CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-swarm-memory-manager

Agent skill for swarm-memory-manager - invoke with $agent-swarm-memory-manager

51

2.25x
Quality

28%

Does it follow best practices?

Impact

90%

2.25x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is agent-swarm-memory-manager in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

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 content is a well-sectioned but monolithic spec whose code examples are non-executable pseudo-MCP syntax rather than runnable JavaScript, and whose batch/destructive memory operations lack validation checkpoints. Concept-name bullet lists and a stray duplicate frontmatter block add padding.

Suggestions

Replace the `mcp__claude-flow__memory_usage { ... }` pseudo-syntax with real, runnable JavaScript function calls so examples are copy-paste executable.

Add explicit validation/verification checkpoints for the destructive and batch operations (e.g. re-read after an atomic write to confirm version, verify agents_synced against expected roster after a sync broadcast, assert cache-hit-rate and sync_latency thresholds before reporting metrics).

Remove the duplicate YAML frontmatter block embedded in the body, the flavor intro sentence, and the concept-name bullet lists (CRDT, vector clocks, LRU, write-ahead logging) that merely restate what Claude already knows.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete code blocks, but several sections just name concepts Claude already knows ("Implement multi-level caching (L1/L2/L3)", "CRDT", "vector clocks", "LRU eviction", "write-ahead logging") as bullet lists without actionable detail, plus flavor intro text and a stray duplicate frontmatter block.

3 / 5

Actionability

Code blocks give a concrete shape of the memory_usage calls (keys, values, namespaces), but the syntax `mcp__claude-flow__memory_usage { ... }` is not valid JavaScript and is not copy-paste executable, fitting the pseudocode-not-executable anchor; bullet sections like "Implement CRDT" only describe.

3 / 5

Workflow Clarity

There is a loose topical sequence (initialize → cache → sync → metrics → recovery) but no explicit validation checkpoints for batch read operations, atomic writes, and distributed sync broadcasts; per the rubric, destructive/batch operations without validation cap this at 3.

3 / 5

Progressive Disclosure

The ~185-line body has clear section headers but is entirely monolithic — no references to separate files and no bundle files exist (references/, scripts/, assets/ absent); content like the API operation catalog and recovery procedures is inlined where it could be split out, and a duplicate YAML frontmatter block is embedded in the body.

3 / 5

Total

12

/

20

Passed

Description

7%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 placeholder template ("Agent skill for X - invoke with $X") rather than a real capability description: it states no concrete actions, no natural trigger terms, and no use-when guidance. Only the specific niche name keeps it from being entirely generic.

Suggestions

Replace the placeholder with concrete capabilities, e.g. "Stores, retrieves, and synchronizes shared memory state across hive-mind agents using the claude-flow memory_usage tool, with caching, conflict resolution, and replication."

Add an explicit "Use when..." trigger clause naming natural user phrases (e.g. shared memory, swarm coordination, agent state sync, cache invalidation).

Remove the "invoke with $agent-swarm-memory-manager" meta-text from the description; invocation mechanics do not belong in the capability description.

DimensionReasoningScore

Specificity

The description only states "Agent skill for swarm-memory-manager" and "invoke with $agent-swarm-memory-manager" — it names no concrete actions whatsoever, just a meta-template label of what the skill is.

1 / 5

Completeness

It gives an extremely vague "what" ("Agent skill for swarm-memory-manager") and no "when" — the "invoke with" clause is about how to call it, not when Claude should use it, so both what and when are missing or extremely vague.

1 / 5

Trigger Term Quality

The only terms are the invocation token "swarm-memory-manager" and "$agent-swarm-memory-manager"; these are technical invocation tokens, not natural phrases a user would say when they need the skill.

1 / 5

Distinctiveness Conflict Risk

The niche name "swarm-memory-manager" is fairly specific and unlikely to collide with unrelated skills, but the description itself is generic template language with no functional triggers, so it could still overlap with other hive-mind/coordination skills.

3 / 5

Total

6

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/ruflo
Reviewed

Table of Contents

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.