plan
Restate requirements, assess risks, and create step-by-step implementation plan. WAIT for user CONFIRM before touching any code.
52
40%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/plan/SKILL.mdQuality
Discovery
17%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 outlines a planning-before-coding workflow but is too process-oriented and lacks natural trigger terms users would actually say. It is missing an explicit 'Use when...' clause, making it difficult for Claude to know when to select this skill from a large pool. The behavioral instruction about waiting for confirmation is an internal process detail rather than a useful selection signal.
Suggestions
Add a 'Use when...' clause with natural trigger terms like 'plan implementation', 'break down this task', 'help me think through this feature before coding', 'implementation strategy'.
Include more specific, user-facing keywords such as 'feature planning', 'task breakdown', 'pre-coding analysis', 'implementation steps'.
Separate behavioral instructions (like 'WAIT for user CONFIRM') from the description — the description should focus on what the skill does and when to use it, not internal process rules.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names some actions ('restate requirements', 'assess risks', 'create step-by-step implementation plan') but they are somewhat generic and not deeply concrete. The behavioral instruction 'WAIT for user CONFIRM before touching any code' describes process rather than capability. | 2 / 3 |
Completeness | The description addresses 'what' at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1. | 1 / 3 |
Trigger Term Quality | No natural user-facing trigger terms are included. Users would not typically say 'restate requirements' or 'assess risks' — they might say 'plan this feature', 'help me implement', or 'break this down'. The description lacks keywords a user would naturally use. | 1 / 3 |
Distinctiveness Conflict Risk | The combination of requirements restating, risk assessment, and planning before coding is somewhat distinctive, but 'implementation plan' and 'assess risks' are broad enough to overlap with general coding assistance or project management skills. | 2 / 3 |
Total | 6 / 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 clearly communicates the planning workflow and the critical confirmation gate, which is its strongest aspect. However, it leans toward describing behavior rather than providing concrete, actionable instructions Claude can execute (no actual tool calls, prompts, or templates). There's moderate verbosity with sections that explain things Claude could infer, like when to use a planning step.
Suggestions
Replace the descriptive 'How It Works' section with a concrete template or structured prompt that Claude should follow when generating a plan, making it directly actionable.
Remove or significantly condense the 'When to Use' section—Claude can infer appropriate contexts from the skill description.
Add a concrete output schema or checklist format that the plan MUST follow, rather than just showing one example.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary sections like 'What This Skill Does' which largely repeats the workflow, and 'When to Use' which explains obvious scenarios Claude could infer. The example output is helpful but lengthy. Some tightening is possible. | 2 / 3 |
Actionability | The skill describes what the planner agent does but lacks concrete executable guidance—there are no actual commands, code snippets, or tool invocations. It's more of a description of behavior than actionable instructions Claude can follow to perform the planning task. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced: analyze → break down → identify dependencies → assess risks → present plan → WAIT for confirmation. The critical gate (no code until confirmation) is explicitly stated and emphasized, and modification feedback loops are provided. | 3 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections and references to related commands at the end. However, the large example output block is inline when it could be separated, and the 'When to Use' and 'How It Works' sections add bulk that could be condensed or linked out. | 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.
- Repository
- sc30gsw/claude-code-customes
- Commit
7aff694
- 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.