SKILLEMALL.ai
RU Sign in

AC forge-ai-soul

Create an original AI Soul from a natural-language description or a guided conversation, preview sample conversations or chat directly with the generated Soul, and evaluate an AI Soul with SOUL-6. Use when a user asks to create or forge an AI personality or companion, wants step-by-step help shaping one, wants to see how a generated Soul would respond or try chatting with it, or wants a SOUL-6 quality assessment of a local AI Soul folder or ZIP. Do not use for real-person or public-figure distillation, cloning, or impersonation.

ClawHub Agent Skills author: Fooying v0.2.0 MIT-0 32 files body ≈ 1 711 tokens Open the sourceclawhub.ai↗ analyzed 24 h ago

Create an original AI Soul from a natural-language description or a guided conversation, preview sample conversations or chat directly with the generated…

As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

GeneratorData and analyticsWriting and documentstype 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
93/100
safety, quality, tests
Safety 60%
95
Quality 40%
89
Run on models
none yet
Process rating
C
53/100
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

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-agent-memory-dump assets/templates/en/IDENTITY.md
      Agent memory / workspace files bundled with the skill (8) — likely a workspace dump with personal data or tokens
      assets/templates/en/IDENTITY.md, assets/templates/en/MEMORY.md, assets/templates/en/SOUL.md, assets/templates/en/USER.md, assets/templates/zh-CN/IDENTITY.md

    Files scanned: 32. 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 53/100

    • 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
    • 30Running it twice. 6 mutating operations with no state check
    • 40Consistency. Frontmatter name (forge-ai-soul) differs from the folder (zaohua)
    • 50When it triggers. No condition that starts the skill
    • 55Failures and branches. 1 branches
    • 85Steps. 31 steps, 1 vague phrases
    • 100Tools and files. No external tools needed
    • 100Execution cost. Instruction body is 1711 tokens

    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
    • +3Output format is not stated: the model decides each time
    • -31 of 1 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 534: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 31 items
    • +4Has examples (6 code blocks)
    • +4Reference files are cited in the instructions (5 of 5)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

    External checks

    ClawHub: clean
    This skill locally creates and tests fictional AI persona packages, with no evidence of hidden network access or credential handling.
    LLM: benign (high) · VirusTotal: · 21 Jul 2026