02-meta-skill-forge-150
[02] META. Create new skills when existing ones don't cover the task. Analyze unique requirements, build framework (Frame → Research → Plan → Execute), integrate risks, and declare new skill. Use when facing novel problems that existing skills can't address.
68
51%
Does it follow best practices?
Impact
96%
1.62xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/02-meta-skill-forge-150/SKILL.mdQuality
Discovery
75%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 adequately communicates its meta-purpose of creating new skills and includes an explicit 'Use when' clause, giving it good completeness. However, the framework steps (Frame → Research → Plan → Execute) are somewhat abstract and the trigger terms could better capture the natural language users would employ when they want to create or save a new skill. The distinctiveness is strong given its unique meta-skill niche.
Suggestions
Add more natural trigger terms users might say, such as 'teach you a new task', 'save this as a skill', 'remember how to do this', 'create a reusable workflow', or 'no existing skill for this'.
Make the framework steps more concrete by briefly explaining what each produces, e.g., 'builds a structured skill file with triggers, steps, and validation criteria'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (meta/skill creation) and some actions like 'analyze unique requirements', 'build framework', 'integrate risks', and 'declare new skill', but the framework acronym (Frame → Research → Plan → Execute) is somewhat abstract and the actions aren't fully concrete in terms of what they produce. | 2 / 3 |
Completeness | Clearly answers both 'what' (create new skills, analyze requirements, build framework, integrate risks, declare new skill) and 'when' ('Use when facing novel problems that existing skills can't address'), with an explicit trigger clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'new skills', 'novel problems', and 'existing skills can't address', but misses natural user phrases like 'teach you how to', 'learn a new task', 'save this as a skill', 'remember how to do this', or 'create a workflow'. | 2 / 3 |
Distinctiveness Conflict Risk | The meta-skill concept of creating new skills is a clearly distinct niche that is unlikely to conflict with other task-specific skills. The '[02] META' prefix and focus on novel problems without existing skill coverage makes it highly distinguishable. | 3 / 3 |
Total | 10 / 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 significantly over-engineered and verbose for what it accomplishes. The core idea—creating new skills when existing ones don't cover a task—is valid, but the execution drowns it in repetitive template scaffolding, placeholder text, and unnecessary explanations. The content would benefit enormously from being condensed to essential guidance with templates split into a separate reference file.
Suggestions
Cut content by at least 60%: remove the 'What This Skill Does' preamble, the '150% Rule' table, and redundant template sections. Focus on the core workflow and one concrete example.
Move the full Skill File Template to a separate TEMPLATE.md file and reference it with a single link, dramatically improving progressive disclosure.
Replace placeholder-heavy templates (e.g., '[Unique aspect 1]') with one fully worked-through concrete example that demonstrates the entire forge process end-to-end.
Add an explicit feedback loop: if the gap analysis concludes no new skill is needed (Step 1 says No), specify exactly what to do next instead of just stopping.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Massive amounts of template scaffolding and placeholder text that Claude doesn't need spelled out. The '150% Rule' table, 'What This Skill Does' section explaining what AI does, and extensive template boilerplate are all unnecessary padding. The same guidance could be conveyed in under 80 lines. | 1 / 3 |
Actionability | Provides structured templates with placeholder brackets (e.g., '[Unique aspect 1]', '[Challenge 1]') which give shape but are not executable or concrete. The examples section at the end provides some concrete guidance, but most of the skill is abstract fill-in-the-blank templates rather than specific, actionable instructions. | 2 / 3 |
Workflow Clarity | The 7-step sequence (Gap Analysis → Requirements → Framework Construction → Risk Integration → Quality Assurance → Skill Declaration → User Approval) is clearly ordered and includes validation checkpoints in Step 5. However, there's no explicit feedback loop for when validation fails mid-process, and the steps themselves are template shells rather than concrete validated workflows. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. The full skill template, all 7 execution steps, output formats, and examples are all inlined in a single massive document. The 'Skill File Template' section alone could be a separate reference file, as could the detailed step templates. | 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
- majiayu000/claude-skill-registry-data
- Commit
3dd3ac0
- 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.