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

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

63%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.

A detailed, well-sectioned orchestration playbook with concrete sub-agent assignments and clear sequencing, weakened by redundancy between overlapping phase sections and a monolithic structure that inlines templates which would be better split into reference files.

Suggestions

Deduplicate the phase sequence: collapse 'Execution Plan Template', 'Pattern 1: New Feature Development', and the 'Task Execution' orchestration list into a single canonical workflow, referencing it from the others.

Move the large template blocks (Task Analysis, Dependency Graph, Execution Plan, Progress Report) into separate files under references/ and link to them from SKILL.md to enable progressive disclosure.

Replace some placeholder-only template fields with one concrete worked example so the templates read as actionable rather than scaffolding.

Dimension	Reasoning	Score
Conciseness	Mostly functional template content, but noticeably redundant — the 'Execution Plan Template' phases, 'Pattern 1: New Feature Development' phases, and 'Task Execution' orchestration steps restate the same five-phase sequence. It is not a 2 because the templates do serve a structural purpose, and not a 4 because the duplication could be trimmed substantially.	3 / 5
Actionability	Provides concrete, actionable guidance: named sub-agents (specify, taskify, go-implementor, go-review, mentor, document), a decision framework for when to use each, and explicit argument handling (--analyze, --plan, --status). It is not a 5 because the heavy use of placeholder templates ('[Task Name]', '[What needs to be accomplished]') leaves some guidance incomplete.	4 / 5
Workflow Clarity	Clear orchestration sequence with explicit checkpoints ('Wait for Phase 1 completion before proceeding'), success-criteria checklists, and review/validation phases. It is not a 5 because error-recovery feedback loops are not deeply spelled out, and not below 4 since validation steps are present.	4 / 5
Progressive Disclosure	Has clear section headers, but large template blocks (Task Analysis, Dependency Graph, Execution Plan, Progress Report) that belong in separate reference files are all inlined, with zero external references and no bundle files present. It is not a 2 because the section structure is genuinely good, and not a 4 because the ~370-line monolith offers no progressive disclosure.	3 / 5
	Total	14 / 20 Passed

Description

83%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.

A strong, well-structured description that states both capability and an explicit 'Use for' trigger, with good natural-language trigger terms. Main improvement would be tightening 'complex software development tasks' to a more distinctive niche and adding a few colloquial synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'orchestrating complex software development tasks', 'coordinating specialized sub-agents', 'managing parallel work streams' — with only minor gaps in coverage. It is not a 5 because the actions lean slightly abstract ('orchestrating', 'coordinating') rather than enumerating a fully comprehensive set.	4 / 5
Completeness	Explicitly answers both 'what' (orchestrates by coordinating sub-agents and managing parallel work streams) and 'when' via the concrete trigger clause 'Use for large initiatives requiring coordination across multiple specialists.' It is not below 5 because both halves are present and explicitly triggered.	5 / 5
Trigger Term Quality	Includes natural phrases a user might say — 'large initiatives', 'coordination across multiple specialists', 'parallel work streams' — giving good keyword coverage. It is not a 5 because common synonyms and more colloquial variants are missing.	4 / 5
Distinctiveness Conflict Risk	The orchestration/coordinator niche is mostly distinct from the individual specialist skills it delegates to, with only minor overlap risk against broad coding-assistance skills. It is not a 5 because 'complex software development tasks' is somewhat broad and could overlap with general development skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 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	14 / 16 Passed

Repository: rikdc/ai-skills
Path: plugins/dev-skills/skills/manager/SKILL.md
Commit: cd15778

Reviewed: 2 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.