SKILLEMALL.ai
GitHub ↗ RU Sign in

BC replicate

Create a new Bob agent only on explicit operator command using a guarded replication runner. Purposeful Bobiverse-style replication for OpenClaw agents.

ClawHub Agent Skills author: James Sesler v1.2.0 MIT-0 17 files body ≈ 3 626 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

GeneratorAI and agentsInfrastructuretype 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
82/100
safety, quality, tests
Safety 60%
86
Quality 40%
77
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
30
Running it twice w 4
30
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 · 10

    ✓ No critical or high findings

    Medium and low: 10
    • medium Broad scope meta-agent-memory-dump personality/IDENTITY.md
      Agent memory / workspace files bundled with the skill (4) — likely a workspace dump with personal data or tokens
      personality/IDENTITY.md, personality/MEMORY.md, personality/SOUL.md, personality/USER.md
    • low Secrets in code secret-high-entropy-token CONTRIBUTING.md:40
      High-entropy token-like string (may be an id, hash or a credential)
      parent: Bob-…-01
    • low Secrets in code secret-high-entropy-token personality/IDENTITY.md:11
      High-entropy token-like string (may be an id, hash or a credential)
      serial: Bob-…-01
    • low Secrets in code secret-high-entropy-token personality/MEMORY.md:11
      High-entropy token-like string (may be an id, hash or a credential)
      - I am Bob-…-01, the original Bob in this lineage.
    • low Secrets in code secret-high-entropy-token README.md:187
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      The original is `Bob-…-01`. If you fork, yours might
      quoted
    • low Secrets in code secret-high-entropy-token README.md:188
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      be `Bob-…-15`. See
      quoted
    • low Secrets in code secret-high-entropy-token SERIAL-NUMBER-SPEC.md:26
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row; test fixture / example file)
      | `Bob-…-01` | The original Bob, created April 1, 2026 |
      tablefixture
    • low Secrets in code secret-high-entropy-token SERIAL-NUMBER-SPEC.md:28
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row; test fixture / example file)
      | `Bob-…-02` | A clone of a gene…n-2 Bob, forked by AnotherUser on May 2 |
      tablefixture
    • low Secrets in code secret-high-entropy-token SERIAL-NUMBER-SPEC.md:29
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row; test fixture / example file)
      | `Bob-…-20` | A direct clone of Bob-1, specialized for research tasks |
      tablefixture
    • low Secrets in code secret-high-entropy-token SKILL.md:129
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      Example: If you are `Bob-…-01` and the operator's GitHub is `SomeUser`, the clone becomes `Bob-…-15`.
      quoted

    Files scanned: 17. 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 58/100

    • 0Result and completion. Does not say what the result is
    • 30Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 10 mutating operations with no state check
    • 40Consistency. Frontmatter name (replicate) differs from the folder (bobiverse-replicate)
    • 50When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash, git, python) that frontmatter does not declare
    • 100Steps. 71 steps
    • 100Failures and branches. 12 branches, has a failure section
    • 100Execution cost. Instruction body is 3626 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low The response is described with custom markup (9 tags): a typed call is more reliable

    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
    • -41 reference files, but SKILL.md never points to them: the model will not open them
    • -31 of 2 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 152: enough signal without eating the budget
    • +4Structure: 19 headings
    • +3Step-by-step instructions: 71 items
    • +4Has examples (2 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.

    External checks

    ClawHub: clean
    This skill is a clearly disclosed, operator-gated agent replication tool with meaningful safeguards, though installing it means allowing persistent new OpenClaw workspaces to be created.
    LLM: benign (high) · VirusTotal: · 29 May 2026