skill-creator

Guide for creating effective skills. Use when creating a new skill (or updating an existing skill) that extends an agent’s capabilities with specialized knowledge, workflows, or tool integrations.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/builtin-skills/skills/skill-creator/SKILL.md

Quality

Content

67%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.

The body is a well-structured, actionable guide with a clear sequenced workflow, real scripts, and properly signaled reference files. Its main weakness is moderate verbosity in the introductory and principle sections.

Suggestions

Tighten the 'About Skills' introduction and remove the 'onboarding guides' analogy and redundant conciseness emphasis to reduce token cost.

Move the full progressive-disclosure pattern examples (the directory trees and markdown templates) into a reference file, keeping only the selection guidance inline in SKILL.md.

Add an explicit validation/test checkpoint within Step 4 (edit) beyond the packaging-time validation, since script testing is mentioned only briefly.

Dimension	Reasoning	Score
Conciseness	Mostly efficient procedural guidance, but the 'About Skills' intro, the 'onboarding guides' analogy, and repeated conciseness exhortations add padding that could be trimmed without losing clarity.	3 / 5
Actionability	Provides concrete, real commands (scripts/init_skill.py, scripts/package_skill.py) and markdown examples for descriptions and disclosure patterns, with only minor gaps in executable detail.	4 / 5
Workflow Clarity	A clear 6-step sequenced process with an explicit validate->fix->retry feedback loop in the packaging step; not every step has its own checkpoint, so it stops short of a full 5.	4 / 5
Progressive Disclosure	References two real one-level-deep files (references/workflows.md, references/output-patterns.md) that are clearly signaled and organized for discovery, though the body still inlines several full pattern examples that could live in references.	4 / 5
	Total	15 / 20 Passed

Description

73%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.

The description clearly states what the skill does and when to use it with a concrete trigger, occupying a distinct niche. It could broaden trigger synonyms and describe more concrete actions rather than content categories.

Suggestions

Add natural trigger synonyms like 'build a skill' or 'make a skill' to broaden keyword coverage.

Replace the content-category list ('specialized knowledge, workflows, or tool integrations') with concrete actions the skill performs (e.g., 'scaffold, write, validate, and package a skill').

Expand the 'Use when...' clause with a few more concrete triggering contexts (e.g., 'when adding bundled scripts, references, or assets to an existing skill').

Dimension	Reasoning	Score
Specificity	Names the domain ('creating effective skills') and concrete variations ('creating a new skill', 'updating an existing skill'), but 'specialized knowledge, workflows, or tool integrations' describes skill contents rather than concrete actions the skill performs, so coverage is not comprehensive.	3 / 5
Completeness	Explicitly answers both what ('Guide for creating effective skills') and when ('Use when creating a new skill (or updating an existing skill)...') with a concrete trigger, though the trigger set is narrow rather than broad.	4 / 5
Trigger Term Quality	Includes natural phrases a user would say ('creating a new skill', 'updating an existing skill'), but misses common synonyms such as 'build a skill' or 'make a skill'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (skill creation/meta-authoring) with distinct triggers and minimal overlap risk against domain-specific skills.	5 / 5
	Total	16 / 20 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
relative_links	Relative link issues: 6 missing	Warning
referenced_paths_exist	Referenced path issues: 12 missing	Warning

	Total	14 / 16 Passed

Repository: shareAI-lab/Kode-CLI
Path: packages/builtin-skills/skills/skill-creator/SKILL.md
Commit: c7f6fcc

Reviewed: 3 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.