write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
67
80%
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/productivity/write-a-skill/SKILL.mdQuality
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 solid description that clearly communicates both what the skill does and when to use it, with good trigger terms. Its main weakness is that the capability description uses somewhat abstract terms ('proper structure', 'progressive disclosure', 'bundled resources') rather than listing concrete actions. Overall it performs well for skill selection purposes.
Suggestions
Replace abstract terms like 'proper structure' and 'progressive disclosure' with more concrete actions, e.g., 'generate YAML frontmatter, write step-by-step instructions, create companion resource files.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (agent skills) and mentions some structural aspects ('proper structure, progressive disclosure, bundled resources'), but these are somewhat abstract rather than concrete actions. It doesn't list specific steps like 'generate YAML frontmatter, write markdown instructions, create resource files.' | 2 / 3 |
Completeness | Clearly answers both 'what' (create new agent skills with proper structure, progressive disclosure, and bundled resources) and 'when' (Use when user wants to create, write, or build a new skill) with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'create', 'write', 'build', 'new skill'. These are common, natural phrases a user would use when requesting this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | The niche of creating 'agent skills' is quite specific and distinct. The trigger terms 'create/write/build a new skill' are unlikely to conflict with other skills unless there's another skill-creation tool, which would be unusual. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid meta-skill for creating new skills, with excellent workflow clarity and progressive disclosure. Its main weaknesses are moderate verbosity in the description requirements section and a lack of fully concrete, executable examples—the template is a skeleton rather than a working, filled-in example that demonstrates the principles it teaches. The decision criteria sections (when to split, when to add scripts) are practical and well-placed.
Suggestions
Add a complete, filled-in example of a finished SKILL.md (not just the template skeleton) to demonstrate the principles in action and improve actionability.
Trim the 'Description Requirements' section—the explanation of how the agent uses descriptions is something Claude already understands; keep just the format rules, good example, and bad example.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary explanation, such as the 'Description Requirements' section which over-explains what a description is and how the agent uses it. The 'Bad example' explanation is also somewhat verbose. However, most sections are reasonably tight. | 2 / 3 |
Actionability | Provides a clear template and directory structure, but the guidance is more structural/procedural than executable. There are no concrete, copy-paste-ready code examples or commands—the SKILL.md template is a skeleton rather than a working example. The process steps are checklists rather than executable instructions. | 2 / 3 |
Workflow Clarity | The three-step process (gather requirements → draft → review) is clearly sequenced with specific sub-steps. The review checklist at the end serves as an explicit validation checkpoint. The 'When to Add Scripts' and 'When to Split Files' sections provide clear decision criteria for branching paths. | 3 / 3 |
Progressive Disclosure | The skill is well-organized with clear sections that progress from process to structure to template to specific guidance topics. For a standalone skill with no bundle files, the content is appropriately structured with distinct, well-labeled sections and no deeply nested references. | 3 / 3 |
Total | 10 / 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
- mattpocock/skills
- Commit
aaf2453
- 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.