Cc Sdd New Agent
gotalab/cc-sdd
Add or extend coding-agent support in cc-sdd by executing the SOP in docs/cc-sdd/sop-new-agent.md end-to-end.
基于"扩散模型叙事去噪流"的小说写作 SOP。将 AI 视为去杂质机器，通过锁定全局信号、预测叙事噪声、精准去噪、随机修正四个步骤，解决 AI 翻译腔、逻辑断层和故事平淡的问题。
Install Diffusion Narrative Denouncing
$ npx skills add canwhite/Krebs --skill diffusion-narrative-denouncing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install canwhite/Krebs diffusion-narrative-denouncing --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/canwhite/Krebs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/diffusion-narrative-denouncing .claude/skills/diffusion-narrative-denouncing && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "diffusion-narrative-denouncing" agent skill from https://github.com/canwhite/Krebs/tree/main/skills/diffusion-narrative-denouncing into .claude/skills/diffusion-narrative-denouncing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diffusion-narrative-denouncing", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/canwhite/Krebs/tree/main/skills/diffusion-narrative-denouncingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add canwhite/Krebs --skill diffusion-narrative-denouncing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install canwhite/Krebs diffusion-narrative-denouncing --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/canwhite/Krebs.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/diffusion-narrative-denouncing .agents/skills/diffusion-narrative-denouncing && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "diffusion-narrative-denouncing" agent skill from https://github.com/canwhite/Krebs/tree/main/skills/diffusion-narrative-denouncing into .agents/skills/diffusion-narrative-denouncing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diffusion-narrative-denouncing", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add canwhite/Krebs --skill diffusion-narrative-denouncing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install canwhite/Krebs diffusion-narrative-denouncing --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/canwhite/Krebs.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/diffusion-narrative-denouncing .cursor/skills/diffusion-narrative-denouncing && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "diffusion-narrative-denouncing" agent skill from https://github.com/canwhite/Krebs/tree/main/skills/diffusion-narrative-denouncing into .cursor/skills/diffusion-narrative-denouncing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diffusion-narrative-denouncing", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/canwhite/Krebs.git --path skills/diffusion-narrative-denouncing--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add canwhite/Krebs --skill diffusion-narrative-denouncing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install canwhite/Krebs diffusion-narrative-denouncing --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/canwhite/Krebs.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/diffusion-narrative-denouncing .gemini/skills/diffusion-narrative-denouncing && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "diffusion-narrative-denouncing" agent skill from https://github.com/canwhite/Krebs/tree/main/skills/diffusion-narrative-denouncing into .gemini/skills/diffusion-narrative-denouncing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diffusion-narrative-denouncing", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install canwhite/Krebs diffusion-narrative-denouncingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add canwhite/Krebs --skill diffusion-narrative-denouncing -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/canwhite/Krebs.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/diffusion-narrative-denouncing .github/skills/diffusion-narrative-denouncing && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "diffusion-narrative-denouncing" agent skill from https://github.com/canwhite/Krebs/tree/main/skills/diffusion-narrative-denouncing into .github/skills/diffusion-narrative-denouncing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diffusion-narrative-denouncing", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add canwhite/Krebs --skill diffusion-narrative-denouncing -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install canwhite/Krebs diffusion-narrative-denouncing --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/canwhite/Krebs.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/diffusion-narrative-denouncing .opencode/skills/diffusion-narrative-denouncing && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "diffusion-narrative-denouncing" agent skill from https://github.com/canwhite/Krebs/tree/main/skills/diffusion-narrative-denouncing into .opencode/skills/diffusion-narrative-denouncing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diffusion-narrative-denouncing", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
diffusion-narrative-denouncing- GitHub stars
- 1k
- Token cost
- ~831 tokens
- SKILL.md length
- 128 words
- Files
- 4 (incl. references)
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
基于"扩散模型叙事去噪流"的小说写作 SOP。将 AI 视为去杂质机器，通过锁定全局信号、预测叙事噪声、精准去噪、随机修正四个步骤，解决 AI 翻译腔、逻辑断层和故事平淡的问题。
- Tasks that involve Operations and SOPs
- SKILL.md covers 核心理念, 第一步：锁定"全局信号"（确定基调）, 第二步：识别"叙事噪声"（预测噪声 ε） and 第三步：执行"精准去噪"（生成 xₜ₋₁）, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Diffusion Narrative Denouncing is an agent skill from canwhite/Krebs. 基于"扩散模型叙事去噪流"的小说写作 SOP。将 AI 视为去杂质机器，通过锁定全局信号、预测叙事噪声、精准去噪、随机修正四个步骤，解决 AI 翻译腔、逻辑断层和故事平淡的问题。
Its SKILL.md is about 830 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/diffusion-models.md`, `references/noise-checklist.md` and `references/random-perturbation-examples.md`). Compatibility notes: 通用，适用于任何支持长文本的 AI 助手
It sits in Business, Finance & HR, covering Operations and SOPs. The repository describes itself as: An agent focused on attention management. The licence is MIT.
When your agent uses it
- Tasks that involve Operations and SOPs
Example prompts
- “扩散模型叙事去噪流”
- “/diffusion-narrative-denouncing”
Requirements
- Compatibility (from SKILL.md): 通用，适用于任何支持长文本的 AI 助手
What it can do on your machine
Read from SKILL.md and the folder at commit 31d4bea. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
通用，适用于任何支持长文本的 AI 助手
From compatibility in the SKILL.md frontmatter.
Context cost
Diffusion Narrative Denouncing loads about 831 tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 30 tokens; SKILL.md has 128 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from canwhite/Krebs at commit 31d4bea, republished under its MIT licence (© canwhite). 128 words, ~831 tokens.
Download SKILL.mdSave it as
.claude/skills/diffusion-narrative-denouncing/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- diffusion-narrative-denouncing
- description
- 基于"扩散模型叙事去噪流"的小说写作 SOP。将 AI 视为去杂质机器，通过锁定全局信号、预测叙事噪声、精准去噪、随机修正四个步骤，解决 AI 翻译腔、逻辑断层和故事平淡的问题。
- compatibility
- 通用，适用于任何支持长文本的 AI 助手
- license
- MIT
- metadata.version
- 1.0.0
- metadata.author
- Diffusion Narrative Method
- metadata.tags
- 写作, 小说, 创意写作, AI辅助写作
Diffusion 叙事去噪流
核心理念
不要求 AI 一次性变出金子，而是把它当成一个"去杂质机器"。
这套流程通过四个步骤，解决 AI 写作中的三大问题：
- AI 翻译腔：通过识别噪声让 AI 产生警惕
- 逻辑断层：通过锁定全局信息保持一致性
- 故事平淡：通过随机修正增加意外感
第一步：锁定"全局信号"（确定基调）
目的： 相当于确定加噪公式里的原图 (x₀) 比例，防止 AI 写着写着忘了主线。
Prompt 模板
我正在写一本小说，这是目前的【全书大纲】：[粘贴大纲]
这是我【前三章的内容摘要】：[粘贴摘要]
请你扮演'首席编辑'，从这两部分内容中提取：
1. **核心纹理：** 主角的语言风格、叙事视角、故事的底层逻辑。
2. **禁止区域：** 绝对不能出现的设定违和或性格崩坏。
如果理解了，请回复'基调已锁定'，先不要开始写新内容。
**输出要求：**
- 核心纹理：简洁概括，3-4句话描述风格和视角
- 禁止区域：列出4-6个关键要点，包含人物、设定、情节
- 总回复控制在300字以内关键要点
- 提供大纲和前文摘要，让 AI 理解整体语境
- 明确提取核心风格和禁止事项
- 要求确认理解后再继续
第二步：识别"叙事噪声"（预测噪声 ε）
目的： 模仿扩散模型预测噪声。让 AI 自我反思，提前识别出平庸、俗套、废话的倾向。
Prompt 模板
现在，我们要写第 [X] 章，主要情节点是：[描述这一章要发生的事]
在动笔之前，请基于你的'AI 直觉'，预测并列出这一章最容易出现的【叙事噪声】：
1. **逻辑噪声：** 哪些转折最容易显得刻意或降智？
2. **文体噪声：** 哪些描写最容易变成陈词滥调（比如：形容美女只用大眼睛）？
3. **AI 惯性：** 哪些是你最容易生成的'正确但无趣'的废话？
**输出要求：**
- 每类噪声列举2-3个最典型的
- 每个噪声点用1-2句话说明，可举例
- 总回复控制在400字以内关键要点
- 提前告诉 AI 这一章要写什么
- 让 AI 自我审查，预测可能的平庸之处
- 分三个维度识别噪声：逻辑、文体、AI 惯性
第三步：执行"精准去噪"（生成 xₜ₋₁）
目的： 执行核心去噪动作。让 AI 在避开"杂质"的前提下生成内容。
Prompt 模板
现在开始正式撰写。
**指令：** 请避开刚才识别出的'叙事噪声'。
**要求：**
1. 严格对接前文的细节颗粒度，不要跳跃。
2. 每句话都要有明确的信息量，减掉所有'为了描写而描写'的废话。
3. 保持[角色名]在第一步中锁定的性格特征。
**输出要求：**
- 这是"骨架草稿"，包含8-12个核心情节点
- 每个点用简洁短句描述（10-15字）
- 包含关键动作、对话核心、场景转换
- 可用简短的环境/状态词（如"梦境空间震颤"）
- 完全禁止详细描写和完整对话
- 格式：1.XXX 2.XXX 3.XXX...
- 总字数控制在300-400字以内
请开始写出这章的骨架草稿（8-12个核心点）。关键要点
- 明确要求避开第二步识别的噪声
- 强调信息密度和细节连贯性
- 要求保持锁定的人物性格
第四步：注入"随机修正"（增加灵感抖动）
目的： 模仿扩散模型最后的随机项。让原本"太规整"的 AI 文字产生一种像真人写出的"意外感"。
Prompt 模板
这段草稿逻辑很稳，但有点'太像 AI 写的'。
**指令：** 请在这一章里加入一次'随机扰动'（ε 修正）：
1. 加入一个**意料之外的小变数**（比如：突然打破的杯子、一个反直觉的冷笑、一段不知来源的杂音）。
2. 这个变数不需要改变大结局，但要让当前的场景产生一种'不确定性'。
3. 修改完成后，输出最终定稿。关键要点
- 承认草稿逻辑正确但缺乏特色
- 要求加入一个不改变主线但增加不确定性的细节
- 让文字产生"真人写作的意外感"
完整流程总结
| 步骤 | 名称 | 核心动作 | 解决问题 |
|---|---|---|---|
| 1 | 锁定全局信号 | 告诉它"我是谁" | 逻辑断层 |
| 2 | 识别叙事噪声 | 问它"哪些是垃圾" | AI 翻译腔 |
| 3 | 执行精准去噪 | 叫它"丢掉垃圾写" | 信息密度低 |
| 4 | 注入随机修正 | 踢它一脚要"意外" | 故事平淡 |
使用示例
写作前的完整对话流程
用户（第一步）：
我正在写一本科幻小说，大纲是：[粘贴大纲]
前三章摘要：[粘贴摘要]
请按第一步锁定基调。AI：
基调已锁定。
核心纹理：主角是冷静理性派，第一人称叙事，硬科幻逻辑。
禁止区域：主角不能突然情绪化，科技设定不能前后矛盾。用户（第二步）：
现在要写第四章，情节点是：主角进入废弃空间站。
请预测这一章的叙事噪声。AI：
逻辑噪声：最容易让主角"恰好"发现关键线索，显得刻意。
文体噪声：最容易用"阴森恐怖"来形容环境，缺乏新意。
AI 惯性：最容易堆砌"黑暗、寂静、未知"等空洞词汇。用户（第三步）：
好，现在请避开这些噪声写出草稿。[AI 生成草稿...]
用户（第四步）：
逻辑对了，但加入一个随机扰动。[AI 修改并输出最终稿...]
进阶技巧
组合使用
- 多轮迭代：可以在第三步和第四步之间多轮往返，直到满意
- 局部强化：对特定段落单独执行第二步-第四步
- 风格迁移：在第一步中提供目标作品风格，让 AI 模仿特定作者
常见问题
Q：如果 AI 在第二步列出的噪声太笼统怎么办？ A：补充具体约束，如"请针对[某角色][某场景]具体说明"
Q：第四步的随机变数会不会破坏剧情？ A：在 prompt 中强调"不改变大结局"，如果 AI 理解困难，可以手动指定变数的范围
Q：这套流程适合短篇小说吗？ A：适合，但可以简化第一步，直接用一段话描述核心设定即可
References
© canwhite, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (references) in skills/diffusion-narrative-denouncing of canwhite/Krebs.
- SKILL.md
- references/diffusion-models.md
- references/noise-checklist.md
- references/random-perturbation-examples.md
Open the folder on GitHubat commit 31d4bea
Compare with similar skills
Diffusion Narrative Denouncing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Diffusion Narrative Denouncing this skillcanwhite/Krebs | 1k | — | ~831 | Automated safety check: Pass | MIT | |
| Cc Sdd New Agentgotalab/cc-sdd | 3.7k | — | ~1.1k | Automated safety check: Pass | MIT | |
| DBS Business Toolkit Entrydontbesilent2025/dbskill | 10k | — | ~1.9k | Automated safety check: Pass | Custom licence | |
| Agent Sop Authorstrands-agents/agent-sop | 1.2k | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | |
| Polanyi Perspective0xenzyme/polanyi-skill | 137 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Sample Package function Object() { [native code] } AgentHakunaSama/SkillMiner | 100 | — | ~2k | Automated safety check: Pass | None |
Similar skills
DBS Business Toolkit Entry
dontbesilent2025/dbskill
Chinese-language entry skill for the dontbesilent business toolkit: onboards new users, orchestrates tasks across sub-skills, runs numbered prompts and lists hidden ones.
Agent Sop Author
strands-agents/agent-sop
Create (or update) and validate Agent SOPs (Standard Operating Procedures) - markdown-based workflows that guide AI agents through complex, multi-step tasks with RFC 2119 constraints.
Polanyi Perspective
0xenzyme/polanyi-skill
Michael Polanyi 的思维框架。用 Polanyi 视角分析隐性知识、技能习得、经验传承、师徒制、 知识管理、学习方法、AI/工具替代边界、科学共同体与后批判哲学问题。
Sample Package function Object() { [native code] } Agent
HakunaSama/SkillMiner
样本包构造 Agent（簇内分批器）. An agent skill from HakunaSama/SkillMiner.
Fix Issue
crazynomad/notebooklm-jetpack
Drive a single GitHub issue through a full confirm → reproduce → diagnose → fix → verify → report lifecycle, posting progress back to the issue and escalating if it can't be fixed.
More from canwhite/Krebs
Resume Optimizer
canwhite/Krebs
ATS简历优化器 - 根据职位描述(JD)和个人能力，生成符合ATS解析要求的高匹配简历. An agent skill from canwhite/Krebs.
Web Search Tool
canwhite/Krebs
提供网页搜索功能示例，演示如何使用 curl 进行 HTTP 请求。用于学习如何构建包含 scripts 和 references 的标准 skill 结构。
Simpleman
canwhite/Krebs
Simple, plain language communication. An agent skill from canwhite/Krebs.
Wechat Article
canwhite/Krebs
专业微信公众号爆款文章创作，基于痛点情绪故事在前、结论功能在后的原则，提供完整的文章结构、标题、开头、结尾生成方案. An agent skill from canwhite/Krebs.
Related
Categories
Questions about Diffusion Narrative Denouncing
What does Diffusion Narrative Denouncing do?
基于"扩散模型叙事去噪流"的小说写作 SOP。将 AI 视为去杂质机器，通过锁定全局信号、预测叙事噪声、精准去噪、随机修正四个步骤，解决 AI 翻译腔、逻辑断层和故事平淡的问题。. Diffusion Narrative Denouncing is an agent skill from canwhite/Krebs.
When should I use Diffusion Narrative Denouncing?
Diffusion Narrative Denouncing fits situations like: tasks that involve Operations and SOPs.
How do I install Diffusion Narrative Denouncing in Claude Code?
Run `npx skills add canwhite/Krebs --skill diffusion-narrative-denouncing -a claude-code`. Or copy the skill folder (skills/diffusion-narrative-denouncing in canwhite/Krebs) into .claude/skills/diffusion-narrative-denouncing in your project. Claude Code loads it when a task matches its description.
How do I install Diffusion Narrative Denouncing in Codex?
Run `npx skills add canwhite/Krebs --skill diffusion-narrative-denouncing -a codex`. Or copy the skill folder (skills/diffusion-narrative-denouncing in canwhite/Krebs) into .agents/skills/diffusion-narrative-denouncing in your project. Codex loads it when a task matches its description.
Can I use Diffusion Narrative Denouncing in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add canwhite/Krebs --skill diffusion-narrative-denouncing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/diffusion-narrative-denouncing, .gemini/skills/diffusion-narrative-denouncing, .github/skills/diffusion-narrative-denouncing and .opencode/skills/diffusion-narrative-denouncing in your project.
What does Diffusion Narrative Denouncing need to run?
SKILL.md names no scripts, command-line tools or credentials: Diffusion Narrative Denouncing is instructions for the agent only. Compatibility (from SKILL.md): 通用，适用于任何支持长文本的 AI 助手.
Does Diffusion Narrative Denouncing access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Diffusion Narrative Denouncing safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Diffusion Narrative Denouncing use?
Diffusion Narrative Denouncing is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Diffusion Narrative Denouncing use?
About 831 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.1k tokens, read only when the agent opens those files.
What are the alternatives to Diffusion Narrative Denouncing?
Skills that share tags, products or a category with Diffusion Narrative Denouncing: Cc Sdd New Agent (gotalab/cc-sdd, 3.7k stars), DBS Business Toolkit Entry (dontbesilent2025/dbskill, 10k stars), Agent Sop Author (strands-agents/agent-sop, 1.2k stars) and Polanyi Perspective (0xenzyme/polanyi-skill, 137 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Diffusion Narrative Denouncing?
canwhite (a GitHub user) maintains it in canwhite/Krebs, which has 1,038 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on August 28, 2026.
Source: canwhite/Krebs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.