agentmods.dev

zh-ebn-report

zh-ebn-report is a skill for Claude Code, Codex from htlin222/zh-ebn-report-skill. It costs 343 tokens per session (6,157 once invoked), scanned A, original, MIT.

A writing coach for Taiwanese nurses preparing evidence-based nursing reports, which use research findings to guide clinical care. It covers literature reports and case analyses for nursing advancement levels N1–N4.

In plain words
What is it for?
It supports choosing a report type and topic, finding and assessing research, applying evidence to a patient case, evaluating results, and preparing reports for nursing advancement or academic submission.
Why use it?
It helps turn a clinical question into a structured report that follows Taiwanese nursing-association review requirements, including PICO questions, literature searches, critical appraisal, and APA 7 references.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code.

not rated 24repo 4mo ago A scan 343 tokens original MIT

Good fit It supports choosing a report type and topic, finding and assessing research, applying evidence to a patient case, evaluating results, and preparing reports for nursing advancement or academic submission.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/htlin222/zh-ebn-report-skill/zh-ebn-report
View source ↗ htlin222/zh-ebn-report-skill
Install

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.

Any agent
npx skills add htlin222/zh-ebn-report-skill --skill zh-ebn-report
Clone the repo
git clone --depth 1 https://github.com/htlin222/zh-ebn-report-skill

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for zh-ebn-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/htlin222/zh-ebn-report-skill/zh-ebn-report/github.svg)](https://agentmods.dev/skills/htlin222/zh-ebn-report-skill/zh-ebn-report)
Your own site
<a href="https://agentmods.dev/skills/htlin222/zh-ebn-report-skill/zh-ebn-report"><img src="https://agentmods.dev/badge/skills/htlin222/zh-ebn-report-skill/zh-ebn-report/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.

agentmods 80×15 button for zh-ebn-report

Your own site · 80×15
<a href="https://agentmods.dev/skills/htlin222/zh-ebn-report-skill/zh-ebn-report"><img src="https://agentmods.dev/badge/skills/htlin222/zh-ebn-report-skill/zh-ebn-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 343 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,157 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00343 $0.06157
Opus 5 $0.00171 $0.03078
Sonnet 5 $0.00069 $0.01231
Haiku 4.5 $0.00034 $0.00616

Measured 11d ago against content hash 3718ab941103, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

zh-ebn-report 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 11d ago.

The scan reads SKILL.md. This mod also ships 30 executable files (scripts/retro_validate.py, src/zh_ebn_report/__init__.py, src/zh_ebn_report/cli_tools.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

zh-ebn-report/SKILL.md · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

台灣護理實證報告寫作教練（Evidence-Based Nursing Report Coach for Taiwan）

這個技能協助台灣護理人員完成符合台灣護理學會與台灣實證護理學會審查標準的實證報告，涵蓋實證讀書報告與實證案例分析兩種類型。最終目的是幫助護理師通過 N2/N3/N4 進階審查，或產出可投稿的學術作品。

這份技能涵蓋哪些報告類型

台灣實證護理圈主要分成兩種入門類型：

類型 差別 對應層級 篇幅
實證讀書報告（EBR） 評析幾篇文獻後做邏輯性綜整，無個案應用 N1、N2 為主 約 8–15 頁
實證案例分析（EBP case analysis） 將實證結果應用於一位真實病人並評估成效 N3 以上 約 15–25 頁

N4 以上多已進入系統性文獻回顧或護理專案研究，本技能不涵蓋這塊。

寫作前的身分確認

在動筆前，先跟使用者釐清以下四件事，用以決定使用哪個模板與深度：

  1. 要寫哪一種報告？（讀書報告 / 案例分析）
  2. 是哪一級進階？（N1–N4，或是投稿競賽）
  3. 病房別與個案條件是什麼？（決定主題合理性與可行性）
  4. 醫院有沒有專用格式範本？（有的話以醫院範本為準，本技能補足內容）

如果這些都還沒確定，不要急著起草，先用 ask_user_input_v0 工具詢問。

核心工作流程：實證 5A 步驟

所有實證報告都圍繞這五個步驟，缺一不可（讀書報告可到 Appraise 即可，案例分析必須跑完五步）：

  1. Ask — 形成可回答的臨床問題（PICO）
  2. Acquire — 搜尋最佳文獻證據
  3. Appraise — 嚴格評讀證據（CASP + Oxford 證據等級）
  4. Apply — 臨床應用到個案（僅案例分析）
  5. Audit — 結果評值（僅案例分析）

詳細每一步的操作方式、常見錯誤、句型範例，見對應的 reference 檔案。

自動化 Pipeline 與 HITL 審稿角色分工

本技能搭配 zh-ebn-report Python CLI（位於專案根的 src/zh_ebn_report/），以 10 個具名 subagent 分工完成報告草稿。使用者的角色從「寫作者」轉為「HITL 審稿者」——在 9 個 checkpoint 介入決策、批准或要求重寫，最終的文字仍須以自己的話重寫送審（學術倫理不變）。

Subagent 分工（詳見 references/subagent-roles.md）：

# 角色 並行？
1 題目守門員 否
2 PICO 建構員 否
3 搜尋策略師 否
4 CASP 評讀員 × N 是
5 綜整整合員 否
6 分節撰寫員 × 4–6 是
7 語氣守門員 與 8 並行
8 APA 7 格式員 與 7 並行
9 個案敘事員 (案例分析) 與 10 並行
10 應用審計員 (案例分析) 與 9 並行

dispatch 原則：彼此輸入沒依賴的 agent 一律並行呼叫（Phase 4 多篇 CASP、Phase 6 各節、Phase 7 語氣+APA、Phase 5.5 個案+應用）。Claude 在互動協助情境下也應採同樣邏輯。

CLI 介面：

zh-ebn-report init --type reading|case --topic "..."
zh-ebn-report run  --resume <run-id>              # end-to-end
zh-ebn-report topic|pico|search|appraise|synthesise|write|check|render
zh-ebn-report render --final                        # 去 DRAFT 後綴（需已 review）
zh-ebn-report status <run-id>

LLM 後端（v0.6+）：pipeline 預設走 Claude Code CLI（你的 Claude 訂閱），不再強制 ANTHROPIC_API_KEY。透過 LLM_BACKEND 環境變數切換：

Read the full file on GitHub · 282 lines

Files

What ships with it

60 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.

Changes

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.

  1. 11d ago First seen · 282 lines · 343 tokens per session scan A 3718ab941103

Subscribe to this mod's changes

zh-ebn-report is a skill published in the GitHub repository htlin222/zh-ebn-report-skill (24 stars, last pushed 4mo ago), licensed MIT. It adds 343 tokens to every session and 6,157 once invoked, about $0.0017 per session on Opus 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.

Claude CodeLearning and teachingWriting and docsacademic-writingapa-citationscaspclinical-researchevidence-based-medicine
Related

Other skills, from other repositories

respond-to-eval

Turn student course evaluations (free-text + numeric) into an actionable teaching-improvement plan — the teaching analogue of /respond-to-referees. Clusters comments into themes, separates signal from noise, classifies each theme Keep / Change / Investigate / Out-of-scope, and drafts concrete changes mapped to the…

pedrohcgs/claude-code-my-workflow · 111 tokens

slide-excellence

Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", "slide excellence", or before teaching / shipping a deck. Fanout wrapper — for…

pedrohcgs/claude-code-my-workflow · 94 tokens

scaffold-exercises

Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types. Use when user says "make a problem set on X", "scaffold exercises for this lecture", "create practice problems", "generate homework with a solution key"…

pedrohcgs/claude-code-my-workflow · 101 tokens

syllabus

Build or restructure a course syllabus from a topic list or reading list — course description + prerequisites, week-by-week schedule (topic → readings → deliverables), measurable learning objectives, an assessment scheme + rubric, standard policies (late work, AI use, academic integrity, accessibility), and a per-week…

pedrohcgs/claude-code-my-workflow · 140 tokens

teach-from-paper

Turn a research paper into teaching materials — a lecture outline, the 3-5 results worth presenting (with intuition), a slide skeleton ready for /create-lecture, discussion questions, and a problem-set brief. Reads the paper end-to-end and pitches to a stated audience level. Use when user says "turn this paper into a…

pedrohcgs/claude-code-my-workflow · 102 tokens

create-lecture

Create a new Beamer lecture .tex from source papers and materials, with notation consistency checks and the project's preamble wired in. Use when user says "create a lecture on X", "new lecture from these papers", "start a deck on topic Y", "scaffold a new Beamer file", "build me a lecture from these PDFs". Scaffolds…

pedrohcgs/claude-code-my-workflow · 96 tokens