BD ok-skills
OK Skills — automate OK.com, a global classifieds and marketplace platform. Search listings, browse categories, view listing details, manage favorites, and manage posted ads across 10 countries. Use when: "find apartments in Hawaii", "search jobs in Tokyo", "browse used cars in Vancouver", "show Singapore real estate", "check my favorites", "manage my listings on OK.com", "switch country to Japan", "list cities in Canada". Features: keyword search with price range filtering, category browsing (real-estate, jobs, vehicles, services, marketplace), listing detail extraction (price, rooms, area, images, seller info), favorite management, posted-ad management, multi-country locale switching, city search. Supported countries: Singapore, USA, Canada, Japan, UAE, Australia, UK, Hong Kong, Malaysia, New Zealand. Also known as: ok skill, ok skills, ok-skills, ok-core-skill, ok core skill, OK.com automation, OK.com scraper, classified ads bot, property finder, job search agent, marketplace browser. Built for AI agents that need to interact with OK.com programmatically via CLI. Ideal for real estate agents, job seekers, and bargain hunters. OK.com 分类信息自动化技能：搜索帖子、浏览分类、查看详情、管理收藏与帖子， 支持 10 国多城市多语言。
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Shorten the description to 1024 characters.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Exfiltration
intent-browser-credential-storeextension/background.js:9Accesses a browser credential / cookie store (code comment)* - get_cookies: chrome.cookies.getAll
comment -
medium Exfiltration
intent-browser-credential-storescripts/ok/cookies.py:18Accesses a browser credential / cookie store (detector / deny-list definition)cookies: Chrome cookie 列表
detector
Files scanned: 32. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1202 chars, limit 1024
Process rating: all ten parameters 49/100
- 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
- 40Consistency. Frontmatter name (ok-skills) differs from the folder (ok-core-skills)
- 100Tools and files. No external tools needed
- 100Steps. 15 steps
- 100Execution cost. Instruction body is 559 tokens
- 100Running it twice. No mutating operations
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1202: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -32 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Structure: 11 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.