SKILLEMALL.ai
GitHub ↗ RU Sign in

BF ai-era-career-planner

Offline, deterministic career planning for the AI era (China market focus). Holland RIASEC 3-question screen with a complete 8-combo deterministic code table, 5-value (pick-2) and 8-anchor screens, a 12-direction heuristic match with sourced 2026 job-demand ratings (AI Agent talent +244%, AI PM +87.7%, entry-level decline since 2022-10, etc.), an honest factor-model salary reference DB (5376 modeled ranges + 74 scraped cross-check samples with measured -80%..+432% drift — never presented as market data), and a Markdown report generator with an upfront honesty disclaimer. All scripts are python3-stdlib, zero network, JSON in/out, exit codes 0/2.

ClawHub Agent Skills author: orionshaowswmw v2.0.0 MIT-0 29 files body ≈ 1 057 tokens Open the sourceclawhub.ai↗ analyzed 23 h ago

Offline, deterministic career planning for the AI era (China market focus).

As a process F 35/100 · Will not run — References files that are not bundled: references/industries/*.md

GeneratorAI 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
B
84/100
safety, quality, tests
Safety 60%
94
Quality 40%
70
Run on models
none yet
Process rating
F
35/100
Will not run
References files that are not bundled: references/industries/*.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
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 · 6

✓ No critical or high findings

Medium and low: 6
  • low Obfuscation obf-hex-escape-chain data/insurance_broker_companies.json:147
    Escaped/char-code string obfuscation (detector / deny-list definition)
    "source_url": "https://baike.baidu.com/item/%E5%AE%89%E5%BF%83%E8%B4%A2%E4%BA%A7%E4%BF%9D%E9%99%A9%E6%9C%89%E9%99%90%E8%B4%A3%E4%BB%BB%E5%85%AC%E5%8F%B8/19407012",
    detector
  • low Obfuscation obf-hex-escape-chain data/insurance_broker_companies.json:171
    Escaped/char-code string obfuscation (detector / deny-list definition)
    "source_url": "https://baike.baidu.com/item/%E6%B0%B4%E6%BB%B4%E4%BF%9D%E9%99%A9%E7%BB%8F%E7%BA%AA%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8/59125689",
    detector
  • low Obfuscation obf-hex-escape-chain data/insurance_broker_companies.json:195
    Escaped/char-code string obfuscation (detector / deny-list definition)
    "source_url": "https://baike.baidu.com/item/%E4%B8%AD%E5%AE%8F%E4%BA%BA%E5%AF%BF%E4%BF%9D%E9%99%A9%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8/1263983",
    detector
  • low Obfuscation obf-hex-escape-chain data/insurance_broker_companies.json:207
    Escaped/char-code string obfuscation (detector / deny-list definition)
    "source_url": "https://baike.baidu.com/item/%E5%85%89%E5%A4%A7%E6%B0%B8%E6%98%8E%E4%BA%BA%E5%AF%BF%E4%BF%9D%E9%99%A9%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8/342765",
    detector
  • low Secrets in code secret-high-entropy-token data/insurance_broker_companies.json:219
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "source_url": "https://gwoss.citic-prudential.citic/uploadfiles%2Fco…ort%2F20260430%2FhQ…pdf?5Lit5L+h5L+d6K+a5Lq65a+%2FID…pyA
    detector
  • low Obfuscation obf-hex-escape-chain data/insurance_broker_companies.json:327
    Escaped/char-code string obfuscation (detector / deny-list definition)
    "source_url": "https://baike.baidu.com/item/%E5%B9%B3%E5%AE%89%E5%85%BB%E8%80%81%E4%BF%9D%E9%99%A9%E8%82%A1%E4%BB%BD%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8/10609530",
    detector

Files scanned: 29. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: references/industries/*.md

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: references/industries/*.md
  • 0Tools and files. 1 referenced file(s) missing: references/industries/*.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 100Steps. 5 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1057 tokens
  • 100Running it twice. No mutating operations
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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
  • +4No input/output examples
  • +2Single-language instructions
  • +3Description length 652: enough signal without eating the budget
  • +4Structure: 7 headings
  • +3Step-by-step instructions: 5 items
  • +4Reference files are cited in the instructions (10 of 12)
  • +3All 3 scripts are documented
  • +1License stated

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

External checks

ClawHub: clean
This is a coherent offline career-planning skill with no evidence of hidden network use, persistence, or credential access.
LLM: benign (high) · VirusTotal: · 6 Sept 2026