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

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

75%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 well-structured, token-efficient orchestration layer that routes into per-phase step files and references. Its main weakness is that the substantive executable guidance lives in steps/ files that are not shipped in the bundle, so a reviewer cannot verify the actual phase mechanics.

Suggestions

Ship the steps/step-0X-*.md files (or inline the key per-phase mechanics) so the executable guidance referenced by the Phase Dispatch table is verifiable and copy-paste ready.

Add explicit validation/feedback checkpoints into the Phase 1–5 sequence (e.g., confirm progress.json is well-formed after Phase 3, re-prompt on malformed menu input) to lift workflow clarity.

Make the cross-skill bootstrap dependencies (x-shared/capability-loading.md, gotchas.md, x-gemini, x-research) explicit about which are bundled vs. expected to exist, to close the navigation gap.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no explaining what markdown, a TOC, or a PRD is — using tight tables and a state-layout diagram where every token earns its place, matching the score-5 anchor.	5 / 5
Actionability	Concrete details exist (exact MCP call signature, state file paths, phase→step-file table), but the core per-phase mechanics are offloaded to steps/step-0X-*.md files that are absent from the bundle, leaving key executable details missing per the score-3 anchor.	3 / 5
Workflow Clarity	The five phases are clearly sequenced in a dispatch table with purposes, Phase 4 is flagged as the core loop, and the status state machine with disallowed transitions provides checkpoints; only minor validation checkpoints are implicit rather than explicit, matching the score-4 anchor.	4 / 5
Progressive Disclosure	SKILL.md is a genuine overview with four real, one-level-deep reference files clearly signaled in a References section, but the referenced steps/ files are not present in the bundle — a minor navigation/organization gap per the score-4 anchor.	4 / 5
	Total	16 / 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 exemplary: it concisely states both what the skill produces and when to invoke it, with an exhaustive list of natural trigger terms and a distinctive comprehension-gated niche. No vague fluff or over-claims are present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'produces a persistent .x-guide/<slug>/GUIDE.md with full TOC', 'walks the user one part at a time', 'supports resume across sessions', 'comprehension-gated walkthrough' — giving comprehensive coverage with no real gaps, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' ('produces a persistent .x-guide/<slug>/GUIDE.md ... walks the user one part at a time') and 'when' ('Use when the user wants a complex input ... explained step by step in a comprehension-gated walkthrough') with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Enumerates natural trigger terms and synonyms a user would actually say — 'file, function, directory, PRD, plan, spec, URL, pasted prose, or vague feature name' — giving comprehensive coverage including synonyms, matching the score-5 anchor.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche — comprehension-gated linear tutoring with a persistent GUIDE.md + TOC + resume signature — and contrasts itself ('not an explorer or graph viewer'), giving distinct triggers with minimal conflict risk per the score-5 anchor.	5 / 5
	Total	20 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: quangtran88/x-skills
Path: skills/x-guide/SKILL.md
Commit: f17a69e

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.