agent-worker-specialist
Agent skill for worker-specialist - invoke with $agent-worker-specialist
44
13%
Does it follow best practices?
Impact
98%
10.88xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-worker-specialist/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially a placeholder with no meaningful content. It fails on every dimension: it describes no capabilities, includes no natural trigger terms, provides no guidance on when to use it, and is completely indistinguishable from any other skill. It reads as an auto-generated stub rather than a functional skill description.
Suggestions
Replace the entire description with concrete actions the skill performs (e.g., 'Delegates complex tasks to specialized sub-agents for parallel processing').
Add an explicit 'Use when...' clause that describes the scenarios and user requests that should trigger this skill.
Include natural keywords and terms that users would actually say when they need this skill's functionality, rather than internal naming conventions like 'worker-specialist'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for worker-specialist' is entirely abstract with no indication of what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states how to invoke it, not what it does or when it should be selected. | 1 / 3 |
Trigger Term Quality | There are no natural keywords a user would say. 'worker-specialist' is internal jargon, and 'invoke with $agent-worker-specialist' is a technical invocation instruction, not a trigger term. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so generic that it provides no distinguishing information. 'Worker-specialist' could refer to virtually any domain, making it impossible to differentiate from other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is overly verbose, repeating the same memory coordination pattern across 8+ nearly identical code blocks when a single template with a variation table would suffice. The actionability is moderate—concrete MCP tool calls are shown but with inconsistent and sometimes invalid syntax. The lack of any progressive disclosure structure and missing validation checkpoints in workflows significantly weaken the skill's effectiveness.
Suggestions
Consolidate the repetitive mcp__claude-flow__memory_usage code blocks into a single template with a table showing the key/value variations for each worker type and status phase.
Fix the JavaScript syntax inconsistencies—either use proper async/await with function calls or show the MCP tool calls as structured tool-use blocks, not a hybrid.
Add explicit validation checkpoints: verify output quality before marking complete, confirm dependency state after unblocking, validate files exist after creation.
Extract specialized worker types and integration points into separate reference files (e.g., WORKER-TYPES.md, INTEGRATIONS.md) and reference them from a concise overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with repetitive JSON blocks that all follow the same pattern (memory_usage store calls). The skill could be condensed to a single template with variations noted, rather than repeating nearly identical code blocks 8+ times. Much of the content (work patterns, quality standards, integration points) is generic agent behavior that Claude can infer. | 1 / 3 |
Actionability | The code blocks show concrete MCP tool calls with specific parameters, which is useful. However, the JavaScript is not truly executable—it mixes async/await with raw MCP call syntax inconsistently, uses placeholder values like '[ID]' and '[feature]' without explaining how to resolve them, and the dependency management example uses invalid syntax (mixing await with non-function MCP calls). | 2 / 3 |
Workflow Clarity | The sequential execution pattern lists clear steps (receive, verify, execute, report, deliver), and the dependency check includes a blocking flow. However, there are no explicit validation checkpoints—no step says 'verify your output before reporting complete,' and the error recovery for blocked states is incomplete (what happens after reporting blocked?). | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files and no bundle files to support it. All specialized worker types, work patterns, and integration details are inlined despite being candidates for separate reference documents. The content would benefit greatly from splitting worker type templates, integration docs, and metrics into separate files. | 1 / 3 |
Total | 6 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ruvnet/claude-flow
- Commit
2b9e2de
- 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.