agent-planner
Agent skill for planner - invoke with $agent-planner
43
13%
Does it follow best practices?
Impact
92%
1.43xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-planner/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an extremely weak description that provides virtually no useful information for skill selection. It fails on every dimension: it names no concrete actions, includes no natural trigger terms, answers neither 'what' nor 'when', and is so generic it could conflict with numerous other skills. It reads more like a label than a functional description.
Suggestions
Describe what the planner actually does with specific concrete actions (e.g., 'Creates step-by-step execution plans for complex multi-step tasks, breaks down goals into subtasks, and tracks progress').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user needs to break down a complex task, create a project plan, organize steps, or coordinate multiple subtasks').
Remove the invocation syntax ('invoke with $agent-planner') from the description and replace it with domain-specific keywords that distinguish this skill from other potentially similar skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for planner' is entirely vague and abstract, giving no indication of what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. There is no explanation of capabilities and no 'Use when...' clause or equivalent trigger guidance. | 1 / 3 |
Trigger Term Quality | The only keyword is 'planner', which is generic and not a natural term users would say when needing help. The invocation command '$agent-planner' is technical syntax, not a natural trigger term. | 1 / 3 |
Distinctiveness Conflict Risk | 'Planner' is extremely generic and could overlap with any skill involving planning, scheduling, project management, task organization, or strategic thinking. There are no distinct triggers to differentiate it. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is heavily padded with generic planning advice that Claude already understands, making it highly token-inefficient. While it provides some useful concrete elements (YAML output format, MCP tool call examples), the majority of the content describes abstract concepts rather than providing specific, actionable instructions. The lack of validation checkpoints and the monolithic structure further weaken its effectiveness as a skill definition.
Suggestions
Cut the 'Core Responsibilities', 'Best Practices', and 'Collaboration Guidelines' sections entirely — these describe generic planning concepts Claude already knows. Focus on the specific output format and MCP tool calls.
Add validation checkpoints: after generating a plan, specify how to verify it (e.g., check all dependencies are satisfiable, verify agents exist, confirm no circular dependencies).
Split MCP tool reference examples into a separate TOOLS.md file and keep SKILL.md as a concise overview with the YAML output template and a brief workflow.
Replace the abstract 5-step 'Planning Process' with a concrete checklist that includes specific tool calls at each step, making it directly executable rather than descriptive.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanation of generic planning concepts (task decomposition, dependency analysis, risk assessment) that Claude already knows. The 'Best Practices' and 'Collaboration Guidelines' sections are generic advice that add no specific value. The content could be reduced by 60-70% without losing actionable information. | 1 / 3 |
Actionability | The MCP tool integration section provides concrete code examples with specific tool calls, and the YAML output format is a useful template. However, much of the content is abstract guidance ('Analyze the complete scope of the request', 'Identify key objectives') rather than executable instructions. The JavaScript examples appear to be illustrative rather than copy-paste ready. | 2 / 3 |
Workflow Clarity | The planning process has a clear 5-step sequence, and the output format provides structure. However, there are no validation checkpoints or feedback loops — no guidance on what to do if a plan fails validation, how to verify plan quality, or when to re-plan. For an orchestration agent that coordinates destructive or complex multi-agent operations, this is a significant gap. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files and no bundle files to support it. All content — from basic responsibilities to MCP tool examples to best practices — is inlined in a single long document with no clear navigation or separation of quick-start vs. advanced material. | 1 / 3 |
Total | 6 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ruvnet/ruflo
- Commit
844f68d
- 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.