Use when creating a plan using Plan model and enhancing structured design plans in Cursor Plan mode for Java implementations. Use when the user wants to create a plan, design an implementation, structure a development plan, or use plan mode for outside-in TDD, feature implementation, or refactoring work. This should trigger for requests such as Create a plan with Cursor Plan mode; Write a plan with Claude Plan mode; Design an implementation plan; Structure a development plan. Part of cursor-rules-java project
62
72%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/041-planning-plan-mode/SKILL.mdQuality
Discovery
82%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 has strong trigger term coverage and good completeness with explicit 'Use when' clauses and example phrases. However, the actual capabilities described are somewhat vague—it says it 'enhances structured design plans' without specifying concrete outputs or actions. The description is also somewhat repetitive, listing variations of 'create/design/structure a plan' multiple times without adding much new information.
Suggestions
Add more specific concrete actions describing what the skill actually produces (e.g., 'Generates step-by-step implementation plans with file-level task breakdowns, dependency ordering, and test specifications').
Reduce repetition of plan-related phrases and instead use that space to describe distinct capabilities or outputs that differentiate this from generic planning skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Java implementation plans in Cursor Plan mode) and mentions some actions like 'creating a plan', 'design an implementation', 'structure a development plan', but the actual concrete capabilities are vague—it doesn't specify what the skill produces or how it enhances plans beyond generic terms like 'enhancing structured design plans'. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (creating and enhancing structured design plans for Java implementations) and 'when' (multiple explicit 'Use when' clauses and example trigger phrases like 'Create a plan with Cursor Plan mode'). It has clear trigger guidance. | 3 / 3 |
Trigger Term Quality | Good coverage of natural trigger terms: 'create a plan', 'design an implementation', 'structure a development plan', 'plan mode', 'Cursor Plan mode', 'Claude Plan mode', 'outside-in TDD', 'feature implementation', 'refactoring'. These are terms users would naturally say when requesting planning assistance. | 3 / 3 |
Distinctiveness Conflict Risk | While it specifies 'Cursor Plan mode' and 'Java implementations' which help narrow the niche, terms like 'create a plan', 'design an implementation', and 'structure a development plan' are quite generic and could overlap with general planning or architecture skills. The coupling to 'cursor-rules-java project' helps somewhat but the broad planning language creates conflict risk. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has a well-structured interactive workflow with good validation checkpoints and clear sequencing, which is its strongest aspect. However, it lacks concrete examples (sample plan output, YAML frontmatter template, Mermaid diagram snippet) that would make it truly actionable without relying entirely on the external reference file. Some content redundancy between the intro bullets, constraints, and workflow steps could be tightened.
Suggestions
Add a concrete example of the expected plan output structure (even abbreviated) showing YAML frontmatter, a sample task list with Status column, and Execution Instructions section—this would significantly improve actionability.
Include a minimal inline example of the Mermaid diagram format expected in the Approach section, so Claude doesn't need to read the reference file for basic plan generation.
Consolidate the 'What is covered' bullet list into the workflow steps or remove it, as it largely duplicates information found in the Constraints and Workflow sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some redundancy—the 'What is covered' bullet list largely duplicates the workflow and constraints sections. The 'When to use this skill' section lists trigger phrases that are metadata-like and could be in frontmatter rather than body content. Some tightening is possible. | 2 / 3 |
Actionability | The workflow provides a clear sequence of actions but lacks concrete examples—no sample YAML frontmatter, no example Mermaid diagram, no example plan output, no executable commands beyond `date`. The guidance is specific in intent but abstract in execution; Claude would need to rely entirely on the referenced file for actual content patterns. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced (steps 0-5) with explicit validation checkpoints: validate summary before proceeding, confirm proceed before generating, confirm storage location before writing, and update status after each task execution. The feedback loop of gather→validate→confirm→generate is well-defined. | 3 / 3 |
Progressive Disclosure | The skill references `references/041-planning-plan-mode.md` for detailed guidance, which is appropriate one-level-deep disclosure. However, since no bundle files were provided, we cannot verify the reference exists or is well-structured. The skill itself could benefit from a brief inline example of the plan output format rather than deferring everything to the reference file. | 2 / 3 |
Total | 9 / 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.
3fa5789
Table of Contents
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.