CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-creator

Interactive guide for creating, reviewing, and improving agent skills (SKILL.md folders). Use when the user wants to build a new skill ('create a skill', 'make a skill for X', 'write a SKILL.md', 'turn this workflow into a skill'), review or improve an existing skill, fix a skill that never triggers or triggers too often, or validate a skill folder before sharing it. Do NOT use for general prompt writing, MCP server development, or editing arbitrary markdown files.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 actionable and well-sequenced with validation feedback loops, and it uses progressive disclosure correctly with real, clearly-signaled reference files. Its only weakness is minor verbosity in framing prose that could be trimmed for token efficiency.

Suggestions

Trim the opening 'A skill is a folder that teaches an agent...' paragraph, which restates context Claude already has, to improve token efficiency.

Consider moving the 'Workflow: Reviewing an Existing Skill' failure-mode list into a reference file so the main body stays focused on creation.

DimensionReasoningScore

Conciseness

Well-structured and mostly lean, but the ~150-line two-workflow body includes framing prose (e.g., 'A skill is a folder that teaches an agent how to handle a specific task or workflow') that restates context Claude already has and could be tightened.

2 / 3

Actionability

Provides executable commands (`python scripts/validate_skill.py /path/to/your-skill-name`), exact YAML frontmatter and folder-structure templates, and concrete weak/strong description examples that are copy-paste ready.

3 / 3

Workflow Clarity

Both workflows are numbered (create Steps 1–6, review Steps 1–4) with an explicit validation checkpoint (Step 5: run validator, 'Fix every ERROR') and a fix-and-iterate feedback loop in Step 6.

3 / 3

Progressive Disclosure

The body points to real, one-level-deep bundle files (references/frontmatter.md, references/patterns.md, references/testing.md, scripts/validate_skill.py) and keeps that detail out of SKILL.md, which serves as the overview.

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.

The description is exemplary: it pairs concrete capabilities with literal user trigger phrases, an explicit 'Use when' clause, and negative triggers to avoid misfiring. It is distinctive and unlikely to conflict with other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'creating, reviewing, and improving', 'build a new skill', 'review or improve an existing skill', 'fix a skill that never triggers', and 'validate a skill folder' — rather than vague capability claims.

3 / 3

Completeness

Explicitly answers WHAT (creating/reviewing/improving agent skills) and WHEN via a clear 'Use when the user wants to...' clause, reinforced by negative triggers.

3 / 3

Trigger Term Quality

Embeds literal user phrasings a person would naturally say: 'create a skill', 'make a skill for X', 'write a SKILL.md', and 'turn this workflow into a skill'.

3 / 3

Distinctiveness Conflict Risk

Targets a narrow niche (agent SKILL.md folders) with distinct trigger phrases and explicit 'Do NOT use for general prompt writing, MCP server development...' boundaries, making conflicts with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
XiaomiMiMo/MiMo-Code
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.