skillify

Auto-create new skills from repetitive workflows. When you notice yourself doing the same multi-step process repeatedly, extract it into a reusable SKILL.md that any agent can use.

Quality

75%

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 ./.agents/skills/skillify/SKILL.md

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 a well-organized, actionable instruction skill with a clear sequenced protocol and verification checkpoint; its only weakness is minor redundancy between the candidate-selection and quality-checklist sections.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and table/checklist-driven and assumes Claude's competence, but the "When to Skillify" good/bad candidate list and the "Quality Checklist" overlap on uniqueness and reusability, so it could be tightened.	2 / 3
Actionability	It provides a copy-paste-ready SKILL.md template, a concrete placement path (.agents/skills/[skill-name]/SKILL.md), and a concrete verification checklist, giving fully actionable guidance for an instruction-only skill.	3 / 3
Workflow Clarity	The Skill Creation Protocol is a clearly sequenced four-step process (Identify → Generate → Place → Verify) with an explicit validation checklist as the final checkpoint.	3 / 3
Progressive Disclosure	No bundle files exist and none are needed; the self-contained meta-skill is well-organized into clearly headed sections (When to Skillify, Protocol, Naming, Quality Checklist) with no content warranting a separate file.	3 / 3
	Total	11 / 12 Passed

Description

65%

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 communicates a distinctive meta-capability with both what and when, but its trigger is framed as second-person self-observation rather than natural user language, and the second-person voice drags down specificity per the rubric guidelines.

Suggestions

Rewrite in third person to avoid the specificity penalty, e.g. "Auto-creates reusable skills from repetitive multi-step workflows and extracts them into a SKILL.md any agent can use."

Surface natural user trigger phrases in the description, e.g. "Use when the user says 'make this a skill', 'create a skill for this', or 'I keep doing this same thing'."

List the concrete actions more distinctly (e.g. identify the repeated pattern, generate a SKILL.md from a template, place and verify it) to push specificity toward the top anchor.

Dimension	Reasoning	Score
Specificity	The description names concrete actions ("Auto-create new skills", "extract it into a reusable SKILL.md"), which would land at 2, but it uses second-person voice ("When you notice yourself doing the same multi-step process repeatedly"), triggering the required -1 specificity penalty.	1 / 3
Completeness	It clearly answers both what ("Auto-create new skills from repetitive workflows... extract it into a reusable SKILL.md") and when ("When you notice yourself doing the same multi-step process repeatedly"), providing an explicit trigger clause.	3 / 3
Trigger Term Quality	It includes relevant terms ("repetitive workflows", "multi-step process", "reusable SKILL.md") but frames the trigger as agent self-observation rather than natural user phrasings like "make this a skill", so common variations are missing.	2 / 3
Distinctiveness Conflict Risk	The skill-creation-from-repetition niche is distinctive and the trigger (repetitive multi-step pattern to be extracted into a skill) is unlikely to fire for unrelated skills.	3 / 3
	Total	9 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/skillify/SKILL.md
Commit: 04514f0

Reviewed: about 12 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.