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 wpsnote/wpsnote-skills --skill wps-note-intelligent-searchgit clone --depth 1 https://github.com/wpsnote/wpsnote-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/wpsnote/wpsnote-skills/wps-note-intelligent-search)<a href="https://agentmods.dev/skills/wpsnote/wpsnote-skills/wps-note-intelligent-search"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/wps-note-intelligent-search/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/wpsnote/wpsnote-skills/wps-note-intelligent-search"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/wps-note-intelligent-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00093 | $0.02785 |
| Opus 5.5 | $0.00037 | $0.01114 |
| Sonnet 5.5 | $0.00019 | $0.00557 |
| Haiku 4.5 | $0.00009 | $0.00279 |
Grade A, and why
wps-deep-search 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 1mo 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contract（契约）
Input Contract
- 类型: 自然语言查询或结构化搜索请求
- 必填字段:
query: 用户问题或目标
- 可选字段:
context: 对话上下文filters: 时间范围、标签、项目范围、来源偏好等max_results: 默认 10，范围 1-20search_depth:quick | standard | deep（默认standard）source_mode:notes_only | web_only | hybrid（默认hybrid）
- 验证规则:
query长度 >= 2- 问题包含“最新/今日/近期”等时，必须启用网络时效检查
Output Contract
- 类型: 结构化检索结果 + 可读结论
- 保证字段:
results: 结果列表（按综合相关性排序）search_dimensions: 实际执行的检索维度evidence: 证据清单（笔记证据 + 外部证据）confidence: 每条关键结论的置信度（High/Medium/Low 或 0-100）conflicts: 冲突信息或未决点
- 约束:
- 结论必须可追溯到证据来源
- 区分“已证实”和“待验证”
- 明确哪些结论来自笔记，哪些来自外部网络
Error Handling
- 无效查询 → 返回优化建议，不直接失败
- 无匹配结果 → 自动放宽一次约束重试，仍无结果则返回“证据不足”
- 工具失败 → 返回可用部分结果 + 未完成项
- 权威来源不足 → 降级输出，不给确定性结论
核心原则
- 深度搜索不是单轮关键词匹配，而是“启发式漏斗 + 证据收敛”。
- 除非用户明确要求“只查笔记”，默认使用
hybrid（笔记 + 网络权威源）。 - 外部来源必须可追溯，
web_search摘要只能作线索，web_fetch正文才可作证据。 - 严禁编造来源、编造引用、把低权威单一来源当成定论。
- 本版本强制单代理串行执行，禁止调用
sub_agent。 - 该 Skill 为只读检索流程，不调用笔记写入类工具。
与 wps-note 的关系
本 Skill 是 wps-note 的深度检索场景封装层：
- 复用底层能力：搜索、定位、读取、标签聚合
- 新增智能能力：启发式扩展、证据融合、置信度评估
- 新增外部能力：网络权威信源检索与交叉验证
工具列表与调用方式
笔记侧工具（只读）
| 工具名 | 用途 |
|---|---|
search_notes |
笔记级召回（标题/正文/标签维度） |
search_note_content |
单篇笔记内定位关键段落 |
get_note_info |
获取元数据（标题、标签、更新时间） |
find_tags |
标签扩展与近义聚合 |
get_note_outline |
获取结构并定位读取入口 |
read_section |
章节级精读 |
read_blocks |
精确回读证据块 |
read_note / read_note_content |
全文读取（宿主工具名兼容） |
网络侧工具（只读）
| 工具名 | 用途 |
|---|---|
web_search |
单查询检索权威候选 |
batch_web_search |
多查询并行召回（推荐） |
web_fetch |
抓取正文，形成可引用证据 |
禁用工具
sub_agent（本 Skill 禁止使用）
权威信源分级（必须执行）
| 级别 | 定义 | 结论作用 |
|---|---|---|
| Tier 1（一级官方） | 政府/监管/标准组织/公司官方披露/原始机构发布 | 结论主锚点 |
| Tier 2（二级主流） | 主流媒体、头部研究机构、可追溯作者和发布时间来源 | 交叉验证 |
| Tier 3（三级补充） | 社区、自媒体、二次转载、观点文 | 线索与背景，不单独定论 |
规则：
- 关键结论优先 Tier 1；无 Tier 1 时至少要有 2 条独立 Tier 2。
- 仅 Tier 3 时只能输出“探索性判断/证据不足”。
What ships with it
6 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.
- 1mo ago First seen · 278 lines · 93 tokens per session scan A 1b0bce2a14b4
wps-deep-search is a skill published in the GitHub repository wpsnote/wpsnote-skills (183 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 2,785 once invoked, about $0.0004 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.
Other skills, from other repositories
gap-to-topic
Turn a research area into a go/no-go decision dossier for candidate thesis/proposal topics (zero or multiple justified options) — a 3-gate verdict (is the gap open? is it a contribution? is it feasible?) with the evidence laid out so the researcher can verify it. Use when the user asks "is this gap worth pursuing"…
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
research-workflow-orchestrator
Run a resumable end-to-end research workflow that automates low-risk work, pauses at explicit human decision gates, records provenance, and routes each stage to the appropriate research-hub skill or MCP tool.
literature-triage-matrix
Turn a list of papers (Zotero collection, Obsidian cluster, manual list) into a compact comparison matrix written to .research/literaturematrix.md, instead of generic per-paper summaries. Use when the user asks to "make a literature matrix", "compare these papers by method/data/limitations", or "decide which papers…
company-research-method
A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.
ccgui-plugin-creator
A plugin-building workflow for CC GUI, a desktop client that can be extended with plugins written as configuration or JavaScript modules.