agent-planner

Agent skill for planner - invoke with $agent-planner

1.43x

Quality

25%

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

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 is a competently structured planning skill with a concrete YAML output schema and executable MCP integration examples, but it is padded with generic best-practice advice Claude already knows and lacks validation checkpoints in its process. No bundle files are referenced, so all content is inline.

Suggestions

Cut the 'Best Practices' and 'Collaboration Guidelines' sections, which restate SMART-criteria and generic coordination advice Claude already knows, to improve token efficiency.

Add an explicit validation/feedback checkpoint to the Planning Process (e.g. 'After decomposition, verify every subtask has defined inputs/outputs before proceeding to dependency analysis').

Move the detailed MCP tool integration reference and the full YAML output schema into separate reference files linked from the body, leaving a concise overview in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body provides a concrete YAML output format and MCP code examples, but sections like 'Best Practices' ('Specific and actionable, Measurable and time-bound...') and 'Collaboration Guidelines' restate generic SMART/advice concepts Claude already knows, fitting the score-2 anchor of mostly efficient with some unnecessary explanation.	2 / 3
Actionability	There is concrete, copy-pasteable guidance (the YAML plan template and the mcp__claude-flow__ javascript blocks), but large portions ('Identify key objectives', 'Map inter-task dependencies') are abstract description rather than executable instruction, matching score 2's 'some concrete guidance but incomplete'.	2 / 3
Workflow Clarity	The 'Planning Process' section sequences five numbered steps (Initial Assessment through Risk Mitigation), but the steps are abstract with no explicit validation checkpoints or feedback loops, fitting the score-2 anchor 'sequence present but checkpoints missing or implicit'.	2 / 3
Progressive Disclosure	The file is organized into clear sections, but at 120+ lines it is a monolithic single file with no bundle references — content such as the MCP tool integration reference and output-format spec is inlined rather than split into separate files, matching the score-2 anchor of structure present but content that should be separate is inline.	2 / 3
	Total	8 / 12 Passed

Description

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 a minimal invocation label rather than a capability statement: it states no concrete actions, includes no natural trigger terms, and answers neither what the skill does nor when to use it. It scores at the floor of the scale across all dimensions.

Suggestions

Replace the description with concrete actions the planner performs, e.g. 'Decomposes complex requests into subtasks, maps dependencies, and produces a phased execution plan with timelines and risks.'

Add an explicit trigger clause such as 'Use when the user asks to plan a multi-step task, break work into phases, or sequence dependent subtasks.'

Include natural trigger terms users would actually say (e.g. 'plan', 'break down', 'timeline', 'dependencies', 'task sequence') instead of the technical '$agent-planner' invocation syntax.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for planner' names only a domain and offers no concrete actions, matching the score-1 anchor 'Vague or no actions; abstract language'; it does not reach score 2 because no specific actions are named.	1 / 3
Completeness	It answers neither what the skill does (no actions) nor when to use it (no 'Use when...' clause), matching the score-1 anchor 'Missing what OR when'; the missing trigger clause also caps completeness well below 2.	1 / 3
Trigger Term Quality	'invoke with $agent-planner' is technical invocation syntax rather than natural language a user would say, and 'planner' is generic, fitting the score-1 anchor of overly generic/technical jargon with no natural keywords.	1 / 3
Distinctiveness Conflict Risk	'Agent skill for planner' is very generic and would overlap with many planning-related skills, matching the score-1 anchor 'Very generic; would conflict with many skills'; no distinct niche triggers are present.	1 / 3
	Total	4 / 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/ruflo
Path: .agents/skills/agent-planner/SKILL.md
Commit: 26c35b5

Reviewed: about 6 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.