memory-search

Solid

Search memory by frontmatter fields, full-text keywords, or cross-reference graph. Returns ranked file list — never loads full content. Use when the agent needs to find relevant memory without knowing exact paths.

Data & Documents 155 stars 28 forks Updated 2 days ago NOASSERTION

Install

View on GitHub

Quality Score: 83/100

Stars 20%
73
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Memory Search ## Purpose / When to Activate Activate when an agent needs to **find** relevant memory but does not know the exact file path, domain, or DEC ID. This skill **locates** memory — it does not **load** it. After results are returned, the agent invokes `memory-retrieve` to load the specific files. Use cases: - "Which decisions relate to database connection pooling?" → Mode A (frontmatter: domain=infrastructure, tags contains database) - "Where did we discuss pool exhaustion?" → Mode B (full-text keyword: "pool exhaustion") - "What decisions are related to DEC-42?" → Mode C (cross-reference: DEC-42 → related_to + mentions) --- ## Process ### Mode A — Frontmatter Search Search YAML frontmatter fields across `decisions/DEC-*.md` files. 1. Accept query as field-value pairs: `{domain: "infrastructure", level: "operational"}` and/or `{tags: ["connection-pooling"]}` and/or `{related_to: ["<DEC-id>"]}` and/or `{status: "active"}` 2. Grep frontmatter blocks (between `---` delimiters) of all `decisions/DEC-*.md` files 3. Match files where ALL specified fields match (AND logic) 4. Extract `id`, `title`, and matched field values from each hit 5. Rank by: exact tag match > domain match > level match 6. Return top 10 results ### Mode B — Content Search Full-text keyword search across ALL memory files. 1. Accept query as 1-3 keywords (e.g., `"pool exhaustion"`, `"scoring formula"`) 2. Grep all files under `contexts/memory/` for keyword matches 3. For each hit, extract...

Details

Author
Fr-e-d
Repository
Fr-e-d/GAAI-framework
Created
5 months ago
Last Updated
2 days ago
Language
Shell
License
NOASSERTION

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

memory-retrieve

Load only the minimum relevant memory for a task using 3-level progressive disclosure. Activate before context-building — never load full memory dumps. Never substitute summaries for durable memory.

155 Updated 2 days ago
Fr-e-d
AI & Automation Listed

memory-search

Searches the project's recorded memory (core-memory-kit) — decisions, conventions, architecture, the reasoning behind choices, and where things live — and returns a curated, cited summary. Fire whenever the answer might be something the project already established in past work, HOWEVER the question is phrased — any prior decision, convention, rationale, or "how/where/why is it this way" question, including oblique or roundabout asks ("why is everything so spread out?", "remind me what we settled on for X", "how come these files are tiny?"). Also fire when a "[core-memory-kit] Memory available" hint appears on the prompt. The examples are illustrative, not a checklist — prefer recalling over re-deriving an answer from the code. The session-start snapshot is a bounded index; this skill reaches the rest. Skip only when the question is purely about uncommitted or just-edited live code that memory cannot know, concerns this conversation only, or the user asked to ignore memory.

4 Updated today
LH8PPL
AI & Automation Featured

memory-recall

Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this before'. Also use when you see `[memsearch] Memory available` hints injected via SessionStart or UserPromptSubmit. Typical flow: search for 3-5 chunks, expand the most relevant, optionally deep-drill into original transcripts via the anchor format. Skip when the question is purely about current code state (use Read/Grep), ephemeral (today's task only), or the user has explicitly asked to ignore memory.

2,391 Updated 3 days ago
zilliztech