card-coordinator SKILL.md skillA

card-coordinator from helixnow/deep-student is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add helixnow/deep-student/card-coordinator@v0.2.0

Pins v0.2.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
helixnow/deep-student
Path
docs/research/anki-ai-native/agents/skills/card-coordinator/SKILL.md
Versions recorded
1
Latest version
v0.2.0, committed Aug 29, 2026
Size
6,006 bytes
Repository stars
303
License
AGPL-3.0

制卡编排协调者:固化「content-curator 策展 → chatanki_run 生成 → card-qa 质检 → batch_update 修正」多代理闭环,质检交接 documentId(qa 只读自取卡片)、全部卡片写操作由主代理执行.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 制卡编排协调者(card-coordinator · Multi-agent Phase 1 → Phase 2)

本技能面向**主代理**(同时持有 `builtin-chatanki_*` 工具与子代理委派能力的会话),
把 Phase 0 的两份子代理档案(`content-curator` / `card-qa`)固化成一条可复跑的编排管线。

## 编排总线(必须按序执行)

```text
Phase A 策展   subagent(content-curator) → 制卡大纲(知识点清单 + 建议 goal)
Phase B 生成   chatanki_run(goal=大纲建议goal) → chatanki_wait 至终态 → 得 documentId
Phase C 质检   subagent(card-qa, documentId) → qa 自己 get_cards 读卡 → 裁决报告(PASS/FAIL + 补丁)
Phase D 修正   chatanki_batch_update_cards / delete_cards / add_cards 套用补丁
Phase E 复检   再次 card-qa(resume 同一会话 + 同一 documentId)→ PASS 后交付
```

### Phase A — 策展(content-curator)

1. 委派前先确认材料资源 ID 真实存在(`resource_list` / `resource_search`)。
2. 委派入参固定为:`{ "task": "材料: <资源ID/章节>。学习目标: <用户目标>。按你的输出契约产出制卡大纲。", "profile": "content-curator" }`。
3. 大纲回来后检查三件事:出处锚点是否齐全、`dup_risk: high` 条目是否需要用户裁决、
   建议路由是否与 `chatanki_analyze` 的 `routing.route` 一致(不一致以 analyze 为准并记录差异)。
4. **降级规则**:环境未安装 `content-curator` 档案或没有子代理委派工具时,主代理直接用
   `chatanki_analyze` + chatanki skill 的「策展 → 生成 → 质检 决策树」内联完成策展,不阻塞流程。

### Phase B — 生成(主代理专属写面)

1. `chatanki_run`:`goal` 用大纲的「建议 goal 文本」;`maxCards` 用
   `chatanki_analyze` 的 `recommended.maxCards`(词汇表 = 条目数 + 余量);
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add helixnow/deep-student/card-coordinator@sha256:81c9755e21b84d02

The line at the top of this page pins the label v0.2.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_uttbtpgirq3aof5e.svg)](https://markdownregistry.com/a/art_uttbtpgirq3aof5e)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Aug 29, 2026.

versioncommittedcommitsizeaudit
v0.2.0 latest2026-08-29 ccb5eb6 6,006 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6006 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

helixnow/deep-student · 303 stars · license AGPL-3.0 · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_uttbtpgirq3aof5e
GET https://markdownregistry.com/api/v1/resolve?ref=helixnow/deep-student/card-coordinator
GET https://markdownregistry.com/api/v1/blob/81c9755e21b84d021000b854bcd5ea02e970c248e5c48aa0eaa999cff33a45f4

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from helixnow/deep-student

SPSS 论文分析 SKILL.md skill
helixnow/deep-student · .skills/spss-paper-analysis/SKILL.md · 面向论文与课题写作的 SPSS 统计分析工作流。适用于 `.sav`、`csv/xlsx`、SPSS 导出结果表或截图解读场景,帮助用户先确认研究问题、变量角色、分组方式与前提条件,再组织统计执行、结果解释和论文写作输出。重点覆盖描述统计、…
v1.0.0 · audit A · 303 stars
statistics-tools SKILL.md skill
helixnow/deep-student · .skills/statistics-tools/SKILL.md · SPSS 论文分析的统计执行工具组。为 `.sav`、`csv/xlsx` 等数据分析场景声明 MCP 统计后端接口,包括数据集检查、统计分析执行、结果解释与论文表格导出。适用于需要把统计执行能力按需注入到 DeepStudent…
v1.0.0 · audit A · 303 stars
DESIGN.md@docs/dev/acr DESIGN.md file
helixnow/deep-student · docs/dev/acr/DESIGN.md
git:20260808.f473a6d · audit A · 303 stars
DESIGN.md@docs/dev/sota-conversation-core DESIGN.md file
helixnow/deep-student · docs/dev/sota-conversation-core/DESIGN.md
git:20260910.3b6b6f5 · audit A · 303 stars
card-outline SKILL.md skill
helixnow/deep-student · docs/research/anki-ai-native/agents/skills/card-outline/SKILL.md · 制卡大纲方法论:从学习材料抽取最小知识单元、决策卡型、切分粒度并排优先级,产出可直接喂给 chatanki_run 的结构化大纲
v0.1.0 · audit A · 303 stars
card-qa-checklist SKILL.md skill
helixnow/deep-student · docs/research/anki-ai-native/agents/skills/card-qa-checklist/SKILL.md · 卡片质检清单:重复(D1-D3)、粒度(G1-G4)、Cloze 规范(C1-C6)三类规则的判定标准、严重级别与补丁输出格式
v0.1.0 · audit A · 303 stars
deep-student-cloud-sync-e2e SKILL.md skill
helixnow/deep-student · dstu-test/skills/deep-student-cloud-sync-e2e/SKILL.md · Run real, UI-driven Deep Student cloud sync E2E tests. Use when Codex needs to validate WebDAV/cloud sync, backup…
git:20260630.3599d6c · audit A · 303 stars
deep-student-tauri-lab SKILL.md skill
helixnow/deep-student · dstu-test/skills/deep-student-tauri-lab/SKILL.md · Manage Deep Student Tauri desktop test instances through the repo-local tauri-lab CLI. Use when Codex needs to create…
git:20260711.4cc0dad · audit A · 303 stars

Every file in helixnow/deep-student

Browse by kind, by grade A, or by owner.