AI Index
mizchi/skills
Method and tooling for measuring how AI-generated a piece of prose reads, in Japanese or English.
Judge a finished draft as the docs owner would: a fresh agent reads it against the style guide and the reference page in its genre, marks the sentences that fall short, and returns a ship verdict on…
Install Dify Docs Editor Test
$ npx skills add langgenius/dify-docs --skill dify-docs-editor-test -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install langgenius/dify-docs dify-docs-editor-test --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/langgenius/dify-docs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/dify-docs-editor-test .claude/skills/dify-docs-editor-test && 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 "dify-docs-editor-test" agent skill from https://github.com/langgenius/dify-docs/tree/main/.claude/skills/dify-docs-editor-test into .claude/skills/dify-docs-editor-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dify-docs-editor-test", 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/langgenius/dify-docs/tree/main/.claude/skills/dify-docs-editor-testType 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 langgenius/dify-docs --skill dify-docs-editor-test -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install langgenius/dify-docs dify-docs-editor-test --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/langgenius/dify-docs.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/dify-docs-editor-test .agents/skills/dify-docs-editor-test && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "dify-docs-editor-test" agent skill from https://github.com/langgenius/dify-docs/tree/main/.claude/skills/dify-docs-editor-test into .agents/skills/dify-docs-editor-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dify-docs-editor-test", 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 langgenius/dify-docs --skill dify-docs-editor-test -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install langgenius/dify-docs dify-docs-editor-test --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/langgenius/dify-docs.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/dify-docs-editor-test .cursor/skills/dify-docs-editor-test && 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 "dify-docs-editor-test" agent skill from https://github.com/langgenius/dify-docs/tree/main/.claude/skills/dify-docs-editor-test into .cursor/skills/dify-docs-editor-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dify-docs-editor-test", 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/langgenius/dify-docs.git --path .claude/skills/dify-docs-editor-test--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 langgenius/dify-docs --skill dify-docs-editor-test -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install langgenius/dify-docs dify-docs-editor-test --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/langgenius/dify-docs.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/dify-docs-editor-test .gemini/skills/dify-docs-editor-test && 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 "dify-docs-editor-test" agent skill from https://github.com/langgenius/dify-docs/tree/main/.claude/skills/dify-docs-editor-test into .gemini/skills/dify-docs-editor-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dify-docs-editor-test", 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 langgenius/dify-docs dify-docs-editor-testInstalls 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 langgenius/dify-docs --skill dify-docs-editor-test -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/langgenius/dify-docs.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/dify-docs-editor-test .github/skills/dify-docs-editor-test && 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 "dify-docs-editor-test" agent skill from https://github.com/langgenius/dify-docs/tree/main/.claude/skills/dify-docs-editor-test into .github/skills/dify-docs-editor-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dify-docs-editor-test", 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 langgenius/dify-docs --skill dify-docs-editor-test -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install langgenius/dify-docs dify-docs-editor-test --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/langgenius/dify-docs.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/dify-docs-editor-test .opencode/skills/dify-docs-editor-test && 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 "dify-docs-editor-test" agent skill from https://github.com/langgenius/dify-docs/tree/main/.claude/skills/dify-docs-editor-test into .opencode/skills/dify-docs-editor-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dify-docs-editor-test", 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
dify-docs-editor-test- GitHub stars
- 178
- Token cost
- ~1.5k tokens
- SKILL.md length
- 478 words
- Files
- 1
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- CC-BY-4.0
At a glance
Judge a finished draft as the docs owner would: a fresh agent reads it against the style guide and the reference page in its genre, marks the sentences that fall short, and returns a ship verdict on…
- Works in 3 steps: Agree the dispatch with the owner before… → Dispatch the fresh sub-agent(s)… → Relay the report unedited. Then act on…
- Tasks that involve Linting and formatting
- SKILL.md covers Procedure and Dispatch prompt
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Dify Docs Editor Test is an agent skill from langgenius/dify-docs. Judge a finished draft as the docs owner would: a fresh agent reads it against the style guide and the reference page in its genre, marks the sentences that fall short, and returns a ship verdict on the work of this round. Runs in the pipeline's Check stage before any linter.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Writing & Content, covering Linting and formatting. It works with Dify. The licence is CC-BY-4.0.
When your agent uses it
- Tasks that involve Linting and formatting
Example prompts
- “/dify-docs-editor-test”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Agree the dispatch with the owner before sending anything: how many judges, and what each reads. A page written or rewritten whole gets…
- Dispatch the fresh sub-agent(s) (subagent_type: general-purpose) with the template below, filling {DRAFT} (absolute path), {STANDARD} (the…
- Relay the report unedited. Then act on it. The verdict judges this round's work. "Ship with light edits": fix the marked sentences. "Needs…
What it can do on your machine
Read from SKILL.md and the folder at commit 01f1cb6. 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
Dify Docs Editor Test loads about 1.5k tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 478 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 langgenius/dify-docs at commit 01f1cb6, republished under its CC-BY-4.0 licence (© langgenius). 478 words, ~1,457 tokens.
Download SKILL.mdSave it as
.claude/skills/dify-docs-editor-test/SKILL.md (or your agent's skills folder).- name
- dify-docs-editor-test
- description
- Judge a finished draft as the docs owner would: a fresh agent reads it against the style guide and the reference page in its genre, marks the sentences that fall short, and returns a ship verdict on the work of this round. Runs in the pipeline's Check stage before any linter.
Editor Test
The linters measure mechanics. This test measures the writing, and it only measures anything if the judge has not seen the research: a fresh sub-agent gets the draft, the style guide, the reference page, and the shape the page's type follows, and nothing else.
Procedure
- Agree the dispatch with the owner before sending anything: how many judges, and what each reads. A page written or rewritten whole gets its own judge, unless several pages were drafted as one topic and the marks need the cross-page view, in which case one judge reads the set. A round that changed parts of pages sends the touched pages to one judge, each with its changed sections named, or to several judges split by topic when the set is large. Pages of different genres go to different judges, because the reference page differs. One judge per page is a choice, not the default. When no reviewer is in the session, state the dispatch in the report or PR description and proceed.
- Dispatch the fresh sub-agent(s) (
subagent_type: general-purpose) with the template below, filling{DRAFT}(absolute path),{STANDARD}(the style guide's path),{EXEMPLAR}(the reference page in the draft's genre:en/cloud/use-dify/build/new-agent/overview.mdxfor a concept page,en/cloud/use-dify/build/new-agent/build.mdxfor a task page or a reference),{SHAPE}(the pack's page-shape or conventions for this document type, as a path or a path with a section name,path § Section: the CLI pack'sSKILL.md § Page shape, the API pack'sreferences/spec-conventions.md, the env-var pack'sSKILL.md § Document Structure; for a page with no pack, the line reads "none"), and{CHANGED}("the whole page", or the sections and paragraphs this round changed, named as the reader would find them). When one judge reads several pages, the page block (files 3 and 4 and the changed line) and the reply repeat per page, under the page's path. The shape file keeps the judge from marking a required table or synopsis as a fault; the language inside the structure is still judged. Put nothing else in the prompt: no fact sheet, no research, no account of what changed beyond that line, no concerns of your own. - Relay the report unedited. Then act on it. The verdict judges this round's work. "Ship with light edits": fix the marked sentences. "Needs heavy edits": rewrite the marked units whole, from their job. "Needs rewrite": hand the draft and the marks to a fresh drafter, as the pipeline's Write stage does for a changed idea. After either rewrite, dispatch a new judge; never send a revised draft to the same one. Marks outside the change are the page's standing debt: report them to the owner as a list with a proposal for each (fix in this round, or a follow-up), and touch none of them without that decision, because on a release branch a page's debt is not this round's scope.
Show full SKILL.md (2 more words)Show less
Dispatch prompt
You are the editor of a documentation set, reading a draft the way its owner
would before deciding whether it can ship.
Read exactly these files, in this order:
1. {STANDARD}: the whole style guide. Its opening section, "What a Good
Page Does", is the standard; the sections after it are the rules a
page also has to meet.
2. {EXEMPLAR}: a page the owner wrote. It calibrates register and judgment
about what to leave out; the standard in file 1 is the authority. Do not
copy it; measure against it.
Then, for each page under review:
3. {SHAPE}: the conventions this kind of page follows (its sections, tables,
synopsis blocks), given as a file or as one named section of a file;
read only that section. A structure the conventions require is not a
fault; judge the sentences inside it. If this line reads "none", skip it.
4. {DRAFT}: the page under review.
This round changed: {CHANGED}. Read the whole page regardless: a
sentence is judged in the context the page gives it, and a change is
judged by whether it fits the page it landed in.
Read nothing else and run no other command.
Mark every sentence in the draft that falls short of the bar, quoting it,
with one tag each:
- transcribed: a fact stated with no reader who would ask for it here
- reason: a why-clause on an instruction the reader would have followed anyway
- interface: describes what the reader can see on screen at that moment
- dense: two separable ideas in one sentence, or a paragraph that runs past
the point where the reader's question changed
- vocabulary: a word from the code, the spec, or the team, not the product
- missing: a place the reader needed a judgment (what to choose, what to
avoid, what happens if they get it wrong) and got a description
- rule: breaks a rule in a later section of the style guide; name the section
Then give one verdict on this round's work: Ship with light edits / Needs
heavy edits / Needs rewrite, with one sentence on what decided it. Marks
outside the change do not move the verdict; list them separately.
Do not check facts, formatting, links, or terminology. Do not rewrite. Judge
only whether this is writing the owner would put their name to.
Reply with exactly this, once per page, under the page's path:
- **Marked, in this change**: [quoted sentence — tag — five words on why; for rule, the section], one per line, or "none"
- **Marked, elsewhere on the page**: same form, or "none"
- **Best passage**: [the section that meets the bar, in a phrase]
- **Verdict**: [one of the three, and the deciding sentence]© langgenius, CC-BY-4.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/dify-docs-editor-test of langgenius/dify-docs.
Open the folder on GitHubat commit 01f1cb6
Compare with similar skills
Dify Docs Editor Test 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 |
|---|---|---|---|---|---|---|
| Dify Docs Editor Test this skilllanggenius/dify-docs | 178 | — | ~1.5k | Automated safety check: Pass | CC-BY-4.0 | |
| AI Indexmizchi/skills | 356 | — | ~3.6k | Automated safety check: Pass | None | |
| Ig CaptionJakeschincariol/instagram-agent-skill | 458 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Prism Maintainirfndi/prism-liquidity-agent | 122 | — | ~1k | Automated safety check: Pass | MIT | |
| Post Formattercharlie947/social-media-skills | 3.8k | — | ~1.4k | Automated safety check: Pass | MIT | |
| PolishMJbae/awesome-novel-studio | 155 | — | ~3.6k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Ig Caption
Jakeschincariol/instagram-agent-skill
Write the Instagram caption - the line that survives the "...
Prism Maintain
irfndi/prism-liquidity-agent
Maintain the Prism codebase: measure cyclomatic complexity, refactor hotspots, and enforce the anti-slop type discipline.
Post Formatter
charlie947/social-media-skills
Turn a topic into a ready-to-publish LinkedIn post using PAS, AIDA, BAB, STAR, or SLAY frameworks.
Polish
MJbae/awesome-novel-studio
웹소설 윤문 스킬. An agent skill from MJbae/awesome-novel-studio.
Clarity
addyosmani/clarity
Draft, rewrite, or review reader-facing prose so it is specific, useful, and recognizably the author's without inventing facts or performing humanness.
More from langgenius/dify-docs
All 11 skills in this repoDify Docs Feature Research
langgenius/dify-docs
Research a Dify feature before writing or optimizing documentation.
Dify Docs Format Check
langgenius/dify-docs
Check formatting compliance in changed documentation against writing-guides/formatting-guide.md and tools/translate/formatting-{zh,ja}.md.
Dify Docs Terminology Check
langgenius/dify-docs
Audit terminology consistency across documentation against the codebase UI labels and the glossary — in prose and in the UI strings shown in screenshots.
Dify Docs API Reference
langgenius/dify-docs
Rule pack for the Service API specs ({en,zh,ja}/api-reference/openapiservice.json): spec conventions, app-type scoping, code-verification rules, and the audit machinery.
Dify Docs Env Vars
langgenius/dify-docs
Rule pack for the environment variable reference — en/self-host/deploy/configuration/environments.mdx.
Dify Docs Write
langgenius/dify-docs
The entry point for writing or revising any documentation in this repo: user guides, deployment pages, plugin-dev pages, API specs, the env-var reference, CLI pages.
Related
Works with
Categories
Questions about Dify Docs Editor Test
What does Dify Docs Editor Test do?
Judge a finished draft as the docs owner would: a fresh agent reads it against the style guide and the reference page in its genre, marks the sentences that fall short, and returns a ship verdict on…. Dify Docs Editor Test is an agent skill from langgenius/dify-docs. Judge a finished draft as the docs owner would: a fresh agent reads it against the style guide and the reference page in its genre, marks the sentences that fall short, and returns a ship verdict on the work of this round.
When should I use Dify Docs Editor Test?
Dify Docs Editor Test fits situations like: tasks that involve Linting and formatting.
How do I install Dify Docs Editor Test in Claude Code?
Run `npx skills add langgenius/dify-docs --skill dify-docs-editor-test -a claude-code`. Or copy the skill folder (.claude/skills/dify-docs-editor-test in langgenius/dify-docs) into .claude/skills/dify-docs-editor-test in your project. Claude Code loads it when a task matches its description.
How do I install Dify Docs Editor Test in Codex?
Run `npx skills add langgenius/dify-docs --skill dify-docs-editor-test -a codex`. Or copy the skill folder (.claude/skills/dify-docs-editor-test in langgenius/dify-docs) into .agents/skills/dify-docs-editor-test in your project. Codex loads it when a task matches its description.
Can I use Dify Docs Editor Test 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 langgenius/dify-docs --skill dify-docs-editor-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dify-docs-editor-test, .gemini/skills/dify-docs-editor-test, .github/skills/dify-docs-editor-test and .opencode/skills/dify-docs-editor-test in your project.
What does Dify Docs Editor Test need to run?
SKILL.md names no scripts, command-line tools or credentials: Dify Docs Editor Test is instructions for the agent only.
Does Dify Docs Editor Test 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 Dify Docs Editor Test 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 Dify Docs Editor Test use?
Dify Docs Editor Test is published under the CC-BY-4.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Dify Docs Editor Test use?
About 1.5k tokens (SKILL.md is roughly 5.8k 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 Dify Docs Editor Test?
Skills that share tags, products or a category with Dify Docs Editor Test: AI Index (mizchi/skills, 356 stars), Ig Caption (Jakeschincariol/instagram-agent-skill, 458 stars), Prism Maintain (irfndi/prism-liquidity-agent, 122 stars) and Post Formatter (charlie947/social-media-skills, 3.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Dify Docs Editor Test?
langgenius (a GitHub organization) maintains it in langgenius/dify-docs, which has 178 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 30, 2026.
Source: langgenius/dify-docs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.