agent-v3-memory-specialist

Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist

1.77x

Quality

35%

Does it follow best practices?

Impact

85%

1.77x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-v3-memory-specialist/SKILL.md

Quality

Content

50%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 substantial, well-sectioned design document with concrete parameters and a phased migration plan, but it relies on non-executable code skeletons, lacks inline validation for a destructive batch migration, and inlines everything rather than progressively disclosing detail to reference files.

Suggestions

Add inline validation checkpoints to each migration phase (e.g. verify source vs. destination row counts and run a sample query before proceeding to the next backend), since this is a destructive batch operation.

Replace TypeScript class skeletons and pseudocode with minimal executable snippets, or move full implementations into separate reference files and link to them from the overview.

Split detailed code, SQL migration, and benchmark sections into reference files (e.g. MIGRATION.md, BENCHMARKS.md) and link from SKILL.md, and remove the decorative ASCII diagrams and de-duplicated '150x-12,500x' claims to tighten tokens.

Dimension	Reasoning	Score
Conciseness	The body is mostly domain-specific technical content rather than basic-concept explanation, but it is padded with decorative ASCII box diagrams and repeats '150x-12,500x' roughly six times, fitting 'mostly efficient but includes some unnecessary padding that could be tightened'; not severe enough for a 2.	3 / 5
Actionability	Code is structurally concrete (specific HNSW params efConstruction:200, M:16, SQL queries) but the TypeScript classes are non-executable skeletons referencing undefined types and unimplemented methods, matching 'some concrete guidance but incomplete; pseudocode instead of executable code'.	3 / 5
Workflow Clarity	Migration is sequenced into Phase 1-3 by week, but the phases are high-level bullet directives with no inline validation checkpoints; per the rubric, a destructive/batch data migration missing validation steps caps workflow clarity at 3, and the end-state 'Success Criteria' checklist does not supply inline checkpoints.	3 / 5
Progressive Disclosure	Section headers provide structure, but ~318 lines of detailed TypeScript, SQL migration, and benchmark code are all inlined in SKILL.md with no references to separate files; this fits 'some structure but content that should be separate is inline', and no bundle files exist to offset it.	3 / 5
	Total	12 / 20 Passed

Description

21%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 a templated label rather than a capability statement: it names the domain but describes no actions, includes no natural trigger phrases, and lacks any 'Use when...' guidance. It is distinguishable mainly by its internal codename, not by what it does.

Suggestions

Replace the label with concrete third-person actions, e.g. 'Unifies 7 memory systems into AgentDB with HNSW indexing, migrates legacy backends, and benchmarks search performance.'

Add an explicit 'Use when...' clause with natural trigger phrases users would say, e.g. 'Use when consolidating memory backends, migrating data to AgentDB, or improving vector search performance.'

Drop the invocation-syntax token ('$agent-v3-memory-specialist') from the description; it is not a natural trigger term.

Dimension	Reasoning	Score
Specificity	The phrase "Agent skill for v3-memory-specialist" names a specific domain but states no concrete actions at all, fitting the anchor 'names the domain but actions are minimal or generic'; it is above a purely vague label yet below anchor 3 which requires 1-2 concrete actions.	2 / 5
Completeness	It offers a vague 'what' ("Agent skill for v3-memory-specialist") and no real 'when' — "invoke with $agent-v3-memory-specialist" is invocation syntax, not a use-trigger, matching 'has a vague what and no when'; the missing 'Use when...' clause also caps completeness at 3, and this is below that.	2 / 5
Trigger Term Quality	The only terms are the internal codename "v3-memory-specialist" and the invocation token "$agent-v3-memory-specialist"; these are technical jargon/syntax a user would never naturally say, matching the anchor 'no natural keywords; only technical jargon'.	1 / 5
Distinctiveness Conflict Risk	The unique codename "v3-memory-specialist" and its invocation token reduce conflict risk, but the templated 'Agent skill for X - invoke with $X' phrasing provides no behavioral distinctiveness and could overlap with similarly-named agent skills, fitting 'somewhat specific but could still overlap'.	3 / 5
	Total	8 / 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: ruvnet/ruflo
Path: .agents/skills/agent-v3-memory-specialist/SKILL.md
Commit: fa13ee4

Reviewed: about 4 hours 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.