octopus-architecture

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

Quality

66%

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

62%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 delivers an explicitly sequenced, validation-gated workflow with executable orchestration commands, which is its main strength. It loses points to repetitive enforcement padding, a pseudocode LSP example, and inlined content that could be referenced out.

Suggestions

Collapse the repeated MANDATORY/PROHIBITED/DO-NOT-PROCEED warnings into a single concise enforcement note; remove the duplicated agy_status assignment and duplicate Antigravity banner line.

Replace the LSP pseudocode with concrete, runnable invocations or move the LSP guidance into a separate reference file linked from SKILL.md.

Move the capabilities list and example prompts into a referenced file (e.g. references/usage.md) so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly functional with concrete commands, but padded with repeated enforcement injunctions ('MANDATORY', 'PROHIBITED from', 'This is NOT optional', 'DO NOT PROCEED') and duplicate lines (agy_status defined twice, Antigravity listed twice in the banner) that could be trimmed.	3 / 5
Actionability	Provides concrete executable bash commands with real paths and flags (orchestrate.sh spawn, check-providers.sh), but the LSP section uses illustrative pseudocode and a '// ... architecture design ...' placeholder rather than fully executable code.	4 / 5
Workflow Clarity	Four steps are explicitly sequenced with a blocking validation gate (Step 3 checks exit code) and an error-recovery loop (report, show logs, do not substitute with direct design), satisfying the validation/feedback-loop requirement.	5 / 5
Progressive Disclosure	Single-file skill with reasonable section headers and a one-level-deep persona reference (agents/personas/backend-architect.md), but the LSP integration content is inlined rather than split out and no bundle files exist to offload detail.	3 / 5
	Total	15 / 20 Passed

Description

70%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 concise and answers both what and when with a fairly distinct multi-AI-consensus niche. It is held back by generic actions and trigger phrasing that could be more concrete and comprehensive.

Suggestions

Replace abstract domain naming with concrete verbs, e.g. 'Designs API contracts, microservices decompositions, and event-driven architectures with multi-AI consensus'.

Expand the 'when' clause with natural trigger variations: 'Use when the user asks to design, review, or plan a new subsystem, API, or distributed system'.

Add file/term anchors users actually say (e.g. 'REST API', 'schema design', 'scalability plan') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('System architecture and API design', 'multi-AI consensus') but the actual actions are minimal and generic — it never says what it does (designs, reviews, generates) beyond naming the area.	3 / 5
Completeness	Provides both a 'what' ('System architecture and API design with multi-AI consensus') and an explicit 'when' ('use for design reviews and new subsystems'), though the trigger clause could be more specific.	4 / 5
Trigger Term Quality	'design reviews' and 'new subsystems' are natural phrases a user would say when they need this skill, giving good keyword coverage with only minor synonyms missing.	4 / 5
Distinctiveness Conflict Risk	'multi-AI consensus' is a distinct niche and the design-review/new-subsystem triggers are specific enough to minimize overlap with generic architecture skills, with only minor overlap risk.	4 / 5
	Total	15 / 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: nyldn/claude-octopus
Path: .claude/skills/skill-architecture/SKILL.md
Commit: f9b8c92

Reviewed: 4 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.