skill-creator

Create, modify, evaluate, package, and upload skills. Use when users want to create a skill from scratch, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance, optimize a skill's description for better triggering accuracy, package a skill into a zip, or upload a skill to their skill library. Also use when user asks to "capture this workflow as a skill", "make a skill for X", "turn this into a reusable skill", "package this skill", or "upload to my skill library".

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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

The body is highly actionable with a clear, validated multi-phase workflow and well-structured one-level-deep references to real bundle files. Its main weakness is token efficiency: systematic inline Chinese duplication of nearly every section roughly doubles the context cost without adding distinct guidance.

Suggestions

Remove the inline "" parallel-translation blocks (or move Chinese text into a single dedicated localized file) so each section appears once — this alone roughly halves the body's token count.

Where a section's zh and English content are identical, delete the duplicate rather than maintaining both; keep localization in description-cn / a single translation reference instead.

After de-duplication, trim remaining tutorial-style prose (e.g. "This is critical for high-quality skills...") to keep only guidance that Claude would not already infer.

Dimension	Reasoning	Score
Conciseness	The body is actionable and avoids explaining basic concepts, but nearly every section is duplicated as a "<!--zh ... -->" Chinese block, roughly doubling tokens to convey the same information — it could be tightened by serving one language (or a single bilingual source) rather than inline parallel translation.	2 / 3
Actionability	Provides copy-paste-ready shell_exec commands, Python tool-call snippets, JSON/YAML/frontmatter templates, and concrete file paths and directory structures — fully executable guidance rather than vague direction.	3 / 3
Workflow Clarity	An explicit 8-phase sequence with checkpoints ("Wait for user confirmation before proceeding to Phase 4"), validation (auto-run quick_validate.py, conflict check before writing), and a fix/retry feedback loop in the Iterate phase.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview that points one level deep to real, clearly-labeled reference files (super-magic-tools.md, schemas.md) and executable scripts, all verified to exist; detailed tool docs and JSON schemas are appropriately moved out of the body.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that names concrete capabilities and provides explicit, naturally-phrased trigger conditions for both what and when. It fully satisfies the completeness and distinctiveness anchors with no over-claims or fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Create, modify, evaluate, package, and upload skills" plus "run evals", "benchmark", "optimize a skill's description", "package a skill into a zip" — matching the score-3 anchor.	3 / 3
Completeness	Explicitly answers both what (capability summary) and when ("Use when users want to..." and "Also use when user asks to...") with explicit trigger guidance.	3 / 3
Trigger Term Quality	Covers natural terms users would say, including quoted phrases like "capture this workflow as a skill", "make a skill for X", and "upload to my skill library", giving broad trigger coverage.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (skill lifecycle management) with distinctive, skill-creation-specific triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (620 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: dtyq/magic
Path: backend/super-magic/agents/skills/skill-creator/SKILL.md
Commit: 41d7ef4

Reviewed: about 13 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.