SKILLEMALL.ai
GitHub ↗ RU Sign in

AB arch-review

Architecture review based on OpenSpec documents and code. Multi-dimension concurrent evaluation with structured scoring and actionable recommendations. Use when asked to "review architecture", "arch review", "架构评审", "evaluate the design", or "review openspec". Proactively suggest when a project has openspec/specs/ and the user is about to start implementation or refactoring.

ClawHub Agent Skills author: str('tiignidf')[::-1]+'@gmail.com' v1.0.0 MIT-0 5 files body ≈ 3 310 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 67/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, consistency

AnalyzerSoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
96/100
safety, quality, tests
Safety 60%
99
Quality 40%
92
Run on models
none yet
Process rating
B
67/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 1

    ✓ No critical or high findings

    Medium and low: 1
    • low Risky intent intent-offensive-security dimensions.md:162
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Broken access control (horizontal privilege escalation)

    Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 67/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 40Consistency. Frontmatter name (arch-review) differs from the folder (architect-review)
    • 60Result and completion. Output format stated, no completion criterion
    • 100Tools and files. No external tools needed
    • 100Steps. 93 steps
    • 100Failures and branches. 8 branches, has a failure section
    • 100Execution cost. Instruction body is 3310 tokens
    • 100Running it twice. Mutating operations check current state
    • low 10 top-level sections: this looks like several domains in one skill

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +4Description does not say when NOT to use the skill (false activations)
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 4 example trigger phrases
    • +3Description length 377: enough signal without eating the budget
    • +4Structure: 22 headings
    • +3Step-by-step instructions: 93 items
    • +3Output format is stated explicitly
    • +4Has examples (6 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.

    External checks

    ClawHub: clean
    This is an instruction-only architecture review skill; it reads project files and may save a local report, but the behavior is mostly purpose-aligned and disclosed in the workflow.
    LLM: benign (high) · VirusTotal: · 29 May 2026