SKILLEMALL.ai
GitHub ↗ RU Sign in

BF structured-deliberation

Provides a structured multi-agent deliberation framework with role schemas (action/guardian/observer/critic), verification protocols, and stopping criteria. Activate when designing multi-agent systems for non-trivial deliberation, instrumenting agent debates against sycophancy, or seeking an evaluable alternative to free-form group prompting.

ClawHub Agent Skills author: TatsuKo Tsukimi v0.1.0 MIT-0 13 files body ≈ 3 239 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 45/100 · Will not run — References files that are not bundled: templates/round-template.md.tmpl, templates/role-prompt.md.tmpl, templates/artifact-schemas/

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
B
88/100
safety, quality, tests
Safety 60%
94
Quality 40%
79
Run on models
none yet
Process rating
F
45/100
Will not run
References files that are not bundled: templates/round-template.md.tmpl, templates/role-prompt.md.tmpl, templates/artifact-schemas/
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
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 · 6

✓ No critical or high findings

Medium and low: 6
  • low Risky intent intent-offensive-security examples/condensed-deliberation.md:135
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition; test fixture / example file)
    - C-4-2 (critic): "But that same orchestrator is a ransomware target — adversary that compromises it gets full system view" — testable_as: red team simulation against orchestrator
    detectorfixture
  • low Risky intent intent-offensive-security examples/condensed-deliberation.md:145
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file; quoted — discussed, not commanded)
    Critic's lead: "Final attack: ransomware compromise of C's orchestrator. What's recovery time?"
    fixturequoted
  • low Risky intent intent-offensive-security examples/condensed-deliberation.md:149
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)
    - C-4-2 status: pending → tested_confirmed (red team sim against orchestrator showed 6-hour full-system compromise window)
    fixture
  • low Risky intent intent-offensive-security references/claims-infrastructure.md:217
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **Multi-stakeholder verifications**: if multiple parties verify (e.g., red team + compliance + customer support), add a `verifier` field to verifications.
  • low Risky intent intent-offensive-security references/role-schemas.md:206
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Critic: red team / security perspective
  • low Risky intent intent-offensive-security SKILL.md:160
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Critic: who/what attacks? (typically: red team / failure-mode adversary)

Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: templates/round-template.md.tmpl
  • warning missing-ref reference to a missing file: templates/role-prompt.md.tmpl
  • warning missing-ref reference to a missing file: templates/artifact-schemas/
  • warning missing-ref reference to a missing file: ../multi-dim-eval-framework

Process rating: all ten parameters 45/100

Will not run. References files that are not bundled: templates/round-template.md.tmpl, templates/role-prompt.md.tmpl, templates/artifact-schemas/
  • 0Tools and files. 4 referenced file(s) missing: templates/round-template.md.tmpl, templates/role-prompt.md.tmpl, templates/artifact-schemas/
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 100Steps. 87 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3239 tokens
  • 100Progress reporting. Reports progress
  • low 18 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

  • +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
  • +1No license
  • +2Single-language instructions
  • +3Description length 344: enough signal without eating the budget
  • +4Structure: 24 headings
  • +3Step-by-step instructions: 87 items
  • +4Has examples (2 code blocks)
  • +4Reference files are cited in the instructions (5 of 5)
  • +3All 3 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

External checks

ClawHub: clean
This is a coherent deliberation workflow skill with optional local helper scripts, and I found no hidden network access, credential handling, destructive behavior, or background persistence.
LLM: benign (high) · VirusTotal: · 29 May 2026