Combine CLEAR (Concise, Logical, Explicit, Adaptive, Reflective) and CoVe (Chain of Verification) to write and lint agent task files that will be executed by worker agents. Use when orchestration or planning agents are producing task plans, task prompts, or TASK.md style instructions that must be unambiguous, verifiable, and resistant to hallucination.
86
Quality
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 a strong description with excellent completeness and distinctiveness. It clearly identifies its niche (agent task file creation) and provides explicit trigger conditions. The main weakness is that the specific capabilities could be more concrete - listing specific actions like 'validate task dependencies' or 'check instruction clarity' would strengthen the specificity dimension.
Suggestions
Add 2-3 more concrete actions beyond 'write and lint', such as 'validate step dependencies', 'check for ambiguous language', or 'generate verification checkpoints'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (agent task files, CLEAR/CoVe frameworks) and some actions ('write and lint'), but doesn't comprehensively list specific concrete actions like 'validate step dependencies', 'check for ambiguous instructions', or 'generate verification questions'. | 2 / 3 |
Completeness | Clearly answers both what ('Combine CLEAR and CoVe to write and lint agent task files') and when ('Use when orchestration or planning agents are producing task plans, task prompts, or TASK.md style instructions'). Has explicit 'Use when...' clause with specific triggers. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'orchestration', 'planning agents', 'task plans', 'task prompts', 'TASK.md', 'instructions'. These are terms users working with agent systems would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche targeting agent orchestration and task file creation specifically. The combination of CLEAR/CoVe frameworks, 'TASK.md', and 'worker agents' creates clear boundaries unlikely to conflict with general writing or coding skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill that provides concrete guidance for writing agent task files. The template is immediately usable and the CLEAR+CoVe framework is well-integrated with clear application criteria. Minor weaknesses include some redundancy in explanations and the monolithic structure that could benefit from progressive disclosure to separate files.
Suggestions
Remove redundant explanations of CLEAR—define the acronym once and trust Claude to remember it throughout
Consider extracting the full task template into a separate TEMPLATE.md file and referencing it, keeping SKILL.md as an overview with quick-start guidance
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some redundancy—the CLEAR acronym is explained multiple times, and some sections (like 'Your Output Responsibilities') could be tightened. The template and guidelines are useful but occasionally verbose. | 2 / 3 |
Actionability | Provides a complete, copy-paste ready task template with concrete sections, specific linting rules, and clear output expectations. The guidance is specific and executable rather than abstract. | 3 / 3 |
Workflow Clarity | Clear sequential workflow: CLEAR first, then CoVe where needed. The linting rules provide explicit validation checkpoints, and the 'Your Output Responsibilities' section defines a clear process with numbered steps and revision requirements. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear headers and logical sections, but it's a monolithic document (~200 lines) that could benefit from splitting the template and detailed guidelines into separate reference files for complex use cases. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
fd243f9
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.