CtrlK
BlogDocsLog inGet started
Tessl Logo

x-guide

Use when the user wants a complex input (file, function, directory, PRD, plan, spec, URL, pasted prose, or vague feature name) explained step by step in a comprehension-gated walkthrough — produces a persistent .x-guide/<slug>/GUIDE.md with full TOC and walks the user one part at a time, supports resume across sessions

68

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The SKILL.md body is an efficient, well-structured orchestration overview, but its actionability and workflow clarity are undercut because the step files it dispatches to are missing from the bundle and no in-body validation checkpoints are given. Progressive disclosure is partially realized through real reference files but broken by the absent step files.

Suggestions

Add the missing steps/step-01-detect.md through steps/step-05-wrap.md to the bundle, or inline the essential per-phase instructions so the core loop is actionable without external files.

State at least one explicit validation checkpoint in the body (e.g. verify progress.json against the schema after Phase 3, confirm exactly one 'current' part before each Phase 4 render) rather than relying solely on references/progress-schema.md.

List the steps/*.md files in the References section alongside the existing four reference files, or mark them as lazy-loaded, so the disclosure map is complete and navigable.

DimensionReasoningScore

Conciseness

The body is lean — dense dispatch/state/reference tables and short declarative sentences with no explanation of concepts Claude already knows, so every token earns its place.

3 / 3

Actionability

Concrete execution lives in 'Read the step file for that phase' plus four reference files, but the five referenced steps/step-0N-*.md files are absent from the bundle, leaving the core Phase 4 loop described rather than concretely instructed.

2 / 3

Workflow Clarity

The five phases are sequenced in a clear table and state location is explicit, but the body itself names no validation/verification checkpoints; validation rules live only in references and the feedback loop is only implied at this level.

2 / 3

Progressive Disclosure

The four references/ files are present, well-signaled, and one level deep, but the Phase Dispatch table points to five steps/*.md files that do not exist in the bundle, creating a broken navigation path for the primary disclosure targets.

2 / 3

Total

9

/

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 specific, trigger-rich, complete (explicit what + when), and distinct, written in third person without padding. It is a strong model description that fully meets the rubric anchors.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'explained step by step in a comprehension-gated walkthrough', 'produces a persistent .x-guide/<slug>/GUIDE.md with full TOC', 'walks the user one part at a time', 'supports resume across sessions' — matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

Explicit 'Use when the user wants a complex input ... explained step by step' answers when, and the persistent GUIDE.md / one-part-at-a-time / resume clauses answer what, satisfying the both-what-and-when anchor.

3 / 3

Trigger Term Quality

Enumerates natural input forms a user would actually name — 'file, function, directory, PRD, plan, spec, URL, pasted prose, or vague feature name' — giving good coverage of natural trigger terms rather than technical jargon.

3 / 3

Distinctiveness Conflict Risk

The 'comprehension-gated walkthrough' framing plus the .x-guide/<slug>/GUIDE.md artifact carve a clear niche distinct from exploration or research skills, making wrong-skill triggering 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
quangtran88/x-skills
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.