agent-orchestrator-task

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

1.32x

Quality

20%

Does it follow best practices?

Impact

82%

1.32x

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-orchestrator-task/SKILL.md

Quality

Content

28%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 descriptive brochure, not an operational skill: it catalogs capabilities, integration points, and best practices in abstract bullets without a single executable command, a defined operating procedure, or validation checkpoints. It is padded with generic orchestration knowledge Claude already has, and it begins with a stray duplicate YAML frontmatter block that should be removed or made the single real frontmatter.

Suggestions

Replace the capability bullets with an explicit numbered operating procedure the agent follows (decompose → assign → monitor → synthesize), including validation checkpoints such as verifying subtask completion and conflict resolution before synthesizing results.

Remove the stray duplicate YAML frontmatter block at the top of the body and keep exactly one frontmatter for the whole file.

Cut the generic Best Practices / Advanced Features bullets and instead add concrete, executable guidance — actual TodoWrite/memory_store usage examples and a worked decomposition of a real objective — moving extended patterns or integration tables into a references/ file linked from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is noticeably padded: abstract bullet lists like 'Analyzes complex objectives', 'Maximizes parallelization opportunities', and 'Critical path optimization' restate generic orchestration knowledge Claude already has, and the Advanced Features / Best Practices sections add little. It opens with a redundant duplicate YAML frontmatter block (lines 6-28) that is pure noise. This fits score 2 ('several unnecessary explanations or padded sections') rather than score 3, where the padding would be isolated rather than pervasive.	2 / 5
Actionability	Almost nothing is executable: there are no commands, code, or concrete tool invocations in the markdown — only descriptive bullets ('Aggregates outputs from multiple agents', 'Use TodoWrite for transparent progress tracking') with no usage shown. The most concrete material is the high-level Task Patterns ('1. Requirements Analysis (Sequential)...'), which are templates, not steps. This matches score 2 ('minimal concrete guidance; high-level hints but missing the specific steps'); not score 1 only because the Task Patterns and Usage Examples give some concrete shape.	2 / 5
Workflow Clarity	The agent's own operating procedure (how to decompose, assign, monitor, re-plan, synthesize) is never laid out as a sequence — only project-level task-ordering examples are given, and validation/verification checkpoints are entirely absent despite this being a batch-style coordination skill (which caps workflow clarity at 3 at most). This fits score 2 ('rough sequence present but many gaps; steps poorly defined; validation absent'); the pattern sequences keep it off score 1.	2 / 5
Progressive Disclosure	The body has reasonable section structure (Purpose, Core Functionality, Usage Examples, Task Patterns, Integration Points, Best Practices, Advanced Features) and there are no broken or nested references — but there are also no bundle files at all (no references/, scripts/, or assets/ exist), so ~140 lines of abstract content sit monolithically inline where patterns and integration details could be split out. This matches score 3 ('some structure but could be better organized'); not score 4 because nothing is offloaded and the misplaced YAML block buries the actual configuration.	3 / 5
	Total	9 / 20 Passed

Description

12%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 that a frontmatter parser actually extracts is a low-information wrapper stub: no capabilities, no natural trigger phrases, and no use-when guidance. Note the file contains a second, stray YAML frontmatter block in the body whose description ('Central coordination agent for task decomposition, execution planning, and result synthesis') is far more substantive, but it never surfaces to the skill selector — the malformed dual-frontmatter structure is the root defect.

Suggestions

Fix the malformed dual frontmatter: merge the substantive description from the stray second YAML block ('Central coordination agent for task decomposition, execution planning, and result synthesis') into the single top-level frontmatter so it is the description a loader actually reads.

State concrete capabilities in the description (task decomposition, execution planning, dependency management, result synthesis, progress tracking) instead of the wrapper stub 'Agent skill for orchestrator-task'.

Add an explicit 'Use when...' clause with natural user phrases, e.g., 'Use when coordinating multiple agents, breaking a complex objective into subtasks, or managing parallel execution and dependencies.'

Dimension	Reasoning	Score
Specificity	The effective frontmatter description is 'Agent skill for orchestrator-task - invoke with $agent-orchestrator-task' — it names no concrete action the skill performs, only what it is ('Agent skill') and an invocation token. This matches the score-1 anchor ('no concrete actions; pure abstract language') rather than score 2, whose example ('Processes PDF files') still states at least one generic action.	1 / 5
Completeness	It provides a vague 'what' ('Agent skill for orchestrator-task') and no 'when' at all — 'invoke with $...' is syntax, not a 'Use when...' clause. This matches score 2 ('vague what and no when'); it does not reach score 3 because the what never states any function, and it is above score 1 only because a domain is at least named.	2 / 5
Trigger Term Quality	The only trigger-like terms are the internal slug '$agent-orchestrator-task' and 'orchestrator-task' — technical jargon, not phrases a user would naturally say (e.g., 'orchestrate tasks', 'coordinate agents', 'break down this project'). This fits the score-1 anchor ('only technical jargon or entirely generic language') more than score 2, which expects at least one or two generic-but-natural keywords.	1 / 5
Distinctiveness Conflict Risk	'Agent skill for orchestrator-task' is a bare category label with no distinguishing capability or trigger, so it overlaps with any other orchestration/coordination skill in a swarm-style framework (the body names many sibling agents). This fits score 2 ('very broad; high overlap risk with many similar skills'); not score 3, because nothing in the description itself narrows the niche.	2 / 5
	Total	6 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Path: .agents/skills/agent-orchestrator-task/SKILL.md
Commit: b14c79e

Reviewed: 3 days 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.