CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-worker-specialist

Agent skill for worker-specialist - invoke with $agent-worker-specialist

57

10.88x
Quality

Does it follow best practices?

Impact

98%

10.88x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

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 provides detailed, domain-specific coordination protocol guidance organized into clear sections, but is weighed down by repetitive pseudocode blocks, lacks executable code, and is monolithic with no progressive disclosure to supporting files.

Suggestions

Collapse the repeated memory_usage blocks into one parameterized template and show only the differing key/value pairs per work type, cutting substantial token cost.

Either make the code blocks genuinely executable (real tool-call syntax) or explicitly label them as protocol illustrations rather than ```javascript.

Add an explicit validate-then-proceed feedback loop for task completion (e.g. verify deliverables before writing the complete status), and consider moving the specialized work-type templates into a reference file.

DimensionReasoningScore

Conciseness

The body is domain-specific (claude-flow memory protocol) without explaining concepts Claude already knows, but it repeats near-identical memory_usage code blocks six-plus times that could be collapsed to one template plus variations, fitting 'mostly efficient but could be tightened'.

2 / 3

Actionability

The blocks give concrete keys, namespaces, and value structures, but are labeled ```javascript while using non-executable pseudocode syntax (mcp__claude-flow__memory_usage { ... } with no call parens) and placeholders like worker-[ID], matching 'some concrete guidance but pseudocode instead of executable code'.

2 / 3

Workflow Clarity

Sequences (Sequential/Parallel/Emergency) and a dependency-readiness gate with a block-and-report feedback path are present, but the core execution flow lacks an explicit validate-fix-retry loop and checkpoints are largely implicit, fitting 'steps listed but validation gaps'.

2 / 3

Progressive Disclosure

No bundle files exist and the skill is a single ~140-line monolithic file with clear section organization but no file splitting; the repeated protocol templates are inline content that could live in separate references, fitting 'some structure but content that should be separate is inline'.

2 / 3

Total

8

/

12

Passed

Description

17%

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 minimal invocation stub that names a domain but states no concrete capabilities and provides no natural trigger language or use-when guidance, leaving it largely uninformative for skill selection.

Suggestions

Replace the stub with concrete capability verbs, e.g. 'Executes assigned tasks, reports progress, and coordinates with the swarm via shared memory.'

Add an explicit 'Use when...' clause with natural trigger terms users would actually say (e.g. 'Use when the queen-coordinator assigns a task or when parallel worker execution is needed').

Drop the internal '$agent-worker-specialist' invocation syntax from the description; keep trigger terms user-facing.

DimensionReasoningScore

Specificity

The phrase "Agent skill for worker-specialist" names the domain but describes no concrete capability actions (e.g. executes tasks, reports progress), reading as a category label rather than a capability list, matching the 'names domain and some actions, but not comprehensive' anchor more than the fully vague anchor.

2 / 3

Completeness

It offers only a weak 'what' ("Agent skill for worker-specialist") and entirely omits any 'when' / "Use when..." trigger guidance, matching the 'missing what OR when, or both very weak' anchor.

1 / 3

Trigger Term Quality

The only terms are internal system identifiers "worker-specialist" and "$agent-worker-specialist"; a user would not naturally say these when they need the skill, fitting the 'no natural keywords; technical jargon' anchor.

1 / 3

Distinctiveness Conflict Risk

"worker-specialist" identifies a specific role niche within the hive/swarm system, but with no distinct trigger terms it could still overlap with similar worker-type skills, fitting the 'somewhat specific but could still overlap' anchor.

2 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/claude-flow
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.