skillify

Creates release-ready skill packages from proven workflows by drafting SKILL.md frontmatter, trigger-rich instructions, references/contract.yaml, eval scenarios, task profile, and validation commands. Use when the user asks to create a skill, skillify a workflow, package a process, write SKILL.md, make a reusable skill template, or prepare a skill for release checks.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

92%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 content is a tightly structured, action-oriented scaffolding skill: exact commands, an ordered validation ladder with feedback loops, and a real one-level-deep reference bundle that backs every link. The only soft spot is mild verbosity in the First-Principles Gate and some repeated gate-spend guidance.

Suggestions

Collapse the repeated 'do not spend a Tessl live run until internal evidence predicts >=90' / 'do not substitute dry-run for SDK handoff' guidance so it appears once (in Validation) rather than re-stated across the Workflow and template references.

Tighten the First-Principles Gate into a compact checklist; several labeled fields ('Rejected copied assumption', 'Rejected alternatives', 'Fundamental constraints') overlap and could merge without losing the gate's force.

The Validation ladder's step 8 and step 9 Tessl receipts are described twice in the body's prose; keep the canonical wording in the numbered ladder and reference it from the narrative paragraphs.

Dimension	Reasoning	Score
Conciseness	The body is dense and avoids explaining concepts Claude already knows, and the Workflow points to the Validation section rather than duplicating it; the First-Principles Gate's many labeled fields and some repeated fail-fast/Tessl-spend guidance could still be trimmed. Efficient with minor instances of over-explanation.	4 / 5
Actionability	Provides copy-paste-ready exact commands ('./bin/ask skills audit <skill-path> --level strict --json --robot'), concrete file paths for the minimal package, and a complete output YAML template covering the common cases.	5 / 5
Workflow Clarity	A 10-step numbered Workflow is clearly sequenced with explicit validation checkpoints ('Run strict audit. If it fails, fix that failure before broader validation'), a dedicated ordered gate ladder, explicit fail-fast feedback loops, and blocked-plan handling for read-only runners.	5 / 5
Progressive Disclosure	The body is an overview that signals one-level-deep references via links ('[evidence discovery](./references/evidence-discovery.md)', '[skill template](./references/skill-template.md)', '[examples](./references/examples.md)'), and the bundle confirms all referenced paths (contract.yaml, evals.yaml, task-profile.json, discovery-interview.md, evidence-discovery.md, examples.md, skill-template.md) are real files in references/.	5 / 5
	Total	19 / 20 Passed

Description

100%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 is comprehensive, third-person, and tightly scoped to skill creation: it names concrete deliverables, lists natural trigger phrases, and explicitly pairs 'what' with 'when'. No vague fluff or over-claims are present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and named artifacts ('drafting SKILL.md frontmatter, trigger-rich instructions, references/contract.yaml, eval scenarios, task profile, and validation commands'), giving comprehensive coverage rather than a single generic action.	5 / 5
Completeness	Explicitly answers both 'what' (creates release-ready skill packages by drafting the listed artifacts) and 'when' with a concrete 'Use when...' clause enumerating trigger phrases.	5 / 5
Trigger Term Quality	Provides natural, varied trigger phrasings a user would actually say ('create a skill, skillify a workflow, package a process, write SKILL.md, make a reusable skill template, or prepare a skill for release checks'), including synonyms and concrete file names.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (scaffolding release-ready skill packages) with distinct creation triggers that are unlikely to fire for the sibling refactor/install/hardening skills named in its Handoff section.	5 / 5
	Total	20 / 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: jscraik/Agent-Skills
Path: Plugins/skill-factory/skills/scaffolding_templates/skillify/SKILL.md
Commit: 2f91362

Reviewed: 1 day 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.