agent-planner

Agent skill for planner - invoke with $agent-planner

1.43x

Quality

35%

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%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 and the output format is its strongest asset — a concrete, copy-paste YAML plan schema. Weaknesses are generic best-practice filler that pads token cost, pseudocode MCP examples that can't be executed as written, and a planning workflow that never validates or iterates on its own output.

Suggestions

Cut the 'Best Practices' and 'Collaboration Guidelines' sections down to the non-obvious items, and delete the closing aphorism — they restate knowledge Claude already has.

Fix the MCP examples to be actual invocations (e.g., complete tool-call syntax with correct parameter formatting) or move them to a references/ file with one verified example.

Add explicit validation checkpoints to the planning process, e.g., 'Before publishing the plan, confirm every dependency references an existing task-id and every task has an assigned agent', followed by a revise-if-invalid loop.

Dimension	Reasoning	Score
Conciseness	Sections like 'Best Practices' ('Specific and actionable', 'Measurable and time-bound', 'Realistic and achievable') and the closing aphorism 'A good plan executed now is better than a perfect plan executed never' restate planning knowledge Claude already has, matching the anchor 'mostly efficient but includes some unnecessary explanation'. Not 4 because roughly a third of the body (Best Practices, Collaboration Guidelines) is generic filler that could be trimmed without losing information.	3 / 5
Actionability	The YAML output format template is concrete and reusable, but the MCP tool examples are pseudocode — 'mcp__claude-flow__task_orchestrate { task: ... }' is not valid JavaScript and mixes object literal and call syntax — matching the anchor 'some concrete guidance but incomplete; pseudocode instead of executable code'. Not 4 because there are no complete, runnable examples and no instruction on how the MCP calls are actually invoked.	3 / 5
Workflow Clarity	The five planning phases (Initial Assessment → Task Decomposition → Dependency Analysis → Resource Allocation → Risk Mitigation) are clearly listed in sequence, but there are no validation checkpoints — nothing says to verify the plan against the original request, confirm dependencies are acyclic, or check feasibility before publishing. This matches the anchor 'steps listed but validation gaps'.	3 / 5
Progressive Disclosure	No bundle files exist (no references/, scripts/, or assets/ directories), so all ~150 lines live in SKILL.md with reasonable section headers — matching the anchor 'some structure but could be better organized'. Content like the MCP tool integration details and the output-format reference would sit more appropriately in a separate reference file; not 2 because the body is genuinely sectioned and navigable, not a wall of text.	3 / 5
	Total	12 / 20 Passed

Description

20%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 fails its core job: it identifies the skill's invocation syntax but not what the skill does or when to use it. A user (or the model selecting skills) has nothing to distinguish it from any other planning-related skill. The rich capability detail (task decomposition, dependency analysis, timeline estimation) exists only in the body and should be surfaced in the description.

Suggestions

State concrete actions in the description, e.g., 'Decomposes complex requests into phased task plans with dependencies, agent assignments, time estimates, and risk mitigations'.

Add an explicit trigger clause, e.g., 'Use when the user asks to plan a project, break work into tasks, map dependencies, or estimate timelines'.

Remove the invocation-syntax note ('$agent-planner') from the description — it consumes the character budget without helping skill selection — and replace it with natural keywords like 'task plan', 'project breakdown', 'critical path'.

Dimension	Reasoning	Score
Specificity	The description is 'Agent skill for planner - invoke with $agent-planner' — it names no concrete action whatsoever (no 'decomposes tasks', 'creates timelines', 'maps dependencies'), which matches the anchor 'entirely vague; no concrete actions'. Anchor 2 requires at least a generic action verb like 'Processes PDF files'; this has none.	1 / 5
Completeness	The 'what' is only implied vaguely ('agent skill for planner' never states what the skill actually does), and there is no 'when to use it' guidance at all — 'invoke with $agent-planner' is a syntax note, not a trigger condition. This matches anchor 2 ('has a vague what and no when') rather than anchor 1, since the domain (planning) is at least identifiable.	2 / 5
Trigger Term Quality	'planner' is one generic keyword, but the natural phrases a user would actually say ('break down this project', 'create a task plan', 'estimate timeline') are entirely missing, matching the anchor 'one or two generic keywords; missing the natural phrases users say'. Not 3 because there are no synonyms, variations, or usage-oriented terms at all.	2 / 5
Distinctiveness Conflict Risk	'planner' is a very broad term that would overlap with any planning, orchestration, or task-management skill, matching the anchor 'very broad; high overlap risk with many similar skills'. Not 3 because nothing in the description narrows the niche (e.g., 'strategic planning and task orchestration' appears only in the body, not the description).	2 / 5
	Total	7 / 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: b14c79e

Reviewed: 3 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.