SKILLEMALL.ai
GitHub ↗ RU Sign in

AB expert-mode

AI expert panel, specialist advisor, technical review, thoughtful critique, and decision-support system for OpenClaw projects. Use when the user says "activating expert mode", "quick expert mode", or "deep expert mode", or wants virtual experts, expert archetypes/personas, AI specialists, domain advisors, consultants, reviewers, second opinions, strategic analysis, technical analysis, architecture review, design review, implementation review, risk audit, red-team critique, prompt engineering advice, customer experience advice, client relationship guidance, top-notch expert support, or project planning support. Supports quick/standard/deep/custom-length responses, project-local expert rosters, reusable dossiers, custom requested experts, prominent expert biographic anchors, client-relationship stance, and minimal context loading.

ClawHub Agent Skills author: e1red v0.9.0 MIT-0 16 files body ≈ 4 067 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice

AnalyzerAI and agentsInfrastructureOperations and projectstype 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
97/100
safety, quality, tests
Safety 60%
98
Quality 40%
96
Run on models
none yet
Process rating
B
68/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Risky intent intent-offensive-security SKILL.md:20
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      Use Expert Mode when you want an AI expert panel, virtual advisory board, custom expert, expert persona, domain specialist, thoughtful advisor, technical reviewer, critique partner, red team reviewer,
    • low Risky intent intent-offensive-security SKILL.md:33
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - red team reviewer / risk reviewer / safety audit

    Files scanned: 16. 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 68/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 16 mutating operations with no state check
    • 40Consistency. Frontmatter name (expert-mode) differs from the folder (expert-mode-archetypes)
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 70Execution cost. Instruction body is 4067 tokens
    • 100Tools and files. No external tools needed
    • 100Steps. 80 steps
    • 100Failures and branches. 4 branches, has a failure section
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 17 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)
    • +3Description length 840: 120–800 characters recommended
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 3 example trigger phrases
    • +4Structure: 18 headings
    • +3Step-by-step instructions: 80 items
    • +3Output format is stated explicitly
    • +4Has examples (5 code blocks)
    • +4Reference files are cited in the instructions (9 of 12)
    • +3All 2 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.

    External checks

    ClawHub: clean
    This skill is a disclosed project-advisory helper that may read project notes and create local expert roster/dossier files, with no evidence of hidden credential use, exfiltration, or destructive behavior.
    LLM: benign (high) · VirusTotal: · 29 May 2026