agent-v3-memory-specialist

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

1.77x

Quality

25%

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%

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 dense, well-structured technical spec with real code and a phased migration plan, but it is verbose, leans on undefined/pseudocode constructs, and keeps all detail inline with no progressive disclosure. It lands at the middle anchor on every dimension.

Suggestions

Tighten the body by removing the ASCII art boxes, emoji decoration, and repeated 150x-12,500x restatements, and drop explanations of concepts Claude already knows (e.g. what HNSW/O(log n) is).

Make the code executable or explicitly justify the scaffolding: define or stub the referenced helpers (embedContent, retrieveEntries, generate_embedding) and fix the malformed "2>$dev$null" shell redirection.

Move the detailed migration plan, benchmark suite, and SONA integration into referenced bundle files (e.g. MIGRATION.md, BENCHMARKS.md) so SKILL.md becomes a concise overview with one-level-deep navigation.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete code and structured sections, but it is padded with decorative ASCII boxes, emoji-laden hooks, repeated "150x-12,500x" claims, and concept explanations (e.g. O(n) vs O(log n) HNSW) Claude already knows, fitting the "mostly efficient but could be tightened" anchor rather than the lean level-3 example.	2 / 3
Actionability	Substantial TypeScript/SQL is provided, but it depends on undefined helpers (AgentDBAdapter, embedContent, retrieveEntries, generate_embedding), uses malformed shell ("2>$dev$null"), and presents task lists inside ```bash blocks as if they were commands — concrete but incomplete/pseudocode-like, matching the level-2 anchor rather than copy-paste-ready level-3.	2 / 3
Workflow Clarity	Migration is sequenced into Phase 1/2/3 with a validation section and success-criteria checklist, but the destructive batch migration steps lack inline validation checkpoints or fix-retry feedback loops, so per the guideline for batch/destructive operations workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	No bundle files exist and everything — architecture, code, migration plan, benchmarks, coordination — is inline in one ~250-line file with no references; section headers provide organization, but content that should be split into separate files is inline, matching the level-2 anchor rather than the monolithic poorly-organized level-1 or the well-signaled multi-file level-3.	2 / 3
	Total	8 / 12 Passed

Description

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 placeholder that conveys no real capability, no natural trigger terms, and no use-when guidance, making it indistinguishable from other agent skills. It fails all four dimensions at the lowest anchor.

Suggestions

Replace the boilerplate with concrete actions the skill performs, e.g. "Unifies memory systems into AgentDB with HNSW indexing and migrates existing backends."

Add an explicit "Use when..." clause naming natural triggers a user would actually say, such as "Use when consolidating memory backends, migrating to vector search, or integrating AgentDB."

Drop the "$agent-v3-memory-specialist" invocation token from the description and use third-person capability language to improve distinctiveness from sibling agent skills.

Dimension	Reasoning	Score
Specificity	The description only states "Agent skill for v3-memory-specialist" — it names no concrete actions or capabilities whatsoever, matching the vague/abstract anchor rather than the level-2 example that names a domain plus some actions.	1 / 3
Completeness	It answers neither question usefully: "what does this do" is reduced to "Agent skill for..." and "when to use it" is replaced by an invocation syntax with no Use-when clause, so per the guideline a missing explicit trigger guidance caps completeness and the level-1 anchor fits best.	1 / 3
Trigger Term Quality	The only trigger is the technical invocation token "$agent-v3-memory-specialist"; this is jargon, not a natural keyword a user would say, so it matches the no-natural-keywords anchor rather than the level-2 "some relevant keywords" example.	1 / 3
Distinctiveness Conflict Risk	The "Agent skill for X" framing is generic and would be indistinguishable from many sibling agent skills, matching the level-1 "very generic; would conflict with many skills" anchor rather than a distinct niche.	1 / 3
	Total	4 / 12 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: 26c35b5

Reviewed: about 5 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.