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 and distinctiveness. However, the specific actions described are somewhat abstract and process-oriented, and the trigger terms may not fully match how users would naturally express the need for this skill. The description could benefit from more concrete examples of what 'novel problems' look like and more natural trigger language.
Suggestions
Add more natural trigger terms users might say, such as 'teach you a new process', 'save this workflow', 'create a reusable approach', or 'no existing skill covers this'.
Make the actions more concrete by specifying outputs, e.g., 'Creates a new SKILL.md file with structured instructions, trigger conditions, and execution steps' rather than the abstract framework description.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (creating new skills) and some actions (analyze requirements, build framework, integrate risks, declare new skill), but the actions are somewhat abstract and process-oriented rather than concrete deliverables. The framework acronym 'Frame → Research → Plan → Execute' adds some specificity but is still fairly generic. | 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'). The explicit 'Use when' clause provides clear trigger guidance. | 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', 'create a workflow', 'save this process', or 'remember how to do this'. The meta-skill concept may not align with how users naturally phrase requests. | 2 / 3 |
Distinctiveness Conflict Risk | This is a clearly distinct meta-skill about creating other skills, which is a unique niche unlikely to conflict with domain-specific skills. The '[02] META' prefix and the focus on 'novel problems that existing skills can't address' make it clearly 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, explaining meta-concepts at length that Claude already understands. The core idea (identify gap → analyze → build framework → declare skill) is sound but buried under repetitive templates and placeholder-heavy scaffolding. The content would benefit enormously from being cut to ~30% of its current size and splitting the full skill template into a separate referenced file.
Suggestions
Reduce content by at least 60% — remove redundant framework diagrams (the structure appears 3+ times), eliminate explanations of obvious concepts, and consolidate the output format with the skill declaration step.
Extract the 'Skill File Template' section into a separate TEMPLATE.md file and reference it, rather than inlining ~50 lines of boilerplate markdown template.
Replace bracketed placeholders with at least one fully worked-through concrete example showing the complete flow from gap identification to final skill file output.
Add an explicit decision branch after Step 1 (Gap Analysis) — if the gap isn't justified, specify exactly what to do instead (e.g., 'use chain-flow-150 to combine existing skills').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. The skill explains meta-concepts Claude already understands (what a framework is, what gap analysis means), repeats the same information multiple times across sections (the framework structure appears 3+ times), and includes excessive template scaffolding. The 150% rule table adds no actionable value. At ~250+ lines, this could be reduced to under 80 lines without losing substance. | 1 / 3 |
Actionability | Provides structured templates with placeholder-filled steps (gap analysis, requirements, framework construction), which gives some concrete guidance. However, everything is template/pseudocode with bracketed placeholders rather than executable code or truly concrete examples. The good example at the end (live-migrate-150) is the most actionable part but is still high-level. | 2 / 3 |
Workflow Clarity | The 7-step sequence (Gap Analysis → Requirements → Framework → Risk → QA → Declaration → Approval) is clearly ordered and includes quality gates in Step 5. However, there's no explicit validation/feedback loop between steps — if the gap analysis concludes 'No', there's no clear branch. The approval step at the end is good but the intermediate checkpoints are just templates without real verification criteria. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no external references or file splitting. The full skill template, all 7 execution steps, output formats, examples, and operational rules are all inline. The skill template section alone could be a separate referenced file. No bundle files exist to offload content to, and the content doesn't attempt any structural separation. | 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
b1a95aa
- 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.