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

91%

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

92%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, highly actionable agent prompt: every step carries an exact command with flags, fallbacks, and error-recovery paths, and the workflow is clearly sequenced with explicit evaluation criteria. Its only weakness is minor repetition of the uvx fallback and the MDIR fallback expression that could be tightened.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes competence, but contains minor trimmable repetition: the 'If memsearch is not found, try uvx memsearch' fallback is stated twice and the MDIR="${MEMSEARCH_DIR:-...}" fallback expression is repeated verbatim three times in the 'When unsure' section, matching anchor 4 ('minor instances of over-explanation that could be trimmed') rather than 5.	4 / 5
Actionability	Fully executable, copy-paste-ready commands with concrete flags and placeholders: 'memsearch search "<query>" --top-k 5 --json-output --default-collection', 'memsearch expand <chunk_hash>', 'memsearch transcript <jsonl_path> --turn <uuid> --context 3', plus concrete exploratory ls/grep/cat commands and an automated collection-derivation snippet.	5 / 5
Workflow Clarity	A clear five-step sequence (Search, Evaluate, Expand, Deep drill, Return) with explicit evaluation criteria ('Skip chunks that are clearly irrelevant or too generic') and error-recovery fallbacks (uvx fallback; unrecognized transcript format or unfamiliar anchor format falls back to reading the file directly). Operations are read-only, so the destructive/batch validation cap does not apply.	5 / 5
Progressive Disclosure	A ~43-line single-purpose skill with no need for external references, organized into clear sections (Project Collection, Your Task, Steps, When unsure, Output Format); per the rubric's simple-skill guideline this earns a 5 with well-organized sections alone. No bundle files exist and none are referenced.	5 / 5
	Total	19 / 20 Passed

Description

91%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 description: it states concrete tool-specific actions, provides rich natural-language trigger phrases including example questions users would ask, and adds both positive ('Use when') and negative ('Skip when') trigger guidance. The only minor gaps are slight overlap risk with generic memory skills and capability coverage conveyed through flow steps rather than an explicit enumeration.

Dimension	Reasoning	Score
Specificity	Names the tool and several concrete actions ('Search and recall relevant memories from past sessions via memsearch', 'search for 3-5 chunks, expand the most relevant, optionally deep-drill into original transcripts'), but the action list leans on workflow flow rather than a comprehensive enumeration of capabilities, matching anchor 4 rather than 5.	4 / 5
Completeness	Explicitly answers both what ('Search and recall relevant memories from past sessions via memsearch') and when, with a concrete 'Use when...' clause, a capability-hint trigger, and a complementary 'Skip when...' exclusion clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural trigger phrases comprehensively, including synonyms and example questions users would actually say: 'past decisions', 'debugging notes', 'previous conversations', 'project knowledge', and "'what did I decide about X', 'why did we do Y', or 'have I seen this before'", matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	The 'via memsearch' tool binding and the specific '[memsearch] Recall available if needed' capability-hint trigger establish a clear niche, but 'recall memories'/'historical context' phrasing carries minor overlap risk with generic memory-lookup skills, matching anchor 4.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: zilliztech/memsearch
Path: plugins/claude-code/skills/memory-recall/SKILL.md
Commit: 2a4652f

Reviewed: 6 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.