CtrlK
BlogDocsLog inGet started
Tessl Logo

human-architect-mindset

Systematic architectural thinking for irreplaceable human capabilities - domain modeling, systems thinking, constraint navigation, and AI-aware problem decomposition. Use proactively when detecting architectural decisions, system design discussions, or multi-component planning.

51

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

27%

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

The content is well-intentioned and structurally organized, but it is far too verbose for a skill body, leans heavily on conceptual explanation over executable guidance, and makes no use of progressive disclosure despite its length. It would benefit substantially from trimming and splitting.

Suggestions

Cut conceptual exposition Claude already knows (definitions of systems thinking, the loyalty philosophy preamble) and keep only the architect-specific heuristics, question banks, and tables.

Split the long sections into one-level-deep reference files (e.g. PILLARS.md, SDD.md) and keep SKILL.md as a concise overview with signaled links, rather than inlining everything.

Add explicit validation/verification checkpoints to the Architect Process phases — e.g. a "confirm domain model with stakeholders before proceeding" gate — so the workflow has feedback loops.

DimensionReasoningScore

Conciseness

The ~800-line body is verbose and explains concepts Claude already knows (what systems thinking is, generic "An architect asks:" question lists, extended loyalty philosophy), padded with restated material rather than lean guidance.

1 / 3

Actionability

It offers concrete question lists, comparison tables, and the SDD specification hierarchy with named field contracts, but the core architectural guidance is instructional rather than executable — no commands, code, or copy-paste-ready artifacts.

2 / 3

Workflow Clarity

The five-phase Architect Process is clearly sequenced, and the SDD section mentions verification and traceability, but the main workflow lacks explicit validation checkpoints or fix-retry feedback loops for its risky judgment-heavy steps.

2 / 3

Progressive Disclosure

It is a monolithic wall of text in a single file with no bundle files and no one-level-deep referenced material; the loyalty, pillars, process, SDD extension, and question banks are all inlined rather than split into navigable references.

1 / 3

Total

6

/

12

Passed

Description

85%

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 strong: third person, specific capabilities, and an explicit Use-when trigger. Its only weakness is trigger-term breadth, which relies on a few phrasings plus some jargon rather than a fuller spread of natural user terms.

Suggestions

Add more natural trigger phrasings users actually say (e.g. "architecture review", "tech choice", "how should we structure this") alongside the existing ones.

Drop the buzzwordy "irreplaceable human capabilities" framing from the trigger clause; it dilutes the concrete capabilities that follow.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "domain modeling, systems thinking, constraint navigation, and AI-aware problem decomposition" — rather than vague abstractions, matching the anchor for listing several specific capabilities.

3 / 3

Completeness

Explicitly answers what it does (the four named capabilities) and when to use it via the "Use proactively when detecting..." clause, satisfying both the what and the when with an explicit trigger.

3 / 3

Trigger Term Quality

Includes some natural terms users would say ("architectural decisions", "system design discussions") but also leans on jargon ("irreplaceable human capabilities") and omits common variations like "architecture review" or "tech choices", so it stops at "some relevant keywords".

2 / 3

Distinctiveness Conflict Risk

Targets a clear niche — human-side architectural decision-making — with triggers ("multi-component planning", "architectural decisions") unlikely to fire for unrelated 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

skill_md_line_count

SKILL.md is long (802 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
bencium/bencium-marketplace
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.