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] Recall available if needed` capability 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.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a lean, actionable retrieval workflow with concrete commands, clear sequencing, and sensible fallbacks for sandbox failures. Minor conciseness trims and resolving the __INSTALL_DIR__ placeholder would push it to fully copy-paste ready.

Suggestions

Replace or pre-resolve the __INSTALL_DIR__ placeholder so the project-collection command is directly executable, or document the substitution once at the top.

Tighten the deep-drill section's enumeration of unfamiliar anchor formats ('transcript: + turn:, db: instead of rollout:') into a brief parenthetical or move it to a reference file.

Consider extracting the long project-collection bash one-liner into the referenced derive-collection.sh invocation directly to reduce inline noise.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands throughout, but the inline project-collection bash one-liner and the deep-drill anchor-format explanation ('transcript: + turn:, db: instead of rollout:') could be trimmed slightly.	4 / 5
Actionability	Provides concrete, flag-level commands ('memsearch search "<query>" --top-k 5 --json-output --default-collection', 'memsearch expand <chunk_hash>') with fallbacks, but the '__INSTALL_DIR__' template placeholder requires install-time substitution rather than being copy-paste ready.	4 / 5
Workflow Clarity	Clear numbered sequence (Search → Evaluate → Expand → Deep drill → Return) with an Evaluate checkpoint and fallback error-handling for lock/permission and unrecognized-format cases; minor validation gaps but the skill is read-only so no destructive cap applies.	4 / 5
Progressive Disclosure	Well-organized into clearly labeled sections (Project Collection, Steps, When unsure what to search, Output Format) with content appropriately inline for a sub-50-line single-purpose skill and no nested reference chains.	5 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-crafted description that clearly states the skill's purpose, surfaces natural user trigger phrases, includes both positive and negative use conditions, and occupies a distinct niche. Third-person imperative voice is used correctly throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Search and recall relevant memories', 'search for 3-5 chunks, expand the most relevant, optionally deep-drill into original transcripts via the anchor format' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what ('Search and recall relevant memories from past sessions via memsearch') and when ('Use when the user's question could benefit from historical context...'), plus negative triggers ('Skip when the question is purely about current code state...').	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms ('historical context, past decisions, debugging notes, previous conversations, or project knowledge') and concrete user phrases ('what did I decide about X', 'why did we do Y', 'have I seen this before').	5 / 5
Distinctiveness Conflict Risk	Clear niche (memory recall via memsearch) with distinct triggers including the injected '[memsearch] Recall available if needed' capability hint, minimizing conflict with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zilliztech/memsearch
Path: plugins/codex/skills/memory-recall/SKILL.md
Commit: 3e98e4a

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.