skill-creator

Guide for creating effective skills. Use when creating or updating a skill.

Quality

73%

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 ./runtime/harnesses/src/embedded-skills/skill-creator/SKILL.md

Quality

Content

72%

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

A concise, well-organized guide that avoids explaining concepts Claude already knows and provides a concrete SKILL.md template. It is held back by abstract procedural steps and an implicit rather than explicit validation/feedback loop.

Suggestions

Replace abstract steps like 'Clarify the task' and 'Validate with a real invocation path' with concrete actions, e.g., 'Ask the user for 2-3 example inputs/outputs' and 'Run the skill on a sample invocation and check the output matches the template'.

Add an explicit validation checkpoint with a feedback loop, e.g., 'If the generated SKILL.md is missing required frontmatter, add it and re-check before finishing'.

Dimension	Reasoning	Score
Conciseness	The body is a lean ~45-line workflow with a compact template, assumes Claude's competence, and contains no padding or explanation of already-known concepts.	3 / 3
Actionability	The SKILL.md template and explicit frontmatter format rules are concrete and copy-paste ready, but several workflow steps ('Clarify the task', 'Define minimal reusable structure', 'Validate with a real invocation path') are abstract direction without concrete methods.	2 / 3
Workflow Clarity	A clear numbered 1-10 sequence is present with validation (step 9) and iteration (step 10) mentioned, but there is no explicit validation checkpoint with a concrete method or an error-recovery feedback loop.	2 / 3
Progressive Disclosure	At under 50 lines with no external references needed and well-organized sections (headings, numbered workflow, fenced template), it meets the simple-skill allowance for score 3.	3 / 3
	Total	10 / 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.

A clear, third-person description that answers both what it does and when to use it, with a distinct niche. Its main weakness is limited specificity and trigger-term coverage, naming only two generic actions.

Suggestions

List more concrete actions (e.g., 'define structure, write frontmatter, validate format, iterate from feedback') to lift specificity toward score 3.

Broaden trigger terms beyond create/update (e.g., 'author, scaffold, or update a reusable skill') to improve natural-keyword coverage.

Dimension	Reasoning	Score
Specificity	It names the domain (creating skills) and the actions 'creating' and 'updating', but these are generic high-level verbs rather than multiple specific concrete actions as the score-3 anchor requires.	2 / 3
Completeness	It states the what ('Guide for creating effective skills') and an explicit when ('Use when creating or updating a skill'), matching the score-3 anchor for both.	3 / 3
Trigger Term Quality	'Use when creating or updating a skill' uses natural phrasing users would say, but coverage is limited to those two variations with no common alternatives.	2 / 3
Distinctiveness Conflict Risk	The skill-authoring niche is clear and the trigger is distinct from other skills' triggers, making mis-routing unlikely.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: holaboss-ai/holaOS
Path: runtime/harnesses/src/embedded-skills/skill-creator/SKILL.md
Commit: 74c7b6f

Reviewed: 6 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.