BF privacy-search
隐私优先的多引擎并行搜索 Skill，提供十大搜索引擎（百度/必应/搜狗/360/DuckDuckGo/Yandex/Startpage/Qwant/Brave/本地SearXNG）并行检索。V1.7 新增 MCP Server 形态（stdio JSON-RPC 2.0 暴露 search/synthesize/fetch 三工具），可被 Claude Code/Cursor/n8n 直接挂载，让搜索能力成为任何 Agent 的即插组件。V1.6 新增 Perplexity 式答案合成（引用+正文抓取+citation）和定时引擎失效告警，jieba 默认安装提升中文精度。支持结果缓存与搜索历史、统一 HTTP 出口（隐私头/UA池/代理/自动重试真正生效）、标准 SimHash 去重、多因子加权排序（共识度/位次/相关度/权威度/域名质量）、多套备选选择器与解析诊断、bangs 语法透传、网页正文抓取、搜索结果导出（Markdown/HTML/PDF）、LLM 摘要（智谱 GLM-4-Flash + 抽取式降级）、定时 selftest + 告警、MCP Server 生态桥接。SearXNG 本地实例双路径部署，隐私模式 normal/strict 一键切换，不污染系统 Python 环境。
隐私优先的多引擎并行搜索 Skill，提供十大搜索引擎（百度/必应/搜狗/360/DuckDuckGo/Yandex/Startpage/Qwant/Brave/本地SearXNG）并行检索。V1.7 新增 MCP Server 形态（stdio JSON-RPC 2.0 暴露…
As a process F 42/100 · Will not run — References files that are not bundled: references/config.yaml.example
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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 · 0
✓ No critical or high findings
Files scanned: 26. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: references/config.yaml.example
Process rating: all ten parameters 42/100
- 0Tools and files. 1 referenced file(s) missing: references/config.yaml.example
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 20 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2988 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low 11 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)
- +3Output format is not stated: the model decides each time
- -33 of 19 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 557: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.