octopus-architecture

System architecture and API design with multi-AI consensus — use for design reviews and new subsystems

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-architecture/SKILL.md

Quality

Content

77%

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

The body delivers highly actionable, well-sequenced guidance with strong validation gates, but it is verbose with repetitive enforcement framing and keeps too much inline rather than splitting detail into referenced files.

Dimension	Reasoning	Score
Conciseness	The body is padded with repeated enforcement language ("MANDATORY - CANNOT SKIP", "CRITICAL", "PROHIBITED", repeated "You MUST") and an emoji banner template that could be tightened, matching the score-2 anchor; not score 1 because it avoids explaining concepts Claude already knows, not score 3 because of the redundancy and emphasis inflation.	2 / 3
Actionability	Provides concrete executable commands (orchestrate.sh spawn backend-architect "...", check-providers.sh) with real paths and concrete LSP tool examples, matching the score-3 copy-paste-ready anchor; placeholders like <user's architecture request> are appropriate rather than pseudocode.	3 / 3
Workflow Clarity	A clear 4-step sequence (STEP 1 banner, STEP 2 execute, STEP 3 validation gate, STEP 4 present) includes explicit validation checkpoints and an error-recovery feedback loop, matching the score-3 anchor.	3 / 3
Progressive Disclosure	Content is largely inline and monolithic (banner template, bash blocks, LSP examples all in SKILL.md) with external paths (codex-host-adapter.md, backend-architect.md) mentioned inline rather than as clearly-signaled navigation; no bundle files exist to offset this, matching the score-2 anchor.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 clearly answers what the skill does and when to use it with an explicit trigger clause, but it stays somewhat abstract and could broaden its natural trigger terms to improve specificity and reduce overlap with general design skills.

Dimension	Reasoning	Score
Specificity	Quotes "System architecture and API design with multi-AI consensus" name the domain and a couple of actions but stop short of listing multiple concrete actions like the score-3 anchor; not score 1 because concrete actions (architecture design, API design) are named.	2 / 3
Completeness	Answers both what ("System architecture and API design with multi-AI consensus") and when via an explicit trigger clause ("use for design reviews and new subsystems"), matching the score-3 anchor with an explicit 'use for...' trigger.	3 / 3
Trigger Term Quality	Trigger phrase "use for design reviews and new subsystems" offers some natural keywords but misses common variations users would say (e.g. "design a system", "architecture review"); not score 3 due to thin coverage, not score 1 because real trigger words are present.	2 / 3
Distinctiveness Conflict Risk	The "multi-AI consensus" framing is a distinct niche, but "System architecture and API design" is broad enough to overlap with general coding/design skills, so it lands on the score-2 anchor rather than a clearly-conflict-free score 3.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-architecture/SKILL.md
Commit: 9f39f0c

Reviewed: 2 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.