CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-orchestrator-task

Agent skill for orchestrator-task - invoke with $agent-orchestrator-task

44

1.32x
Quality

19%

Does it follow best practices?

Impact

82%

1.32x

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-orchestrator-task/SKILL.md

The canonical home for this skill is agent-orchestrator-task in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

Quality

Content

21%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 conceptual feature catalog for a Task Orchestrator agent: well-sectioned but verbose, with no executable guidance, no validation checkpoints, and a malformed stray YAML block. It tells Claude what the agent does in the abstract but not how to actually run it.

Suggestions

Add concrete, executable guidance — the actual tools/commands or step-by-step procedure for decomposing a task and dispatching subtasks (e.g., how to call TodoWrite, how to spawn agents, how to query memory).

Insert validation checkpoints into the task patterns (e.g., verify subtask results before synthesis, re-plan on blocker detection) since orchestration is a batch operation requiring feedback loops.

Remove the redundant second YAML block (lines 6-28) and trim generic capability bullets that restate knowledge Claude already has, keeping only instructions that add new information.

DimensionReasoningScore

Conciseness

The body is noticeably verbose, cataloging generic capabilities Claude already knows ("Analyzes complex objectives", "Identifies logical subtasks", "Bottleneck identification") across padded sections like Core Functionality, Advanced Features, and Integration Points.

2 / 5

Actionability

The entire body describes capabilities abstractly and includes no executable code, commands, or concrete steps — the "Task Patterns" are phase labels and the "Usage Examples" are quoted prompts, so it describes rather than instructs.

1 / 5

Workflow Clarity

The Task Patterns give a rough phase sequence but the steps are poorly defined high-level labels with no commands, and validation/verification is entirely absent in a batch orchestration context where the rubric requires feedback loops.

2 / 5

Progressive Disclosure

The document has clear section headers and no nested references (no bundle files exist), but all content is inlined — including a stray second YAML config block and detailed patterns that could live in separate files — so organization is only moderate.

3 / 5

Total

8

/

20

Passed

Description

17%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 generic templated placeholder that names a domain but provides no concrete capabilities, no natural trigger terms, and no "Use when" guidance. It is unlikely to help a user or Claude decide when to invoke this skill.

Suggestions

Replace the templated text with concrete actions the skill performs, e.g. "Decomposes complex objectives into subtasks, plans parallel/sequential execution, and synthesizes agent results."

Add an explicit "Use when..." clause with natural trigger phrases such as "multi-step feature development", "coordinating multiple agents", or "breaking down a complex objective".

Drop the "$agent-orchestrator-task" invocation syntax from the description; keep trigger language user-facing rather than mechanical.

DimensionReasoningScore

Specificity

The phrase "Agent skill for orchestrator-task" names a domain but states no concrete actions — it only identifies the skill type, while "invoke with $agent-orchestrator-task" is invocation syntax, not a capability.

2 / 5

Completeness

It offers a vague "what" ("Agent skill for orchestrator-task") and no real "when" — the invocation hint is not a "Use when..." trigger clause, and the guideline caps completeness at 3 for missing trigger guidance; here both are weak so it sits at 2.

2 / 5

Trigger Term Quality

The only terms are "orchestrator-task" and "$agent-orchestrator-task", which are technical invocation jargon rather than natural phrases a user would say when needing this skill.

1 / 5

Distinctiveness Conflict Risk

The templated "Agent skill for X - invoke with $X" pattern is broad and would overlap with any sibling skill using the same template, despite referencing one specific task name.

2 / 5

Total

7

/

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.