x-mindful

Use BEFORE implementation when AI has produced a plan, spec, design doc, PRD, or code-bearing proposal and you want a senior-engineer architect-review pass — walks the user through the decisions, tradeoffs, assumptions, blind spots, shape mismatches, and future-debt AI silently embedded. Surfaces "what AI did, what it picked over alternatives, what it took on, and what gets harder later" one item at a time with confirm / modify / reject / skip gates. Hard-blocks code-level details so the human stays at architectural direction.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/x-mindful/SKILL.md

Quality

Content

56%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 body is well-structured with a clear phase workflow, taxonomy, and a copy-paste-ready output envelope, but it is undermined by references to bundle files (gotchas.md and the steps/ directory) that do not exist, breaking both actionability and progressive disclosure.

Suggestions

Add the missing steps/ directory with step-01-detect.md through step-05-handoff.md, since the Phase Dispatch instructs Claude to read each step file before executing its phase.

Create gotchas.md or remove the 'load gotchas.md' item from the MANDATORY Bootstrap and References sections, so the bootstrap step does not fail.

Trim the motivational opening paragraph and de-duplicate the taxonomy between the intro and the 'What x-mindful Surfaces' table to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with purposeful tables (taxonomy, anti-triggers, phase dispatch), but the motivational opener ('AI is now fast and cheap at producing plans... What it misses is the senior-engineer instinct...') and restating of the taxonomy between the intro and the table could be tightened.	3 / 5
Actionability	The output-contract envelope template and routing/anti-trigger tables are concrete, but the per-phase execution guidance is delegated to step files (steps/step-01..05) and gotchas.md that do not exist in the bundle, leaving the actual execution incomplete from the body alone.	3 / 5
Workflow Clarity	Five phases are clearly sequenced in the dispatch table with per-phase purposes, the Phase 4 gate loop has explicit confirm/modify/reject/skip checkpoints, and a 'done' criterion plus verifier-slot resolution are defined; minor gaps come from the missing step files that hold the detailed steps.	4 / 5
Progressive Disclosure	The overview→references design is sound and the four references/*.md files are real and clearly signaled, but the body points to missing bundle paths — gotchas.md (listed under MANDATORY Bootstrap and References) and the entire steps/ directory (step-01 through step-05) — so the disclosure structure has broken links that prevent navigation to key content.	3 / 5
	Total	13 / 20 Passed

Description

87%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 specific, complete, and well-differentiated with an explicit 'Use when' clause and concrete architect-review actions. Its main weakness is second-person imperative voice ('Use BEFORE implementation') instead of the required third person, which costs it a specificity point.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('walks the user through the decisions, tradeoffs, assumptions, blind spots...', 'Surfaces... one item at a time with confirm / modify / reject / skip gates', 'Hard-blocks code-level details'), approaching comprehensive coverage; reduced from 5 to 4 because the imperative 'Use BEFORE implementation' is second-person voice rather than the required third person.	4 / 5
Completeness	Explicitly answers both what ('walks the user through... Surfaces... Hard-blocks code-level details') and when ('Use BEFORE implementation when AI has produced a plan, spec, design doc, PRD...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural-term coverage with synonyms ('plan, spec, design doc, PRD, or code-bearing proposal') and user-facing phrases ('what tradeoffs did AI silently pick', 'what gets harder later'), but a few of the most natural utterances from the body (e.g. 'what could break') are absent from the description itself.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (pre-implementation architect-review gate for AI-generated plans, hard-blocking code-level detail) that is explicitly contrasted with x-review/x-guide, giving it distinct triggers and minimal conflict risk.	5 / 5
	Total	18 / 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-mindful/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.