agent-goal-planner

Agent skill for goal-planner - invoke with $agent-goal-planner

1.42x

Quality

Does it follow best practices?

Impact

87%

1.42x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-goal-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 functions more as an invocation instruction than a skill description, providing no information about what the skill does, what actions it performs, or when it should be selected. Claude would have almost no basis for choosing this skill appropriately from a list of available skills.

Suggestions

Add concrete actions the skill performs, e.g., 'Breaks down high-level objectives into actionable steps, creates milestone timelines, and tracks goal progress.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to plan goals, break down objectives, create action plans, set milestones, or organize tasks toward a target outcome.'

Remove the invocation instruction ('invoke with $agent-goal-planner') from the description and replace it with functional content that helps Claude understand the skill's purpose and when to select it.

Dimension	Reasoning	Score
Specificity	The description provides no concrete actions whatsoever. 'Agent skill for goal-planner' is entirely vague and does not describe what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states it's an 'agent skill' and how to invoke it, providing no functional or contextual information.	1 / 3
Trigger Term Quality	The only keyword is 'goal-planner', which is a technical/internal term. There are no natural user-facing trigger terms like 'plan goals', 'set objectives', 'create milestones', etc.	1 / 3
Distinctiveness Conflict Risk	The description is so generic that it could conflict with any planning, goal-setting, or agent-related skill. There are no distinct triggers or domain-specific terms to differentiate it.	1 / 3
	Total	4 / 12 Passed

Implementation

12%

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

This skill reads as a high-level conceptual description of GOAP planning rather than an actionable skill file. It spends most of its token budget explaining concepts Claude already understands (A* search, OODA loops, goal decomposition) while providing almost no concrete, executable guidance. The MCP integration examples use unclear function signatures without explaining actual tool availability or expected outputs.

Suggestions

Remove the verbose capability descriptions and conceptual explanations of GOAP/A* that Claude already knows; replace with a concise 2-3 line summary of when and how to invoke this planning approach.

Replace the abstract MCP integration examples with real, executable tool calls showing actual inputs and expected outputs for a concrete planning scenario.

Add validation checkpoints to the workflow, such as 'verify preconditions are met before executing each action' and 'check goal state satisfaction after each step' with specific verification commands.

Either create bundle files for detailed reference material (action libraries, domain modeling examples) or restructure the single file with a clear quick-start section followed by concise reference sections.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and padded with concepts Claude already knows. The lengthy descriptions of GOAP, A* search, OODA loops, and core capabilities are all things Claude is deeply familiar with. The bullet-point lists of capabilities read like a resume rather than actionable instructions. Most of this content could be eliminated.	1 / 3
Actionability	The content is almost entirely abstract description rather than concrete guidance. The MCP integration examples are pseudocode-like snippets with made-up function signatures that aren't clearly executable. There are no real commands, no actual code to run, and no specific steps Claude can follow to accomplish anything concrete.	1 / 3
Workflow Clarity	The 5-step planning methodology provides a clear sequence (State Assessment → Action Analysis → Plan Generation → Execution Monitoring → Dynamic Replanning), but it lacks any validation checkpoints, error recovery steps, or concrete feedback loops. The OODA loop is mentioned conceptually but not operationalized with actual verification steps.	2 / 3
Progressive Disclosure	The content is a monolithic wall of text with no references to external files and no bundle files to support it. Everything is inlined in a single document with no clear navigation structure or separation of overview from detailed content. There's no quick-start section or pointers to deeper resources.	1 / 3
	Total	5 / 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: ca77f83

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.