manager

Engineering manager agent for orchestrating complex software development tasks by coordinating specialized sub-agents and managing parallel work streams. Use for large initiatives requiring coordination across multiple specialists.

Quality

38%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/dev-skills/skills/manager/SKILL.md

Quality

Content

31%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill reads more like a project management methodology document than an actionable skill for Claude. It is highly repetitive, with decomposition/parallelization/phasing concepts restated across multiple sections (Task Analysis, Execution Plan Template, Execution Patterns, Task Execution). The content lacks concrete, executable guidance — there are no actual mechanisms shown for invoking sub-agents, no validation steps, and no real-world examples with specific inputs and outputs.

Suggestions

Replace the abstract templates with concrete, executable examples showing exactly how to invoke each sub-agent (e.g., actual tool calls or command syntax) with real input/output examples.

Consolidate the heavily duplicated content: Task Analysis, Execution Plan Template, Execution Patterns, and Task Execution sections all cover the same decompose-delegate-track workflow — merge into one concise section.

Add explicit validation checkpoints and feedback loops (e.g., 'Verify sub-agent output meets acceptance criteria before proceeding; if not, re-delegate with specific feedback').

Split the monolithic file: move the execution patterns, decision framework, and progress tracking templates into separate referenced files, keeping SKILL.md as a concise overview with clear navigation links.

Dimension	Reasoning	Score
Conciseness	The skill is heavily verbose and repetitive. The execution patterns repeat information already covered in the execution plan template. The dependency management section, progress tracking template, and communication style sections all explain concepts Claude already understands (project management basics). Multiple sections convey the same ideas (decomposition, parallelization, phased execution) in slightly different formats.	2 / 5
Actionability	The content is almost entirely templates and abstract frameworks rather than executable guidance. There are no actual commands to invoke sub-agents, no concrete code, and no real examples of how delegation actually works mechanically. The 'Available Sub-Agents' section lists skills but doesn't show how to actually call them. Everything is markdown templates with placeholder text rather than actionable instructions.	2 / 5
Workflow Clarity	The phases are clearly sequenced with dependency awareness (e.g., 'Wait for Phase 1 completion before proceeding'), and there are explicit dependency graphs. However, there are no validation checkpoints or feedback loops — no steps for verifying that sub-agent outputs meet quality standards before proceeding, no error recovery if a phase fails, and no explicit verification that delegated work was completed correctly before moving to the next phase.	3 / 5
Progressive Disclosure	The skill is a monolithic ~300-line file with no references to external files and no bundle structure. The execution patterns, decision framework, templates, and communication guidelines could all be split into separate reference files. Everything is inlined in one large document with many sections that would benefit from being separate files referenced from a concise overview.	2 / 5
	Total	9 / 20 Passed

Description

46%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 establishes a high-level role (engineering manager agent) and provides a 'Use for' clause, but it relies heavily on abstract organizational language rather than concrete actions. The trigger terms are too generic and managerial rather than reflecting what users would naturally request. It would benefit significantly from listing specific concrete capabilities and more natural trigger phrases.

Suggestions

Add concrete actions the skill performs, e.g., 'Breaks down large features into subtasks, delegates to specialized coding agents, merges results, and tracks progress across work streams.'

Include natural trigger terms users would say, such as 'build a full feature', 'implement across multiple files', 'large refactor', 'multi-step project', or 'coordinate changes across the codebase'.

Make the 'Use for' clause more specific with examples, e.g., 'Use when the user requests a complex multi-file feature, a large-scale refactor, or any task that benefits from breaking work into parallel sub-tasks across different parts of the codebase.'

Dimension	Reasoning	Score
Specificity	Names the domain (engineering management, orchestrating software development) but the actions are generic — 'coordinating specialized sub-agents' and 'managing parallel work streams' are abstract descriptions rather than concrete actions like 'creates task breakdowns', 'assigns work to agents', or 'tracks progress'.	2 / 5
Completeness	Has both 'what' (orchestrating complex software development tasks by coordinating sub-agents and managing parallel work streams) and 'when' ('Use for large initiatives requiring coordination across multiple specialists'). However, the 'when' clause is vague — 'large initiatives' and 'multiple specialists' don't provide concrete trigger scenarios.	4 / 5
Trigger Term Quality	Contains some relevant terms like 'engineering manager', 'software development', 'sub-agents', and 'parallel work streams', but these are not natural phrases users would say. Users are more likely to say things like 'build a feature', 'refactor the codebase', 'implement across multiple files', or 'large project'. Missing common synonyms and natural trigger phrases.	2 / 5
Distinctiveness Conflict Risk	The 'engineering manager agent' and 'sub-agents' framing provides some distinctiveness, but 'complex software development tasks' is broad enough to overlap with many coding-related skills. The description doesn't clearly delineate what separates this from a general coding skill or a project management skill.	3 / 5
	Total	11 / 20 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: rikdc/ai-skills
Path: plugins/dev-skills/skills/manager/SKILL.md
Commit: a43676e

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.