FC academic-knowledge-base
面向学术研究者的个人知识中枢。整合 Karpathy LLM Wiki 知识编译能力 + SmartLib 海量文献检索能力，形成私有知识库与外部文献库双轨联动的研究助手。 支持4类数据入库（文献检索结果、用户上传文献、资讯报道、个人学术数据）、研究专题（文献子集+智能命名+笔记+AI分析+导出）、向量化语义检索、分词匹配检索、参考文献管理、Wiki知识层自动维护。 ✨ 亮点：入库文献自动保留原始数据库来源链接（覆盖300+数据库，如Scopus/WoS/EI/PubMed等，覆盖率100%），支持多源交叉验证。 采用懒加载引导式初始化，无需前置配置即可使用。配额管理复用 global-biblio-base 的 gateway 凭证和计次规则（v3.1：5接口，每次调用计1次），配额耗尽后暂停外部检索请求。 适用场景：文献管理、知识积累、论文写作辅助、研究调研。触发词：保存到知识库、知识库统计、我的知识库、给这篇打标签、列出我的专题、文献管理、论文管理、我的论文库、文献收藏、研究笔记、知识整理、学术知识库、论文知识库、文献整理、学术笔记、研究知识管理、收藏这篇文章、加入知识库、文献综述工具。 A personal knowledge hub for academic researchers — integrating Karpathy LLM Wiki + SmartLib literature search + vectorized semantic retrieval. Ingested literature automatically preserves original database source links (300+ databases, 100% coverage) for cross-verification. Quota managed via global-biblio-base gateway with v3.0 billing rules (5 interfaces, 1 quota per successful call), restricted display when quota exhausted. Production URL: read from global-biblio-base/config.json → SMARTLIB_GATEWAY_URL (Gateway v47, version 67)
面向学术研究者的个人知识中枢。整合 Karpathy LLM Wiki 知识编译能力 + SmartLib 海量文献检索能力，形成私有知识库与外部文献库双轨联动的研究助手。…
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
- 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
-
critical Secrets in code
secret-openai-keyconfig.json:3OpenAI-style API key (quoted — discussed, not commanded)"SMARTLIB_GATEWAY_SECRET": "sk-O…mi2",
quoted
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Write Edit Bash WebFetch AskUserQuestion
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1041 chars, limit 1024 - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "agent_created" - note
frontmatter-keyunknown frontmatter key "recommends" - note
frontmatter-keyunknown frontmatter key "disable"
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 17 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3440 tokens
- low 19 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)
- +3Description length 1040: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 40 headings
- +3Step-by-step instructions: 17 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.