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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/super-magic/agents/skills/skill-creator/SKILL.md

Quality

Content

62%Weight 40%Scale 1-5

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

A well-structured, actionable skill-creation workflow with concrete commands and clear phases, undermined by moderate verbosity and inline detail that should be offloaded to the existing reference files. Navigation to references is signaled in prose but not linked, and one reference file is orphaned.

Suggestions

Move the full packaging-validator rules and the detailed package/upload CLI argument tables into a reference file (e.g. references/packaging.md) and keep SKILL.md to a one-line pointer plus the single canonical command per mode.

Trim repeated Table-of-Contents echo lines and consolidate the three near-duplicate packaging blocks (package-only, package+upload, package-then-upload) into one table or one block with a flag toggle to cut ~60-80 lines.

Convert plain-text reference mentions to markdown links (e.g. [system-tools.md](references/system-tools.md)) and either reference script-output-for-super-magic.md from the relevant phase or remove it, so every bundle file is reachable and navigation is one-level-deep.

Dimension	Reasoning	Score
Conciseness	The ~380-line body is mostly efficient and assumes Claude's intelligence, but it carries noticeable padding — repeated table-of-contents echoes, redundant 'Important'/'Note' callouts, near-duplicate packaging blocks, and a full validator rules section that could live in the script — placing it between 'mostly efficient' and 'noticeably verbose'.	3 / 5
Actionability	Guidance is largely executable — concrete package/validate/aggregate commands with absolute-path placeholders and working code snippets for tool calls — with only minor gaps (e.g., evals test/grade flow is described procedurally rather than as a ready-to-run command).	4 / 5
Workflow Clarity	An explicit 8-phase workflow with clear sequencing and several validation checkpoints (plan confirm, conflict check, quick_validate auto-run, validation-fail retry); a few checkpoints are advisory rather than enforced, so it is above the midpoint but not a clean 5.	4 / 5
Progressive Disclosure	Structure is decent — three real reference files (system-tools.md, schemas.md, script-output-for-super-magic.md) and a scripts/ dir are present and most body references resolve — but the body inlines substantial detail (full validator rules, packaging arg lists, tool-call format tutorial) that belongs in references, references are plain-text not links, and script-output-for-super-magic.md is never referenced from the body.	3 / 5
	Total	14 / 20 Passed

Description

96%Weight 40%Scale 1-5

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 conveys a broad capability set, explicit trigger conditions, and a rich set of natural example phrases. It is comprehensive on what and when, with only minor breadth-related overlap risk.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete actions ('create', 'modify', 'evaluate', 'package', 'upload', 'benchmark', 'optimize') and then drills into specific sub-tasks like description triggering accuracy and zip packaging, giving comprehensive coverage.	5 / 5
Completeness	Both 'what' (the capability summary sentence) and 'when' (the explicit 'Use when...' clause plus five 'Also use when user says...' example phrases) are answered clearly and concretely.	5 / 5
Trigger Term Quality	It packs in natural user phrasings — 'create a skill from scratch', 'make a skill for X', 'turn this into a reusable skill', 'package this skill', 'upload to my skill library' — covering common synonyms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The skill's niche (skill authoring/lifecycle) is fairly distinct, but the verbs 'create', 'modify', 'optimize' are broad and could create minor overlap with general-purpose or refactoring skills; trigger phrases help, so it stays at 4 rather than 5.	4 / 5
	Total	19 / 20 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: dtyq/magic
Path: backend/super-magic/agents/skills/skill-creator/SKILL.md
Commit: f9973c5

Reviewed: 2 days 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.