agent-crdt-synchronizer

Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer

2.93x

Quality

Does it follow best practices?

Impact

97%

2.93x

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-crdt-synchronizer/SKILL.md

Quality

Content

15%

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 verbose, monolithic code dump of standard CRDT implementations that re-teaches concepts Claude already knows, with code that is concrete but not executable due to missing dependencies and acknowledged simplifications, and no workflow checkpoints or progressive disclosure. It functions as a reference library rather than actionable, token-efficient skill guidance.

Suggestions

Collapse the full CRDT class implementations into a concise overview plus one minimal executable example, relying on Claude's existing knowledge of G-Counter/OR-Set/LWW-Register/RGA rather than re-implementing them in full.

Add a real step-by-step usage workflow with explicit validation checkpoints (e.g. register CRDT -> apply operation -> compute delta -> sync with peer -> verify convergence), since synchronization is a risky distributed operation.

Move detailed implementations into separate reference files under references/ and have SKILL.md point to them one level deep, restoring progressive disclosure instead of a monolithic inline dump.

Dimension	Reasoning	Score
Conciseness	The body is a ~1000-line dump of full reference implementations for well-known CRDTs (G-Counter, OR-Set, LWW-Register, RGA) that Claude already understands, plus a noisy second YAML config block — heavily padded rather than lean, matching the 'verbose; padded with unnecessary context' anchor and not the 'mostly efficient' score 2.	1 / 3
Actionability	Substantial concrete JavaScript is provided, but it is not executable as-is: undefined classes (VectorClock, SyncScheduler, PNCounter, ORMap) and methods (compareStates, applyCRDTOperation, serializeState) are referenced, and several blocks are explicitly marked 'Simplified'/'real implementation would use topological sort', fitting 'incomplete; missing key details' rather than copy-paste-ready score 3.	2 / 3
Workflow Clarity	The body is a reference code library, not a sequenced procedure; the numbered 'Core Responsibilities' is a feature list rather than an ordered workflow, and there are no validation checkpoints for the risky distributed-merge/sync operations despite the sync hooks only echoing 'Validating convergence' without actual verification.	1 / 3
Progressive Disclosure	No bundle files exist and everything lives inline in one ~1000-line SKILL.md with no external references or navigation — a monolithic wall of code far beyond the small-skill exemption, matching the 'monolithic wall of text; poor organization' anchor.	1 / 3
	Total	5 / 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 generic boilerplate that names the skill's domain without describing any concrete actions, natural trigger terms, or a 'Use when' clause, making it indistinguishable from templated skill descriptions. It fails to tell Claude what the skill does or when to invoke it.

Suggestions

Replace the boilerplate with concrete capabilities, e.g. 'Implements state-based and operation-based CRDTs (G-Counter, OR-Set, LWW-Register, RGA) and synchronizes deltas across peer nodes.'

Add an explicit trigger clause: 'Use when synchronizing eventually-consistent distributed state, merging replicated data types, or resolving conflicts without consensus.'

Include natural user-facing keywords (conflict-free replicated data types, merge, eventual consistency, sync) rather than only the '$agent-crdt-synchronizer' invocation token.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer' names the domain but lists zero concrete actions, matching the vague 'Helps with documents' anchor rather than a score-2 that would require naming some actions.	1 / 3
Completeness	It neither explains what the skill concretely does nor gives a 'Use when...' clause; the 'invoke with' phrase is invocation syntax, not trigger guidance, so both what and when are missing/very weak.	1 / 3
Trigger Term Quality	The only trigger term is the technical invocation token '$agent-crdt-synchronizer'; there are no natural keywords a user would say, fitting the 'technical jargon or overly generic' anchor like 'Handles document object model manipulation'.	1 / 3
Distinctiveness Conflict Risk	The 'Agent skill for X - invoke with $X' phrasing is generic auto-generated boilerplate that would be indistinguishable across many skills, matching the 'would conflict with many skills' anchor.	1 / 3
	Total	4 / 12 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
skill_md_line_count	SKILL.md is long (1002 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: ruvnet/claude-flow
Path: .agents/skills/agent-crdt-synchronizer/SKILL.md
Commit: 26c35b5

Reviewed: about 8 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.