Name: agent-planner
Rating: 60 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-planner

Agent skill for planner - invoke with $agent-planner

1.43x

Quality

41%

Does it follow best practices?

Impact

92%

1.43x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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

Quality

Content

53%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 is well-structured with a useful output template and MCP integration examples, but it mixes concrete artifacts with abstract process prose and generic best-practice padding. Validation feedback loops are named but not actually wired into the workflow.

Suggestions

Replace abstract Planning Process bullets with concrete, executable steps and tighten or remove the generic 'Best Practices' SMART list and closing platitude.

Make MCP snippets valid and copy-pasteable, or explicitly label them as illustrative pseudocode with a pointer to a runnable reference.

Add an explicit validation checkpoint (e.g. 'Review the plan against success_criteria before publishing; revise gaps') to close the workflow feedback loop.

Dimension	Reasoning	Score
Conciseness	The core planning guidance and output template are reasonably efficient, but the 'Best Practices' SMART-style bullets and the closing platitude ('A good plan executed now...') restate generic knowledge Claude already has, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	A concrete YAML output template and MCP tool examples are provided, but the process steps are abstract ('Analyze the complete scope', 'Break down into subtasks') and the MCP snippets are pseudo-syntax rather than valid executable code, matching 'some concrete guidance but incomplete; pseudocode instead of executable code'.	3 / 5
Workflow Clarity	The five-phase Planning Process gives a clear sequence, but validation is only mentioned abstractly ('Build in validation checkpoints') with no explicit validate-then-proceed feedback loop, fitting 'steps listed but validation gaps; checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	The single file is well-organized with clear section headers and no nested external references needed; it is slightly long with the MCP examples inlined, fitting 'good structure; most content appropriately placed; minor organization gaps'.	4 / 5
	Total	13 / 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 description is thin and mechanism-focused: it names the planner domain and an invocation syntax but never states concrete capabilities or a natural 'use when' trigger. It reads as a routing label rather than a capability statement.

Suggestions

Add concrete actions, e.g. 'Decomposes complex requests into atomic tasks, maps dependencies, estimates timelines, and flags risks.'

Replace the '$agent-planner' invocation syntax with a natural 'Use when...' clause such as 'Use when breaking down a multi-step project into an executable plan.'

Include common trigger phrases users would actually say (planning, task breakdown, project timeline, dependency map) to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	The phrase 'Agent skill for planner' names the planning domain but describes no concrete actions (e.g. decompose tasks, map dependencies), matching the 'names the domain but actions are minimal or generic' anchor; it does not reach the 1-2 concrete actions required for a 3.	2 / 5
Completeness	The 'what' is vague (just 'planner') and there is no 'Use when...' clause; 'invoke with $agent-planner' is a trigger mechanism, not a use-case trigger, so it matches 'has a vague what and no when'.	2 / 5
Trigger Term Quality	'planner' is the only natural keyword; '- invoke with $agent-planner' is technical invocation syntax users would not naturally say, fitting 'one or two generic keywords; missing the natural phrases users say' rather than the broader coverage of a 3.	2 / 5
Distinctiveness Conflict Risk	'planner' / '$agent-planner' carves out a planning/orchestration niche that is somewhat specific, but the thin description could still overlap with other planning or orchestration skills, matching 'somewhat specific but could still overlap'.	3 / 5
	Total	9 / 20 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/ruflo
Path: .agents/skills/agent-planner/SKILL.md
Commit: fa13ee4

Reviewed: about 8 hours 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.