knowledge-curation-skill

knowledge-curation-skill is a skill for Claude Code, Codex from Supreme-Ultimate/novel-to-script-team. It costs 31 tokens per session (2,234 once invoked), scanned A, original, MIT.

A knowledge-organising process for reviewing material in a sources folder and incorporating useful information into a team's internal reference files and knowledge base. It removes duplicates and routes information to the appropriate place.

In plain words
What is it for?
Use it to review new knowledge, identify its type, check existing coverage, choose a destination, and add suitable methods, rules, or examples to the team's files.
Why use it?
It prevents useful research from becoming scattered or repeated across files. It also rejects material when its intended user, workflow stage, or practical value is unclear.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ls -la ./pending-knowledge/.

Good fit Use it to review new knowledge, identify its type, check existing coverage, choose a destination, and add suitable methods, rules, or examples to the team's files.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-team
agentmods
npx agentmods add skills/supreme-ultimate/novel-to-script-team/knowledge-curation-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 knowledge-curation-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/knowledge-curation-skill.svg)](https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/knowledge-curation-skill)
Your own site
<a href="https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/knowledge-curation-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/knowledge-curation-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,234 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 $0.00031 $0.02234
Opus 5 $0.00015 $0.01117
Sonnet 5 $0.00006 $0.00447
Haiku 4.5 $0.00003 $0.00223

Measured 8d ago against content hash 0524eaed8037, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

knowledge-curation-skill 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 8d 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.

skills/knowledge-curation-skill/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

知识收编技能

必读

  1. ../../references/index.md
  2. ../../references/07-knowledge-curation.md
  3. ../../knowledge/canon-map.md

执行模式

模式1:标准收编(~ingest)

扫描 sources/ 目录,执行知识整合。

模式2:批量收编待处理知识(~ingest-pending)

触发条件:收到 ~ingest-pending 指令

执行流程

Step 1:扫描待处理目录
ls -la ./pending-knowledge/
  • 列出所有待处理文件
  • 识别文件类型(.txt, .md, 目录等)
Step 2:逐个分析文件

对每个文件执行:

  1. 读取文件内容
  2. 提取核心知识点(3-10个)
  3. 收编前强制5问(必须明确回答,否则拒绝收编):
    • Q1:哪个 agent 会用到这个知识?(必须指定具体 agent 名称,如 script-writer、storyboard-artist)
    • Q2:在哪个阶段会用到?(必须指定具体工作流阶段,如 ~write、~storyboard-seedance)
    • Q3:现有知识库是否已覆盖?(如已覆盖且无明显增量,拒绝收编)。必须执行 grep -rn "关键概念1\|关键概念2" references/*.md,记录命中文件:行号:摘要。未执行 grep = 自动拒绝
    • Q4:目标文件行数是否安全?(执行 wc -l <目标文件>,超 800 行 [WARNING],超 1200 行 [OVERSIZED] 禁止追加)
    • Q5:是否存在多文件命中?(执行 grep -l "核心概念" references/*.md,命中 2+ 文件必须选择主文件并说明理由)
  4. 判断知识类型:
    • 方法论(归属 references/)
    • 执行规则(归属 skills/)
    • 案例示例(归属 sources/)
    • 拒绝收编(无法明确使用场景)
分级示例参考

A级(references/ 核心区)

  • ✅ 「节奏呼吸感四步法」→ ref/16(≥2 agent 用,高频)
  • ✅ 「共情四步法」→ ref/14(情绪设计核心)
  • ❌ 「70个女频梗库」→ 太具体,应为 C 级

B级(references/ 分镜区)

  • ✅ 「Seedance 景别运镜组合」→ ref/11
  • ✅ 「Beat Board 九宫格方法」→ ref/09

C级(sources/)

  • ✅ 「韩国编剧案例分析」→ sources/screenwriting-methodology/
  • ✅ 「标题起名30公式」→ sources/screenwriting-methodology/

D级(references/ 进阶区)

  • ✅ 「色彩心理学补充」→ ref/15
  • ✅ 「光影叙事新技法」→ ref/17

拒绝

  • ❌ AI 写作 prompt(与工作流无关)
  • ❌ 行业报告/职业规划(无 agent 使用场景)
  • ❌ 纯理论无可执行规则
Step 3:知识路由分析

为每个知识点生成路由表:

| 知识点 | 归属位置 | 集成方式 | 优先级 | 理由 |
|--------|---------|---------|--------|------|
| ... | references/XX.md | 新增/补充/替换 | A/B/C | ... |
Step 3.5:批量检查点(每 15 个文件)

每处理 15 个文件后输出中间报告:

### 批量检查点 #N

**本批文件**:[文件列表]
**VERIFIED**:X 个
**FAILED**:Y 个
**累计进度**:已处理 M / 总计 T

**暂停条件检查**:
- [ ] FAILED >= 3 → 暂停并报告
- [ ] 目标文件 OVERSIZED → 暂停并报告
- [ ] 主题冲突 → 暂停并报告
Step 4:执行集成
  • 使用 Edit 工具更新对应文件
  • 遵循"补充优先、替换慎重"原则
  • 保持文档结构一致性
  • 每次 Edit 后立即执行 grep -n "唯一短语" <文件> 确认写入
  • 验证成功输出:[VERIFIED] Edit <文件>
  • 验证失败重试一次,仍失败标记 [FAILED] Edit <文件> <原因>

Read the full file on GitHub · 222 lines

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. 8d ago First seen · 222 lines · 31 tokens per session scan A 0524eaed8037

Subscribe to this mod's changes

knowledge-curation-skill is a skill published in the GitHub repository Supreme-Ultimate/novel-to-script-team (162 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 2,234 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens