recall

Search agentmemory for past observations, sessions, and learnings about a topic using hybrid BM25 plus vector plus graph search. Use when the user says "recall", "what did we do about", "did we ever", "have we seen", or needs context from past sessions.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%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.

A tight, actionable body for a simple read-only skill: concrete tool call, clear sequenced workflow with edge-case handling, and a useful anti-pattern. The only blemishes are a partly redundant checklist and a dangling shared-file reference.

Suggestions

Resolve or remove the dangling ../_shared/TROUBLESHOOTING.md reference (the file does not exist in the bundle) so progressive disclosure can score full marks.

Collapse the Checklist into the Workflow (or trim it to only items not already stated as steps) to remove the conciseness redundancy.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanation of what memory or search is), but the Checklist section restates the Workflow and Why sections, so a minor instance of padding could be trimmed.	4 / 5
Actionability	"memory_smart_search { \"query\": \"...\", \"limit\": 10 }" with a concrete expected-output block, plus workflow steps specifying exact params (limit: 10, importance >= 7), is copy-paste-ready and covers the common cases.	5 / 5
Workflow Clarity	This is a simple single-action skill (call one tool) with an unambiguous 5-step sequence, an explicit zero-results edge-case branch, and a closing checklist; the simple-skill exception applies and the sequence is fully clear.	5 / 5
Progressive Disclosure	Sections are well-organized and the See-also links to sibling skills are appropriate, but the Troubleshooting reference to ../_shared/TROUBLESHOOTING.md does not resolve to a real file, a minor navigation gap that keeps it off anchor 5.	4 / 5
	Total	18 / 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: third-person voice, concrete what-and-when, and excellent natural trigger phrases. The only soft spot is a slightly broad "needs context from past sessions" clause that invites overlap with sibling session skills.

Suggestions

Tighten the trailing trigger "or needs context from past sessions" to something more specific (e.g. "or asks what was previously decided or observed about a topic") to reduce overlap with recap/handoff/session-history.

Consider naming one or two more concrete output actions (e.g. "groups results by session and surfaces high-importance records") to lift specificity from broad single-action to multi-action coverage.

Dimension	Reasoning	Score
Specificity	"Search agentmemory for past observations, sessions, and learnings ... using hybrid BM25 plus vector plus graph search" names the domain and several concrete facets (observations, sessions, learnings, three search modes), but it is essentially a single search action rather than the broad multi-action coverage of the anchor-5 example.	4 / 5
Completeness	It explicitly states what the skill does (search agentmemory for past observations/sessions/learnings via hybrid search) and when to use it (concrete trigger phrases plus "needs context from past sessions"), satisfying both halves of the anchor-5 example.	5 / 5
Trigger Term Quality	"Use when the user says 'recall', 'what did we do about', 'did we ever', 'have we seen'" are natural phrases a user would actually say, with strong synonym coverage, matching the comprehensive anchor-5 example.	5 / 5
Distinctiveness Conflict Risk	The quoted triggers ("did we ever", "have we seen") carve a clear niche, but "or needs context from past sessions" is broad enough to overlap with closely related session skills (recap, handoff, session-history), so it is mostly distinct with minor overlap risk rather than minimal.	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: rohitg00/agentmemory
Path: plugin/skills/recall/SKILL.md
Commit: 2d38daf

Reviewed: 1 day 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.