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.

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 content is well-structured and action-oriented with executable commands and a clear retrieval workflow. Its main weakness is minor verbosity in the framing/advice lines that restate Claude's existing competence.

Suggestions

Drop generic guidance Claude already follows, e.g. "Be concise — only include information that is genuinely useful for the user's current question," to tighten token efficiency.

Reframe the implicit "Evaluate" step as an explicit validation checkpoint (e.g. "Stop if all results are irrelevant before expanding") to lift workflow clarity.

Replace the opening "You are a memory retrieval agent... Your job is to..." preamble with a one-line purpose statement to reduce padding.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-driven, but a few lines restate what Claude already knows ("Be concise — only include information that is genuinely useful for the user's current question") and the opening "Your job is to..." is mild padding that could be trimmed.	4 / 5
Actionability	Provides concrete, executable commands with specific flags (e.g. `memsearch search "<query>" --top-k 5 --json-output --default-collection <collection>`, `memsearch expand <chunk_hash> ...`, `parse-transcript.py ... --turn <turn_id> --context 3`) plus the `uvx memsearch` fallback; minor gaps remain around runtime substitution of the collection name.	4 / 5
Workflow Clarity	A clear five-step sequence (Search → Evaluate → Expand → Deep drill → Return) with an explicit "Evaluate" filtering checkpoint and fallback branches in the deep-drill step; the operation is read-only so the destructive/batch validation cap does not apply, but checkpoints are implicit rather than framed as validation.	4 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the body is a self-contained ~50 lines organized into well-labeled sections (Project Collection, Your Task, Steps, When unsure what to search, Output Format), satisfying the simple-skill exception for well-organized single-file content.	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.

The description is strong: third-person voice, concrete actions, natural trigger phrases, explicit what/when guidance, and well-bounded scope with skip conditions. It is a model of a complete, distinct, action-oriented skill description.

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" — covering the full retrieval flow with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ("Search and recall relevant memories from past sessions via memsearch" with the search/expand/drill flow) and when ("Use when the user's question could benefit from historical context..." plus the SessionStart/UserPromptSubmit hint trigger), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users actually say — "what did I decide about X", "why did we do Y", "have I seen this before" — plus synonyms like "past decisions", "debugging notes", "previous conversations".	5 / 5
Distinctiveness Conflict Risk	Clear niche (memsearch memory recall) with distinct triggers; the explicit skip conditions ("purely about current code state (use Read/Grep)") sharply bound it against overlap 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/opencode/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.