agent-planner

Agent skill for planner - invoke with $agent-planner

1.43x

Quality

17%

Does it follow best practices?

Impact

92%

1.43x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-planner/SKILL.md

Quality

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is critically deficient across all dimensions. It provides only an invocation command without explaining what the skill does, when to use it, or any distinguishing features. Claude would have no basis for selecting this skill appropriately from a collection of available skills.

Suggestions

Add specific concrete actions the planner performs (e.g., 'Creates project timelines, breaks down complex tasks into subtasks, estimates effort, identifies dependencies').

Include an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks to plan a project, create a roadmap, break down tasks, or organize work').

Clarify what type of planning this skill handles to distinguish it from other potential planning-related skills (e.g., project planning vs. travel planning vs. meal planning).

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for planner' is completely abstract with no indication of what the skill actually does.	1 / 3
Completeness	The description fails to answer both 'what does this do' and 'when should Claude use it'. It only provides invocation syntax ('invoke with $agent-planner') without any functional description or usage guidance.	1 / 3
Trigger Term Quality	The only potential trigger term is 'planner' which is vague and generic. No natural keywords a user would say when needing planning assistance (e.g., 'plan', 'schedule', 'organize tasks', 'roadmap').	1 / 3
Distinctiveness Conflict Risk	'Planner' is extremely generic and could conflict with any skill involving planning, scheduling, project management, or task organization. No distinguishing characteristics are provided.	1 / 3
	Total	4 / 12 Passed

Implementation

35%

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

This skill is significantly over-engineered, explaining planning fundamentals that Claude inherently understands. The useful content (MCP tool integration, YAML output format) is buried under verbose descriptions of obvious concepts. The skill would be far more effective at 1/3 the length, focusing only on the specific output format and tool commands.

Suggestions

Remove the 'Core Responsibilities', 'Best Practices', and abstract 'Planning Process' descriptions - Claude already knows how to plan strategically

Keep only the YAML output format template and MCP tool integration examples as the core actionable content

Add explicit validation steps: how to verify a plan is complete, what signals indicate replanning is needed

Move MCP tool examples to a separate REFERENCE.md file and keep SKILL.md as a concise overview with the output format

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive explanation of planning concepts Claude already knows (task decomposition, dependency analysis, risk assessment). The 'Core Responsibilities' and 'Best Practices' sections explain obvious planning principles that add no value.	1 / 3
Actionability	Provides some concrete code examples for MCP tool integration and a YAML output format template, but much of the content is abstract guidance ('Analyze the complete scope', 'Identify key objectives') rather than executable instructions.	2 / 3
Workflow Clarity	The 5-step planning process is listed but lacks validation checkpoints or feedback loops. No explicit verification steps between phases, and no guidance on what to do if planning fails or needs revision.	2 / 3
Progressive Disclosure	Content is structured with headers but is monolithic - all content is inline with no references to external files. The MCP tool examples and output format could be split into separate reference files for cleaner organization.	2 / 3
	Total	7 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: b2618f9

Reviewed: 4 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.