agent-memory-coordinator

Agent skill for memory-coordinator - invoke with $agent-memory-coordinator

1.53x

Quality

14%

Does it follow best practices?

Impact

95%

1.53x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

3%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 descriptive marketing-style catalog of an idealized memory system: it names capabilities (compression, deduplication, semantic search, sharding) without a single executable instruction, command, or tool call. It also opens with a stray second YAML frontmatter block, indicating malformed structure. The content tells an agent nothing it can actually do.

Suggestions

Replace the abstract capability bullets with concrete, executable guidance: actual memory tool calls or commands for store/retrieve/search/delete/sync with their key arguments (e.g. the real key syntax 'project$auth$jwt-config' shown as a worked example).

Define a step-by-step memory workflow with validation checkpoints — especially a verify-before-delete step for destructive operations (delete, garbage collection) — instead of the current feature catalog with no sequence.

Split the namespace schemas, security/compliance policy, and advanced-feature lists into separate reference files (e.g. references/namespaces.md, references/security.md) linked from a concise SKILL.md overview, and remove the stray second YAML frontmatter block from the body.

Dimension	Reasoning	Score
Conciseness	The ~190-line body is a catalog of abstract bullet lists ('Smart Retrieval', 'Predictive prefetching', 'Replication for reliability') padded across a dozen sections with no executable substance. It lands at 2 rather than 1 because it does not explain textbook concepts Claude already knows — it is aspirational filler rather than redundant tutorial prose.	2 / 5
Actionability	The body is entirely descriptive: 'Store: Save data with optional TTL and encryption' and similar bullets contain no code, commands, tool names, or API calls an agent could execute — the 'only describes rather than instructs' anchor is an exact match. The lone shell snippets in the hooks are decorative echo statements.	1 / 5
Workflow Clarity	There is no sequence of steps anywhere — the body enumerates features, not a process, and offers no validation checkpoints for its own destructive operations (delete, garbage collection). Score 2 would require at least a rough sequence, which is absent.	1 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and the body references none, so ~190 lines of namespace schemas, security policy, and feature lists sit inline in SKILL.md — content that clearly belongs in separate files. Section headers provide some structure, keeping this above the unstructured-wall anchor at 1.	2 / 5
	Total	6 / 20 Passed

Description

25%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 frontmatter description is a stub: it names the skill but communicates no capabilities and no usage triggers, functioning as invocation metadata rather than a trigger-capable description. The real description ('Manage persistent memory across sessions and facilitate cross-agent memory sharing') is buried in a second YAML block in the body where it cannot serve as the skill's trigger description. It reads like a generated placeholder.

Suggestions

Replace the frontmatter description with the actual capability statement from the body's second YAML block, e.g. 'Manage persistent memory across sessions and facilitate cross-agent memory sharing: store, retrieve, search, sync, and garbage-collect namespaced memory entries.'

Add an explicit trigger clause, e.g. 'Use when the user asks to remember, recall, or persist information across sessions, or when coordinating shared memory between agents.'

Remove the invocation metadata ('$agent-memory-coordinator', 'invoke with') from the description — it adds no capability or trigger information and wastes the description's token budget.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Agent skill for memory-coordinator') but lists zero concrete actions — 'Manage persistent memory across sessions...' lives only in the body's second YAML block, not in the frontmatter description being evaluated. It is not score 1 because the domain is explicitly named; not 3 because no actions of any kind are stated.	2 / 5
Completeness	The 'what' is vague ('Agent skill for memory-coordinator' says nothing about what it actually does) and the 'when' is entirely absent, which the guidelines cap at 3. This matches anchor 2 (vague what, no when) rather than 3, because even the what is only implied.	2 / 5
Trigger Term Quality	Only the technical identifiers 'memory-coordinator' and '$agent-memory-coordinator' appear — none of the natural phrases a user would say ('remember', 'recall', 'what did we decide about'). It fits anchor 2 (one or two generic keywords, missing natural phrases) better than the pure-jargon anchor at 1, since 'memory' is a genuine domain term.	2 / 5
Distinctiveness Conflict Risk	Nothing distinguishes it from any other memory/persistence skill, and the only trigger is the unnatural token '$agent-memory-coordinator'. It overlaps broadly with memory-related skills (anchor 2) but is not 'helps with code and documents'-level generic (anchor 1).	2 / 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-memory-coordinator/SKILL.md
Commit: b14c79e

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.