SKILLEMALL.ai
GitHub ↗ RU Sign in

AC dual-agent-debate

Run a structured 2-agent debate loop between ChatGPT (OpenAI API) and the user's own thoughts retrieved from Supabase Open Brain via MCP, iterating up to 3 rounds (or until semantic agreement), then write the final outcome back to Open Brain. Use when user asks to compare/pressure-test an idea against prior thoughts or memory.

ClawHub Agent Skills author: tvaloki v0.3.0 2 files body ≈ 440 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationSupabaseAI 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
94/100
safety, quality, tests
Safety 60%
100
Quality 40%
85
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
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: 2. 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 59/100

    • 0Result and completion. Does not say what the result is
    • 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
    • 60Failures and branches. 2 branches
    • 100Tools and files. No external tools needed
    • 100Steps. 8 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 440 tokens
    • 100Running it twice. No mutating operations

    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)
    • +3Output format is not stated: the model decides each time
    • -2localhost URLs: will not work for another user
    • +1No license
    • +2Single-language instructions
    • +3Description length 328: enough signal without eating the budget
    • +4Structure: 5 headings
    • +3Step-by-step instructions: 8 items
    • +4Has examples (5 code blocks)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

    External checks

    ClawHub: clean
    The skill appears purpose-aligned, but it reads and writes Open Brain memories and may send private thoughts/context to OpenAI or a local OpenClaw agent.
    LLM: benign (medium) · VirusTotal: · 29 May 2026