agent-goal-planner
Agent skill for goal-planner - invoke with $agent-goal-planner
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-goal-planner28
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
0%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 a label and invocation command without explaining what the skill does, what actions it performs, or when it should be used. Claude would have no meaningful basis for selecting this skill over others.
Suggestions
Add specific concrete actions the skill performs (e.g., 'Breaks down complex goals into actionable steps, creates milestone timelines, tracks progress toward objectives').
Include an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks to plan a project, set goals, create a roadmap, or break down tasks').
Remove the invocation command from the description and focus on capability and trigger information that helps Claude select the right skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for goal-planner' is completely abstract and does not describe 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 an invocation command with no explanation of capabilities or use cases. | 1 / 3 |
Trigger Term Quality | The only terms present are 'agent', 'goal-planner', and the invocation command. These are technical/internal terms, not natural keywords a user would say when needing goal planning assistance. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'goal-planner' is vague and could conflict with any planning, task management, or organizational skill. There are no distinct triggers to differentiate it from other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
20%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads like a conceptual overview or marketing description of GOAP rather than actionable guidance for Claude. It extensively explains planning concepts Claude already understands while providing almost no concrete, executable instructions for actually performing goal-oriented planning in practice. The MCP examples are disconnected from the methodology and lack context.
Suggestions
Replace the abstract capability lists with concrete examples showing actual state representations, action definitions with preconditions/effects, and a worked planning example
Remove explanations of well-known concepts (A*, OODA, preconditions) and instead show executable code or specific command sequences
Add a concrete workflow example: given state X, goal Y, and actions A/B/C, show the exact planning and execution steps with validation checkpoints
Connect the MCP integration examples to the methodology by showing when in the workflow each would be called and what the expected inputs/outputs are
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanations of concepts Claude already knows (A* search, OODA loops, preconditions/effects). The bullet-point lists of 'core capabilities' and methodology steps explain basic planning concepts rather than providing actionable guidance. | 1 / 3 |
Actionability | The content is almost entirely abstract description rather than concrete instruction. The MCP examples at the end are pseudocode-like snippets without context on when/how to use them, and the main body describes what GOAP is rather than how to actually implement or execute plans. | 1 / 3 |
Workflow Clarity | The 5-step methodology and OODA loop provide a sequence, but there are no validation checkpoints, no concrete examples of state transitions, and no guidance on what to do when steps fail beyond abstract 'trigger replanning'. | 2 / 3 |
Progressive Disclosure | Content is a monolithic block with no references to external files for detailed examples or advanced usage. The structure uses headers but everything is inline, and the MCP examples feel disconnected from the methodology description. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
100%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.
- Reviewed
Table of Contents
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.