SKILLEMALL.ai
GitHub ↗ RU Sign in

AB scout

Pre-development reference research. Produces a Steal List: concrete patterns extracted from real products and real codebases that solved similar problems. Two modes: UI/UX (screenshot + analyze the best products) and Code (find repos, read implementations, compare architectures). Output: structured reference document at .scout/ in the project root. Use when: "find references", "how do others do this", "show me examples", "research before building", "scout", "what's out there", "prior art". Proactively suggest when the user is about to build something non-trivial and hasn't looked at prior art.

ClawHub Agent Skills author: Hybirdss v1.0.0 MIT-0 2 files body ≈ 2 984 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process B 75/100 · Nearly there — weak spots: inputs and preconditions, consistency

ReferenceSoftware 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
94/100
safety, quality, tests
Safety 60%
95
Quality 40%
92
Run on models
none yet
Process rating
B
75/100
Nearly there
Inputs and preconditions w 11
0
Consistency w 8
40
Result and completion w 14
60
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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
    • medium Broad scope meta-broad-allowed-tools SKILL.md:1
      Broad tool permissions pre-approved: Bash
      allowed-tools: Bash Read Write Grep Glob AskUserQuestion WebSearch WebFetch Agent

    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 75/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 40Consistency. Frontmatter name (scout) differs from the folder (steal-list)
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 28 steps
    • 100Failures and branches. 6 branches, has a failure section
    • 100Execution cost. Instruction body is 2984 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

    • +4Description does not say when NOT to use the skill (false activations)
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 6 example trigger phrases
    • +3Description length 600: enough signal without eating the budget
    • +4Structure: 17 headings
    • +3Step-by-step instructions: 28 items
    • +3Output format is stated explicitly
    • +4Has examples (7 code blocks)

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

    External checks

    ClawHub: clean
    The skill appears to be a disclosed research/scouting helper that may inspect a project and save a local report, with no evidence of deception or harmful behavior.
    LLM: benign (medium) · VirusTotal: · 29 May 2026