BD llm-wiki
个人知识库构建系统（基于 Karpathy llm-wiki 方法论）。让 AI 持续构建和维护你的知识库， 支持多种素材源（网页、推特、公众号、小红书、知乎、YouTube、PDF、本地文件）， 自动整理为结构化的 wiki。 触发条件：用户明确提到"知识库"、"wiki"、"llm-wiki"，或要求对已初始化的知识库执行 消化、查询、健康检查等操作。不要在用户只是要求"总结这篇文章"时触发——必须是明确的 知识库相关意图。
As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Dangerous commands
cmd-pipe-to-shell-known-hostinstall.sh:216Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)echo " 推荐安装 bun：curl -fsSL https://bun.sh/install | bash"
code literal -
low Dangerous commands
cmd-pipe-to-shell-known-hostinstall.sh:226Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)echo " 安装 uv：curl -LsSf https://astral.sh/uv/install.sh | sh"
code literal
Files scanned: 27. 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")
Process rating: all ten parameters 48/100
- 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
- 40Consistency. Frontmatter name (llm-wiki) differs from the folder (llm-wiki-personal)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 197 steps
- 100Execution cost. Instruction body is 3544 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low 17 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (7 tags): a typed call is more reliable
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)
- +3Output format is not stated: the model decides each time
- -32 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 216: enough signal without eating the budget
- +4Structure: 35 headings
- +3Step-by-step instructions: 197 items
- +4Has examples (21 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.
External checks
ClawHub: suspicious
This is a coherent local knowledge-base skill, but it needs review because URL ingestion can use browser-debugging capture, automatically fall back to an external service, and the installer can overwrite local skill directories.
LLM: suspicious (high) · VirusTotal: · 29 May 2026