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.

1.62x

Quality

—

Does it follow best practices?

Impact

96%

1.62x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

47%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content provides a clear, well-gated workflow but is undermined by verbose placeholder scaffolding and abstract templates that restate structure redundantly.

Suggestions

Collapse the redundant structure derivations into one canonical template and strip ASCII trees and emoji headers that add tokens without information.

Replace fill-in-the-blank placeholders with at least one fully worked concrete example skill so the guidance is actionable rather than schematic.

Dimension	Reasoning	Score
Conciseness	The body is heavily padded with ASCII-tree scaffolding, emoji headers, and fill-in-the-blank placeholder templates that re-derive the same structure multiple times (Construction Framework, 7-step Execution Protocol, and a separate Skill File Template).	1 / 3
Actionability	Steps are structured templates with clear scaffolding, but they consist of bracketed placeholders like '[Setup step 1]' and '[Unique aspect 1]' rather than executable, copy-paste-ready guidance.	2 / 3
Workflow Clarity	The 7-step protocol (GAP ANALYSIS → USER APPROVAL) is a clearly numbered sequence with explicit quality gates ('After Frame: [What must be true]') and an approval checkpoint.	3 / 3
Progressive Disclosure	The skill is a self-contained single file with no bundle references, and while it is sectioned, large template blocks that could be split out sit inline with no overview-to-detail layering.	2 / 3
	Total	8 / 12 Passed

Description

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 is complete and distinct with explicit what-and-when guidance, but its action language is abstract and its trigger terms miss natural user phrasings.

Suggestions

Replace abstract verbs with concrete actions, e.g. 'Drafts a SKILL.md with frontmatter, framework steps, and risk table' instead of 'build framework'.

Add natural trigger terms users would actually say, such as 'no skill fits', 'create a new skill', or 'reusable workflow'.

Dimension	Reasoning	Score
Specificity	Lists several named actions ('Analyze unique requirements', 'build framework (Frame → Research → Plan → Execute)', 'integrate risks', 'declare new skill') but they are abstract meta-level verbs rather than concrete technical actions like 'Extract text and tables'.	2 / 3
Completeness	It explicitly states both what the skill does (create/analyze/build/integrate/declare) and when to use it ('Use when facing novel problems that existing skills can't address').	3 / 3
Trigger Term Quality	The 'Use when facing novel problems that existing skills can't address' clause offers relevant triggers, but phrases like 'novel problems' are abstract and miss common variations a user would naturally say.	2 / 3
Distinctiveness Conflict Risk	The meta skill-forge niche ('Create new skills when existing ones don't cover the task') is clearly distinct from operational skills and unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: majiayu000/claude-skill-registry
Commit: 8271354

Reviewed: about 18 hours ago

Table of Contents

Discovery Implementation Validation

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.