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
Quality
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 ./skills/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.
This description has good structure with explicit 'what' and 'when' components, and occupies a distinct meta-level niche. However, the framework terminology (Frame → Research → Plan → Execute) is somewhat abstract, and the trigger terms could better match natural user language for requesting new skill creation.
Suggestions
Add natural trigger terms users might say, such as 'create a skill', 'teach Claude', 'add capability', 'custom workflow', or 'new automation'
Expand the framework steps with brief concrete examples (e.g., 'Frame the problem scope, Research existing patterns, Plan implementation, Execute and test')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (skill creation) and some actions ('Analyze unique requirements', 'build framework', 'integrate risks', 'declare new skill'), but the framework acronym (Frame → Research → Plan → Execute) is somewhat abstract without concrete examples of what each step entails. | 2 / 3 |
Completeness | Clearly answers both what ('Create new skills', 'Analyze unique 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 'novel problems', 'new skills', and 'existing skills can't address', but lacks natural user phrases like 'create a skill', 'add capability', 'teach Claude', or 'custom workflow' that users might actually say. | 2 / 3 |
Distinctiveness Conflict Risk | Has a clear meta-level niche focused specifically on skill creation, which is distinct from task-execution skills. The '[02] META' prefix and focus on 'novel problems that existing skills can't address' creates clear boundaries. | 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 suffers from severe verbosity, explaining meta-concepts Claude already understands while providing templates that could be generated dynamically. The core idea (create new skills when gaps exist) is valid but buried under excessive templating and repetitive structure. The '150% Rule' framing adds cognitive overhead without proportional value.
Suggestions
Reduce to ~50 lines: state when to forge (gap criteria), the minimal framework (Frame/Research/Plan/Execute), and one compact example. Remove all inline templates.
Move the full skill file template to a separate SKILL_TEMPLATE.md file and reference it with a single link.
Remove explanations of what skills are and what Claude should do - focus only on the unique decision criteria for when forging is appropriate vs. using existing skills.
Add explicit validation: 'Before declaring skill complete, verify: (1) gap is genuine, (2) framework covers all phases, (3) at least one concrete example works.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines with excessive templating and repetition. The '150% Rule' concept is explained multiple times, and the skill includes lengthy templates that Claude could generate on demand. Much of this content (what a skill is, basic framework concepts) is knowledge Claude already possesses. | 1 / 3 |
Actionability | Provides concrete templates and step-by-step protocols, but they're more like fill-in-the-blank forms than executable guidance. The examples are illustrative but the actual 'how to forge a skill' is buried in verbose templating rather than clear, minimal instructions. | 2 / 3 |
Workflow Clarity | The 7-step process is clearly sequenced (Gap Analysis → Requirements → Framework → Risk → QA → Declaration → Approval), but validation checkpoints are implicit rather than explicit. Step 7 asks for approval but doesn't specify what to do if rejected or how to iterate. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. The entire skill template, all examples, and all protocols are inline. Content that could be in separate reference files (full skill template, detailed examples) bloats the main document significantly. | 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
- Commit
6213d1a
- 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.