Agent skill

Draft Edit

by NxcoreAI in NxcoreAI/EverRoom

Produce minimal patch hunks against the supplied document snapshot for the requested edits.

Custom licenceAuto-check passed

Install Draft Edit

skills CLI
$ npx skills add NxcoreAI/EverRoom --skill draft-edit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NxcoreAI/EverRoom draft-edit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NxcoreAI/EverRoom.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agents/doc-writer/skills/draft-edit .claude/skills/draft-edit && rm -rf skills-src

Use ~/.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/

Facts

Skill name
draft-edit
GitHub stars
3k
Token cost
~257 tokens
SKILL.md length
80 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
Custom licence

At a glance

Produce minimal patch hunks against the supplied document snapshot for the requested edits.

  • Works in 8 steps: 只改 instruction… → 选最小 target:修改块内容用裸 blockId(整块… → replace 的 markdown 只包含该 target… → …
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Draft Edit is an agent skill from NxcoreAI/EverRoom. Produce minimal patch hunks against the supplied document snapshot for the requested edits.

Its SKILL.md is about 260 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: EverRoom - A workspace that remembers your projects, decisions, and sources.

Example prompts

  • “/draft-edit”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. 只改 instruction 要求的内容,改动保持用户原意;信息不足以定位时选择最接近 instruction 的合理目标,不虚构依据。
  2. 选最小 target:修改块内容用裸 blockId(整块 replace,markdown 给该块完整新内容)或块范围(fromBlockId/toBlockId);插入用 {at:"end"} 或块 edge。禁止使用 fromOffset/toOffset…
  3. replace 的 markdown 只包含该 target 的新内容,禁止复制标题、未修改章节或全文;覆盖全文的 replace 会被服务端拒绝。
  4. 一个 hunk 对应一个独立改动,hunks 之间不得重叠;delete 省略 markdown。
  5. 修改列表、引用或任务列表的内部内容时,同样替换其顶层父块并给出完整替换 markdown。
  6. target 中的 blockId 只能来自 blockIndex,不确定归属时先对照 ordinal 与 textPreview 再定。
  7. documentMarkdown 中段落末尾的 ^... 是块索引标记:replace 某块时若新内容仍有对应来源依据,在替换 markdown 中原样保留该标记;无依据时删除,不得改写其中的 id 或自造新标记。
  8. 输入携带 materialSources 或 memoryIndex 且被替换块确实整合了某来源内容时,按 SYSTEM.md 块索引标记规则在替换 markdown 的段末附对应索引标记(文档块与记忆项两类;id…

What it can do on your machine

Read from SKILL.md and the folder at commit b0d58e5. 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.

Context cost

Draft Edit loads about 257 tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 80 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~26
When it runs · the whole SKILL.md, loaded when a task matches
~257

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 80 words (~257 tokens).

“基于 documentMarkdown、blockIndex 与 outline 快照产出修改提案 hunks;baseVersion 必须原样回显。”

— opening of SKILL.md by NxcoreAI, Custom licence
name
draft-edit

Read the full SKILL.md on GitHub

Files

Just SKILL.md in agents/doc-writer/skills/draft-edit of NxcoreAI/EverRoom.

Open the folder on GitHubat commit b0d58e5

Compare with similar skills

Draft Edit 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.

Draft Edit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Draft Edit this skillNxcoreAI/EverRoom3k—~257Automated safety check: PassCustom licence
Minimalismsickn33/agentic-awesome-skills47k1 repos~2.2kAutomated safety check: PassMIT
Sbom Supply Chainsickn33/agentic-awesome-skills47k2 repos~3.4kAutomated safety check: PassMIT
Agent Supply Chaingithub/awesome-copilot40k1 repos~2.7kAutomated safety check: PassMIT
Supply Chain Securityzhaoxuya520/reverse-skill40k4 repos~953Automated safety check: WarnMIT
Implementing Supply Chain Security With In Totomukul975/Anthropic-Cybersecurity-Skills34k—~2.5kAutomated safety check: PassApache-2.0

Similar skills

  • Minimalism

    sickn33/agentic-awesome-skills

    Web and App implementation guide for the Minimalism design style.

    47k GitHub starsUsed in 1 repo~2.2k tokens
    MobileAuto-check passed
  • Sbom Supply Chain

    sickn33/agentic-awesome-skills

    Generate, sign, and verify SBOMs and provenance attestations to secure the software supply chain.

    47k GitHub starsUsed in 2 repos~3.4k tokens
    SecurityAuto-check passed
  • Agent Supply Chain

    github/awesome-copilot

    Official

    Verify supply chain integrity for AI agent plugins, tools, and dependencies.

    40k GitHub starsUsed in 1 repo~2.7k tokens
    SecurityAuto-check passed
  • Supply Chain Security

    zhaoxuya520/reverse-skill

    A skill your agent uses for software supply-chain security assessment covering SBOM, SCA, CI/CD pipelines, container images, build integrity, dependency provenance, and vulnerability reachability.

    40k GitHub starsUsed in 4 repos~953 tokens
    SecurityAuto-check: warnings
  • Implementing Supply Chain Security With In Toto

    mukul975/Anthropic-Cybersecurity-Skills

    Implements supply chain integrity verification for container builds with the in-toto framework: generating signing keys, defining a supply chain layout, recording pipeline steps as signed link…

    34k GitHub stars~2.5k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Supply Chain Guard

    davila7/claude-code-templates

    Detect and remediate software supply chain attacks in npm, PyPI, crates.io, GitHub Actions, and CI/CD pipelines by scanning for known compromised packages, malicious versions, filesystem IOCs, C2…

    32k GitHub stars~1.7k tokensUpdated today
    DevOps & CloudAuto-check: notes

More from NxcoreAI/EverRoom

All 17 skills in this repo
  • Reconstruct a complete, searchable memory from an untrusted meeting or conversation transcript.

    3k GitHub stars~714 tokensUpdated today
    Auto-check passed
  • Room Enrichment

    NxcoreAI/EverRoom

    Organize a newly created Context Room from its title and description into structured room info.

    3k GitHub stars~297 tokensUpdated today
    Auto-check passed
  • Brief Refresh

    NxcoreAI/EverRoom

    Regenerate a Context Room brief from the room's current documents and context.

    3k GitHub stars~177 tokensUpdated today
    Auto-check passed
  • Merge Name

    NxcoreAI/EverRoom

    Suggest names for a Context Room created by merging two rooms.

    3k GitHub stars~150 tokensUpdated today
    Auto-check passed
  • Canonical Schema

    NxcoreAI/EverRoom

    canonical schema 字段语义与各 provider 原始格式要点(gmail/outlook/google-calendar)。产出格式映射时使用。

    3k GitHub stars~895 tokensUpdated today
    Auto-check passed
  • Complete a rich-text document at the cursor using the EverRoom FIM protocol.

    3k GitHub stars~265 tokensUpdated today
    Auto-check passed

Questions about Draft Edit

What does Draft Edit do?

Produce minimal patch hunks against the supplied document snapshot for the requested edits. Draft Edit is an agent skill from NxcoreAI/EverRoom. Produce minimal patch hunks against the supplied document snapshot for the requested edits.

How do I install Draft Edit in Claude Code?

Run `npx skills add NxcoreAI/EverRoom --skill draft-edit -a claude-code`. Or copy the skill folder (agents/doc-writer/skills/draft-edit in NxcoreAI/EverRoom) into .claude/skills/draft-edit in your project. Claude Code loads it when a task matches its description.

How do I install Draft Edit in Codex?

Run `npx skills add NxcoreAI/EverRoom --skill draft-edit -a codex`. Or copy the skill folder (agents/doc-writer/skills/draft-edit in NxcoreAI/EverRoom) into .agents/skills/draft-edit in your project. Codex loads it when a task matches its description.

Can I use Draft Edit 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 NxcoreAI/EverRoom --skill draft-edit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/draft-edit, .gemini/skills/draft-edit, .github/skills/draft-edit and .opencode/skills/draft-edit in your project.

What does Draft Edit need to run?

SKILL.md names no scripts, command-line tools or credentials: Draft Edit is instructions for the agent only.

Does Draft Edit 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 Draft Edit 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 Draft Edit use?

Draft Edit has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Draft Edit use?

About 257 tokens (SKILL.md is roughly 1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Draft Edit?

Skills that share tags, products or a category with Draft Edit: Minimalism (sickn33/agentic-awesome-skills, 47k stars), Sbom Supply Chain (sickn33/agentic-awesome-skills, 47k stars), Agent Supply Chain (github/awesome-copilot, 40k stars) and Supply Chain Security (zhaoxuya520/reverse-skill, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Draft Edit?

NxcoreAI (a GitHub organization) maintains it in NxcoreAI/EverRoom, which has 2,983 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 8, 2026.

Source: NxcoreAI/EverRoom on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.