实时看到沟通过程，共享数据库记忆，确保上下文一致。
Query the memory system for relevant learnings from past sessions
>- Corrects speech-to-text transcription errors using dictionary rules and Claude's built-in AI (no external API key required — Native AI Correction is the DEFAULT). Stage 3 API is a backup for automation without Claude Code. Builds personalized correction databases that learn from each fix, auto-loads person-name ASR variants from your people roster, and reads per-domain context files that prime the AI pass for context-dependent homophones. Triggers when working with ASR/STT output containing recognition errors, homophones, garbled technical terms, person-name errors, or Chinese/English mixed content. Also triggers on requests to clean up meeting notes, lecture transcripts, interview recordings, or any text produced by speech recognition. Use this skill even when the user just says "fix this transcript", "clean up these meeting notes", or mentions garbled names without invoking ASR specifically.
>- recon (find unsafe SQL construction sites), batched verify (trace user input to those sites in parallel subagents, 3 sites each), and merge (consolidate batch results). Covers string concat, f-strings, unsafe ORM methods, and dynamic identifiers. Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/sqli-results.md. Use when asked to find SQLi or database injection bugs.
How to use it
Take thedotmack/mem-search from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.