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

Quality

Content

50%

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 coherent, sequenced GOAP methodology but is held back by over-explanation of known concepts, abstract rather than executable planning guidance, and a monolithic structure with no progressive disclosure.

Suggestions

Cut explanations of concepts Claude already knows (what A* is, what state spaces are, the OODA acronym) and keep only the skill-specific procedure; trim buzzword-heavy capability bullets.

Add concrete, runnable guidance for actually executing a plan step and detecting failure (e.g., specific validation commands or check calls) rather than only describing the replanning concept abstractly.

Introduce explicit validation checkpoints in the workflow (e.g., "After each action, verify observed state matches predicted effects; if not, trigger replanning") to turn implicit feedback into a concrete verify-then-proceed loop.

Dimension	Reasoning	Score
Conciseness	The body is structured, but it over-explains concepts Claude already knows (A* search, state spaces, the OODA loop) and pads the capability list with buzzwords ("intelligent algorithms," "novel solutions through creative action composition"), so it could be tightened considerably.	2 / 3
Actionability	The MCP JavaScript snippets provide some concrete shape, but the core planning methodology is abstract description ("Use A* pathfinding to search," "Evaluate paths based on cost and heuristic distance") with no executable code or concrete commands Claude could actually run to perform GOAP.	2 / 3
Workflow Clarity	The five-step methodology is clearly sequenced with sub-steps and includes a replanning feedback loop (OODA), but validation checkpoints are implicit and abstract ("Determine if replanning is needed") rather than concrete verify-then-proceed gates.	2 / 3
Progressive Disclosure	Content is a single monolithic file with organized sections but no external references or navigation; the inline capability list and MCP examples are reasonable to keep inline, yet nothing is offloaded, keeping it at "organized but monolithic."	2 / 3
	Total	8 / 12 Passed

Description

50%

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 description establishes a clear domain (GOAP planning) but relies on abstract, buzzword-heavy language and omits any "Use when..." trigger guidance, leaving it mediocre across all dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when breaking a complex objective into a sequenced action plan, when a goal requires multi-step pathfinding, or when the user mentions GOAP or action planning."

Replace abstract buzzwords ("intelligent plans," "novel solutions") with concrete actions such as "decomposes goals into preconditions/effects, searches action sequences with A*, and replans on execution failure."

Add natural-language trigger variations users would actually say ("plan to reach a goal," "figure out the steps to achieve X," "goal planning") to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the GOAP domain and a few capability areas ("adaptive replanning, multi-step reasoning, and finding optimal paths through complex state spaces") but the actions are abstract and padded with buzzwords like "intelligent plans," "novel solutions," and "creative ways" rather than concrete operations.	2 / 3
Completeness	Clearly states what the skill does (creates plans to achieve objectives) but has no "Use when..." clause or equivalent trigger guidance, capping completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes relevant terms ("Goal-Oriented Action Planning," "GOAP," "plans," "objectives," "replanning") but leans on technical jargon ("complex state spaces," "novel solutions") and misses natural user phrasings like "plan steps to reach a goal" or "break a goal into steps."	2 / 3
Distinctiveness Conflict Risk	GOAP is a recognizable niche, but generic phrasing like "multi-step reasoning" and "plans to achieve complex objectives" could overlap with general planning skills, and the absence of explicit triggers increases conflict risk.	2 / 3
	Total	8 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: 8ae8752

Reviewed: 2 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.