Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cafe3310/public-agent-skills --skill obsidian-knowledge-filtergit clone --depth 1 https://github.com/cafe3310/public-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cafe3310/public-agent-skills/obsidian-knowledge-filter)<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/obsidian-knowledge-filter"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/obsidian-knowledge-filter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/obsidian-knowledge-filter"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/obsidian-knowledge-filter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.01470 |
| Opus 5.5 | $0.00010 | $0.00588 |
| Sonnet 5.5 | $0.00005 | $0.00294 |
| Haiku 4.5 | $0.00002 | $0.00147 |
Grade A, and why
obsidian-knowledge-filter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
技能: Obsidian 知识筛选器 (Obsidian Knowledge Filter)
描述
此技能旨在从由大量 Markdown 文件组成的知识库(例如 Obsidian Vault)中,通过一个精确且分阶段的工作流,进行知识的检索、筛选和提取。它采用带编号前缀的 YAML 和 Markdown 文件来管理每一步的中间数据,并在每个关键步骤暂停以供用户审阅,确保最终产出的内容高度相关且无重复。
核心理念: 此技能的目标是在用户的指导下,通过一系列独立的脚本和分析步骤,精确地从知识库中提炼与特定主题相关的信息,并通过结构化的方式呈现,最终形成综合分析报告。
何时使用
当用户请求您通过查找、关联和综合分散在个人知识库中的信息来解决复杂问题时,请使用此技能。此工作流特别适用于需要高精度、希望减少冗余信息并全程参与筛选过程的场景。
工作流程
该过程分为四个主要阶段,每个阶段都以用户审阅为节点。
阶段 1: 关键词搜索与分析
步骤 1.1: 运行分析脚本 001_analyze_files.py
此脚本递归地在指定目录中搜索所有 .md 文件,并执行以下操作:
-
文件排除: 自动跳过任何路径中包含
tmp-,_attachments, 或.trash的文件/目录。 -
关键词分析: 查找包含指定关键词的文件,记录每个关键词的出现频率。
-
上下文合并: 将包含关键词的行的上下文(默认为前后 10 行)合并成连续的行号区间。
-
输出: 在一个新建的
tmp-YYYY-MM-DD-HH-MM-SS-analysis/临时目录中,生成001_analysis.yaml。
001_analysis.yaml 格式详解:
这是一个 YAML 文件,包含一个文件信息对象的列表。每个对象都具有以下结构:
- file_path: '文件夹/2025-12-29-示例文件.md' # 相对于当前工作目录的路径
keyword_counts:
- word: '关键词1'
count: 5
- word: '关键词2'
count: 2
line_ranges:
- [10, 30] # 第一个内容提取区间
- [45, 65] # 第二个内容提取区间
步骤 1.2: 用户审阅分析文件
Agent 暂停并请求用户审阅 001_analysis.yaml,用户可手动编辑此文件以增删文件或修改行号区间。
阶段 2: 内容提取与清理
步骤 2.1: 运行提取脚本 002_extract_content.py
用户确认后,此脚本会读取 001_analysis.yaml,并根据其中的 file_path 和 line_ranges 提取相应的内容。
-
内容清理: 在提取内容后,脚本会执行以下三项自动清理:
- 合并换行: 将连续的多个换行符合并为一个。
- 移除加粗: 删除所有的 Markdown 加粗标记 (
**)。 - 移除图片: 删除所有的 Markdown 图片链接 (
![[...]])。
-
输出: 在同一个临时目录中,生成
002_content.yaml,其结构与001_analysis.yaml类似,但每个对象都增加了一个content字段。
002_content.yaml 格式详解:
- file_path: '文件夹/2025-12-29-示例文件.md'
keyword_counts:
# ... (同上)
line_ranges:
# ... (同上)
content: "这是从文件中提取并清理后的文本内容...\n..."
步骤 2.2: 用户审阅内容文件
Agent 再次暂停,请求用户审阅 002_content.yaml,确保提取和清理后的内容符合预期。
阶段 3: 内容洞察综合
步骤 3.1: Agent 进行分块综合分析
用户确认后,Agent 开始对 002_content.yaml 进行智能分析。为提升效率并保证分析的连贯性,Agent 采用分块「读取-分析-写出」循环模式:
- 分块读取: Agent 以 1000 行为单位,逐块读取
002_content.yaml文件;例如,第一次会读取 1-1000 行。 - 综合分析: 针对刚才读取的 整个内容块(其中可能包含多个文件片段),Agent 在内部进行一次性综合分析,提炼出所有与用户任务相关的洞察、观点和联系。
- 单次写入: Agent 将 2 产生的分析洞察,一次性地追加写入到
003_content_analysis.md文件中,清晰地标注每个洞察来源于哪个文件。 - 循环执行: 跳到 1 继续下一块,直到处理完所有内容块。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 114 lines · 24 tokens per session scan A f0bc109142e8
obsidian-knowledge-filter is a skill published in the GitHub repository cafe3310/public-agent-skills (256 stars, last pushed 9d ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,470 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
obsidian-knowledge-filter compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| obsidian-knowledge-filtercafe3310/public-agent-skills | Skill | 256 | 9d ago | Apache-2.0 | A | 24 | Claude Code, Codex |
| memory-initflc1125/skills | Skill | 39 | today | MIT | A | 50 | Claude Code, Codex |
| paleo-automocasus/paleo | Skill | 21 | 3mo ago | MIT | A | 79 | Claude Code |
| paleo-trim-contextmocasus/paleo | Skill | 21 | 3mo ago | MIT | A | 40 | Claude Code |
| paleo-conversemocasus/paleo | Skill | 21 | 3mo ago | MIT | A | 82 | Claude Code |
| firstsun-harnessfirstsun-dev/skills | Skill | 5 | 5d ago | none | A | 141 | Codex |
| rem-sleepfirstsun-dev/skills | Skill | 5 | 5d ago | none | A | 55 | Claude Code, Codex |