agent-planner

Agent skill for planner - invoke with $agent-planner

1.43x

Quality

13%

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 is an extremely weak description that provides virtually no useful information for skill selection. It fails on every dimension: it names no concrete actions, includes no natural trigger terms, lacks both 'what' and 'when' guidance, and is so generic it would be indistinguishable from many other potential skills.

Suggestions

Describe what the planner actually does with specific concrete actions (e.g., 'Creates step-by-step project plans, breaks down complex tasks into subtasks, estimates timelines and dependencies').

Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user asks to plan a project, break down a task, create a roadmap, or organize work into steps').

Clarify the specific domain or niche this planner covers to distinguish it from other planning-related skills (e.g., is it for software project planning, daily scheduling, strategic planning, etc.).

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for planner' is entirely vague and abstract, giving no indication of what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause and no description of capabilities.	1 / 3
Trigger Term Quality	The only keyword is 'planner', which is generic and not a natural term users would say when needing help. The invocation command '$agent-planner' is technical syntax, not a natural trigger term.	1 / 3
Distinctiveness Conflict Risk	'Planner' is extremely generic and could overlap with any skill involving planning, scheduling, project management, task management, or general organization. There are no distinct triggers to differentiate it.	1 / 3
	Total	4 / 12 Passed

Implementation

27%

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

This skill is overly verbose, spending significant tokens on generic planning advice and abstract concepts that Claude already understands. While it provides some useful concrete elements (YAML output template, MCP tool call examples), much of the content reads like a management textbook rather than actionable agent instructions. The lack of validation checkpoints and monolithic structure further weaken its effectiveness.

Suggestions

Cut the 'Best Practices', 'Collaboration Guidelines', and 'Core Responsibilities' sections entirely — these are generic concepts Claude already knows. Focus on the specific output format and MCP tool usage.

Add explicit validation checkpoints: e.g., 'After task decomposition, verify no circular dependencies exist' and 'Before dispatching to agents, confirm all referenced agents are available via task_status'.

Split MCP tool integration examples and the YAML output format into separate reference files, keeping SKILL.md as a concise overview with links.

Replace abstract instructions like 'Analyze the complete scope of the request' with concrete decision criteria, e.g., 'If task has >3 independent subtasks, use strategy: parallel; otherwise use strategy: sequential'.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with many sections that explain concepts Claude already knows (what task decomposition is, what dependency analysis means, generic best practices like 'specific and actionable, measurable and time-bound'). The 'Best Practices' and 'Collaboration Guidelines' sections are largely platitudes. The content could be reduced by 60%+ without losing actionable information.	1 / 3
Actionability	The YAML output format template and MCP tool integration examples provide some concrete guidance. However, much of the content is abstract instruction ('Analyze the complete scope of the request', 'Identify key objectives') rather than executable steps. The JavaScript examples use tool calls but are illustrative rather than copy-paste ready for real scenarios.	2 / 3
Workflow Clarity	The 5-step planning process provides a clear sequence, and the output format gives structure. However, there are no validation checkpoints or feedback loops — no step says 'verify the plan is feasible before proceeding' or 'if dependency analysis reveals circular dependencies, do X'. For a planning agent that orchestrates other agents, missing validation/error recovery is a significant gap.	2 / 3
Progressive Disclosure	All content is in a single monolithic file with no references to external files. The MCP tool integration, output format examples, best practices, and collaboration guidelines could all be split into separate reference files. With no bundle files provided and no external references, everything is dumped inline creating a wall of text.	1 / 3
	Total	6 / 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: 9d4a9ea

Reviewed: 6 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.