CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

A well-structured, clearly sequenced multi-phase skill with strong workflow clarity and good signaling for the reference files that exist; it is held back by verbosity in a few blocks and by core per-phase step files being referenced but missing from the bundle.

Suggestions

Either include the five steps/step-0X-*.md files in the bundle or stop referencing them as if present, so progressive disclosure and actionability are not undermined by missing targets.

Tighten the verbatim blocks — collapse the exhaustive trigger-keyword lists into representative examples plus a pointer, and shorten the full envelope example to a compact schema reference.

Trim restatement such as the repeated 'inverse of x-review / x-guide' framing and the duplicated dependency list between Bootstrap and Dependencies.

DimensionReasoningScore

Conciseness

The body is dense domain-specific spec with no Claude-known-concept padding and uses tables efficiently, but at ~160 lines it carries verbatim blocks (the long trigger-keyword lists in lines 69-73 and the full envelope example in 106-128) that could be trimmed or referenced out.

2 / 3

Actionability

Inline guidance is concrete — an exact MCP recall call, a copy-paste decision-envelope template, and explicit menu verbs — but the per-phase executable detail is delegated to steps/step-0X-*.md files that are not present in the bundle, leaving the actionable core incomplete here.

2 / 3

Workflow Clarity

Five phases are sequenced in a dispatch table with per-phase purpose, anchored by MANDATORY Bootstrap and Completion checkpoints, a Phase 4 confirm/modify/reject/skip/quit gate loop, and an x-verify completion step — clear sequence with explicit validation.

3 / 3

Progressive Disclosure

The four references/*.md files exist, are one level deep, and are well-signaled via both the References and lazy-load Bootstrap sections, but the five referenced steps/step-0X-*.md files are absent from the bundle, breaking the disclosure structure.

2 / 3

Total

9

/

12

Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific, well-triggered description with an explicit Use-when clause and a distinct niche; its only real flaw is second-person voice ('you want'), which costs it one specificity point per the rubric.

Suggestions

Rephrase in third person to avoid the second-person penalty — e.g. 'Use BEFORE implementation when a plan, spec, design doc, PRD, or code-bearing proposal has been produced and a senior-engineer architect-review pass is wanted.'

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('walks the user through the decisions, tradeoffs, assumptions, blind spots, shape mismatches, and future-debt', 'confirm / modify / reject / skip gates', 'Hard-blocks code-level details'), which is anchor-3 caliber; reduced by one per the second-person penalty for 'you want a senior-engineer architect-review pass'.

2 / 3

Completeness

Explicitly answers both: what (surfaces decisions/tradeoffs/assumptions/blind spots one item at a time with confirm/modify/reject/skip gates) and when ('Use BEFORE implementation when AI has produced a plan, spec, design doc, PRD, or code-bearing proposal').

3 / 3

Trigger Term Quality

Covers natural terms a user would actually say — 'plan, spec, design doc, PRD, or code-bearing proposal' and 'architect-review pass' — giving good trigger coverage.

3 / 3

Distinctiveness Conflict Risk

Carves a clear niche — pre-implementation architect-level review gate that 'Hard-blocks code-level details so the human stays at architectural direction' — making it unlikely to fire for code review, teaching, or research skills.

3 / 3

Total

11

/

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.