SKILLEMALL.ai
GitHub ↗ RU Sign in

AB agent-architect

Audit and improve an agent at the right layer: persona/tone, constitutional and operating rules, memory architecture, or skill portfolio / reusable workflows. Use when an agent feels off, brittle, repetitive, forgetful, over-scoped, or uneven and the question is which lane is actually weak and what the smallest justified fix is. Helps decide whether to make a plain edit, tighten a rule, adjust memory, change a skill, or do nothing.

ClawHub Agent Skills author: Don Zurbrick v1.0.0 MIT-0 7 files body ≈ 1 416 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, consistency

AnalyzerAI and agentstype 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%
100
Quality 40%
91
Run on models
none yet
Process rating
B
69/100
Nearly there
Inputs and preconditions w 11
0
Consistency w 8
40
When it triggers w 12
50
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 · 0

    ✓ No critical or high findings

    Files scanned: 7. 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 69/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 40Consistency. Frontmatter name (agent-architect) differs from the folder (agent-architect-zurbrick)
    • 50When it triggers. No condition that starts the skill
    • 60Result and completion. Output format stated, no completion criterion
    • 65Failures and branches. 3 branches
    • 100Tools and files. No external tools needed
    • 100Steps. 46 steps
    • 100Execution cost. Instruction body is 1416 tokens
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress

    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

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +1No license
    • +2Single-language instructions
    • +3Description length 435: enough signal without eating the budget
    • +4Structure: 11 headings
    • +3Step-by-step instructions: 46 items
    • +3Output format is stated explicitly
    • +4Has examples (1 code blocks)
    • +4Reference files are cited in the instructions (5 of 5)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: clean
    This is an instruction-only agent-audit skill that recommends where changes should be made, with no code, credentials, install step, or hidden execution behavior.
    LLM: benign (high) · VirusTotal: · 29 May 2026