CtrlK
BlogDocsLog inGet started
Tessl Logo

architecture-review

Review a change for architectural drift, guardrail weakening, and ADR impact before shipping.

55

Quality

61%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/architecture-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

This is a well-structured, concise architecture review checklist that efficiently communicates repo-specific review concerns. Its main weaknesses are the lack of a concrete example finding (which would make the output format more actionable) and the absence of an explicit workflow sequence tying the commands to the checklist review steps.

Suggestions

Add a concrete example of a completed finding (with severity, file, violated rule, why it matters, and exact fix filled in) to make the Findings Format section fully actionable.

Add an explicit workflow sequence: e.g., '1. Run the fast guard check, 2. Review each focus area, 3. If guard script reports issues, address those first, 4. Document findings in the specified format.'

DimensionReasoningScore

Conciseness

Every section is lean and purposeful. No unnecessary explanations of what architecture reviews are or why they matter. The checklist items are terse but clear, and the commands section is minimal.

3 / 3

Actionability

The checklist questions are concrete and specific to the repo, and the commands are copy-paste ready. However, the guidance is mostly interrogative (asking questions) rather than prescriptive (telling Claude exactly what to do), and the findings format lacks a concrete example of a filled-out finding.

2 / 3

Workflow Clarity

The focus areas form a logical sequence and the findings format provides a clear output structure. However, there's no explicit workflow ordering (e.g., run commands first, then check areas) and no validation/feedback loop for what to do if the adr_guard script fails or produces warnings.

2 / 3

Progressive Disclosure

For a skill under 50 lines with no need for external references, the content is well-organized into clear sections (Focus Areas, Commands, Findings Format) that are easy to scan and navigate.

3 / 3

Total

10

/

12

Passed

Description

50%

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 identifies a reasonably specific niche (architecture-focused change review) with domain-specific terminology, but lacks an explicit 'Use when...' clause and misses common trigger terms users would naturally use. It would benefit from listing more concrete actions and adding explicit trigger guidance to help Claude distinguish it from general code review skills.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when reviewing a PR, pull request, or code change for architecture compliance, or when the user asks about ADR conformance or design drift.'

Include more natural trigger terms users would say, such as 'code review', 'PR review', 'pull request', 'architecture compliance', 'design decisions', and 'merge request'.

Expand the concrete actions, e.g., 'Checks changes against Architecture Decision Records (ADRs), identifies guardrail weakening patterns, flags dependency violations, and surfaces architectural drift risks.'

DimensionReasoningScore

Specificity

Names the domain (code review/architecture) and lists some actions (architectural drift, guardrail weakening, ADR impact), but these are somewhat abstract concepts rather than concrete, granular actions like 'flag violations of dependency rules' or 'check compliance with ADR decisions'.

2 / 3

Completeness

The 'what' is partially addressed (review a change for specific concerns), but there is no explicit 'Use when...' clause or equivalent trigger guidance. The phrase 'before shipping' implies timing but doesn't explicitly state when Claude should select this skill.

2 / 3

Trigger Term Quality

Includes some relevant terms like 'architectural drift', 'guardrail', 'ADR', and 'shipping', but misses common natural language variations users might say such as 'code review', 'PR review', 'architecture review', 'design decision', 'pull request', or 'merge'.

2 / 3

Distinctiveness Conflict Risk

The combination of 'architectural drift', 'guardrail weakening', and 'ADR impact' provides some distinctiveness from generic code review skills, but 'review a change' is broad enough to potentially overlap with other review-oriented skills.

2 / 3

Total

8

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
PaloAltoNetworks/shifter
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.