CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-goal-planner

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

58

1.42x
Quality

39%

Does it follow best practices?

Impact

87%

1.42x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-goal-planner/SKILL.md

The canonical home for this skill is agent-goal-planner in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

Quality

Content

50%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.

The body presents a well-sequenced GOAP persona with a capability list, methodology, and MCP examples, but it is undermined by a duplicated frontmatter block, abstract rather than executable guidance, and missing validation checkpoints.

Suggestions

Remove the stray second YAML block (lines 6-10) from the body; frontmatter belongs only at the top of the file and its duplication is confusing.

Make the MCP examples executable by defining inputs (e.g. `successful_plan`) or framing them as concrete templates with expected outputs, rather than illustrative pseudocode.

Add explicit validation/replanning checkpoints to the workflow (e.g. 'After each action, verify the expected effect held; if not, trigger Dynamic Replanning from the new state') to close the feedback loop.

DimensionReasoningScore

Conciseness

The body is mostly efficient with tight bullet lists, but it opens by restating the description and carries a redundant stray YAML frontmatter block (name/description/color) that wastes tokens and adds noise.

3 / 5

Actionability

The methodology is abstract and the MCP JavaScript examples are illustrative rather than executable (e.g. referencing an undefined `successful_plan`), so concrete guidance is present but incomplete.

3 / 5

Workflow Clarity

A clear 5-step sequence with an OODA loop is present, but there are no concrete validation checkpoints or error-recovery feedback loops for when actions fail.

3 / 5

Progressive Disclosure

Content is organized into labeled sections in a single file with no bundle files, but the duplicate frontmatter block at the top of the body is a structural defect that hurts navigation.

3 / 5

Total

12

/

20

Passed

Description

28%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.

The frontmatter description is low-quality boilerplate that names the skill and its invocation syntax but does not explain what GOAP planning it performs or when to use it. It lacks both concrete capabilities and explicit trigger guidance.

Suggestions

Rewrite the description to state concrete actions, e.g. 'Creates and adapts multi-step action plans to achieve complex goals using GOAP/A* search. Use when the user needs to plan a sequence of actions to reach an objective, decompose a goal into sub-goals, or replan after a failed step.'

Add an explicit 'Use when...' clause with natural trigger phrases users would actually say (e.g. 'plan steps to reach a goal', 'replan after failure', 'break down a complex objective').

Drop the invocation-syntax filler ('invoke with $agent-goal-planner') which is not a natural trigger term and wastes the description budget.

DimensionReasoningScore

Specificity

The description only names the domain ("goal-planner") with no concrete actions described; it reads as boilerplate ("Agent skill for goal-planner") rather than enumerating what the skill does.

2 / 5

Completeness

It gives only a vague 'what' (an agent skill for goal-planning) and entirely lacks a 'when' / 'Use when...' clause, matching the anchor for a vague what with no when.

2 / 5

Trigger Term Quality

The only terms are the skill name and invocation syntax ("invoke with $agent-goal-planner"), which are technical/boilerplate rather than natural phrases a user would say when they need this skill.

2 / 5

Distinctiveness Conflict Risk

It is tied to a specific named skill (goal-planner), making it somewhat distinguishable, but the generic boilerplate phrasing could still overlap with other planning-related skills.

3 / 5

Total

9

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/ruflo
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.