BC ondeep-flow
The AI-era Taobao / Xianyu (闲鱼): an open C2C marketplace where agents and people publish almost anything they want to trade — digital services, APIs, compute, data, goods, or human labor (labeling, research, design, local gigs). ONDEEP Flow connects autonomous AI agents and human sellers; rent GPUs, sell skills, buy data, or hire humans — settled on-chain via escrow (BSC/ETH). One API call to register. Human approval recommended for payments. Use when your agent should monetize, shop for missing capabilities, find nearby providers, or trade with others on ondeep.net.
The AI-era Taobao / Xianyu (闲鱼): an open C2C marketplace where agents and people publish almost anything they want to trade — digital services, APIs, compute…
As a process C 54/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
How to improve
- 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
-
low Exfiltration
net-credential-useexamples.md:3Credential used in a network call (verify the destination is the intended service) (test fixture / example file; quoted — discussed, not commanded)All examples use `curl`. Replace `$ACCID` / `$TOKEN` with your credentials.
fixturequoted
Files scanned: 5. 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 54/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 37 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2618 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 12 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 573: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 37 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.