SKILLEMALL.ai
GitHub ↗ RU Sign in

AA web3-pm-interview

Use this skill when preparing candidates for Web3 product manager interviews, especially wallet, exchange, DeFi, DEX, on-chain data, growth, AI Wallet, Agentic Wallet, senior PM, product lead, or product director roles. It analyzes target JDs, maps candidate experience to role requirements, builds interview narratives, generates round-specific playbooks and question banks, runs mock interview scoring, and prepares case or 30/60/90-day plans.

ClawHub Agent Skills author: alexander10011 v0.4.0 MIT-0 42 files body ≈ 1 668 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process A 80/100 · Runs to the end — weak spots: consistency, running it twice

ProcedureInfrastructureAI 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
A
92/100
safety, quality, tests
Safety 60%
93
Quality 40%
91
Run on models
none yet
Process rating
A
80/100
Runs to the end
Running it twice w 4
30
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.

Risky intent 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 purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

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 · 3

    ✓ No critical or high findings

    Medium and low: 3
    • medium Risky intent intent-wallet-secrets references/wallet-pm.md:15
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - Seed phrase, private key, signing, recovery
    • low Risky intent intent-wallet-secrets examples/sample-battle-plan-output.md:92
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (test fixture / example file)
      - Seed phrase, private key, signing
      fixture
    • low Risky intent intent-wallet-secrets examples/web2-fintech-to-wallet-pm.md:67
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (test fixture / example file)
      - Seed phrase, private key, signing
      fixture

    Files scanned: 42. 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 80/100

    • 30Running it twice. 2 mutating operations with no state check
    • 40Consistency. Frontmatter name (web3-pm-interview) differs from the folder (web3-pm-interview-skill)
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 70Failures and branches. 4 branches
    • 100Tools and files. No external tools needed
    • 100Steps. 93 steps
    • 100Inputs and preconditions. Inputs and preconditions are listed
    • 100Execution cost. Instruction body is 1668 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 10 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)
    • +1No license
    • +2Single-language instructions
    • +3Description length 445: enough signal without eating the budget
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 93 items
    • +3Output format is stated explicitly
    • +4Has examples (6 code blocks)
    • +4Reference files are cited in the instructions (14 of 14)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: clean
    This is an instruction-only Web3 interview-prep skill with no executable code or requested permissions, but users should redact private data and practice wallet flows cautiously.
    LLM: benign (high) · VirusTotal: · 29 May 2026