Agent skill

Dify CLI Docs

by langgenius in langgenius/dify-docs

Rule pack for the Dify CLI (difyctl) doc set: en/cli/ and the Enterprise develop/cli/ trees.

CC-BY-4.0Auto-check passed

Install Dify CLI Docs

skills CLI
$ npx skills add langgenius/dify-docs --skill dify-cli-docs -a claude-code

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

GitHub CLI
$ gh skill install langgenius/dify-docs dify-cli-docs --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/langgenius/dify-docs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/dify-cli-docs .claude/skills/dify-cli-docs && 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
dify-cli-docs
GitHub stars
178
Token cost
~1.9k tokens
SKILL.md length
1,110 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
CC-BY-4.0

At a glance

Rule pack for the Dify CLI (difyctl) doc set: en/cli/ and the Enterprise develop/cli/ trees.

  • Works in 6 steps: What do I type: the synopsis in… → What do the positional arguments mean… → What flags exist: ### Flags, a table… → …
  • SKILL.md covers Readers, Source of truth (S2), Three rules that protect users and House style, plus 3 more sections
  • Calls python3; needs DIFY_TOKEN

What it does

Dify CLI Docs is an agent skill from langgenius/dify-docs. Rule pack for the Dify CLI (difyctl) doc set: en/cli/ and the Enterprise develop/cli/ trees. Readers, source of truth, house style, page shape, and content ownership. Loaded by dify-docs-write.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with Dify. The licence is CC-BY-4.0.

Example prompts

  • “/dify-cli-docs”

Requirements

  • Python 3
  • A credential in DIFY_TOKEN

Workflow steps

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

  1. What do I type: the synopsis in [optional] ...repeatable` notation, plus one line on when you would reach for it.
  2. What do the positional arguments mean and where do I get them: ### Arguments, noting the source (" from get app`").
  3. What flags exist: ### Flags, a table with Flag, Type, Default, Description. A recurring flag is described in full each time, because…
  4. What does an invocation look like: ### Examples, a verb-led caption and the command block, no result samples.
  5. What comes back: ### Output, stdout and stderr per mode, success included. -o commands get a | Format | What stdout gets | table with…
  6. What the exit codes mean: ### Exit Codes, linking Output Formats and Exit Codes for the full table.

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

    Shell commands in SKILL.md call:

    • python3

    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 these keys or tokens, usually read from environment variables:

    • DIFY_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Dify CLI Docs loads about 1.9k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 1,110 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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). 1,110 words, ~1,949 tokens.

Download SKILL.mdSave it as .claude/skills/dify-cli-docs/SKILL.md (or your agent's skills folder).
name
dify-cli-docs
description
Rule pack for the Dify CLI (`difyctl`) doc set: en/cli/ and the Enterprise develop/cli/ trees. Readers, source of truth, house style, page shape, and content ownership. Loaded by dify-docs-write.

Dify CLI Documentation

Not an entry point: dify-docs-write loads this pack for en/cli/ pages and the Enterprise develop/cli/ trees.

Readers

Developers, DevOps engineers, and technical PMs who have a Dify account and sign in through the browser device flow. They know their shell and tools like kubectl and gh, so never explain shell basics. They may not know Dify's concepts: one sentence and a link to the main docs, never a re-teach. The "Integrate Your Agents" section is for engineers wiring their own agent to call Dify apps as tools; write for that builder, at engineering depth, and keep it distinct from building agents inside Dify Studio. SSO sign-in (dfoe_ tokens) is Enterprise-only and is documented only in the Enterprise trees.

Source of truth (S2)

Every behavior claim is verified in cli/ on langgenius/dify origin/main, read at the pinned SHA per writing-guides/index.md § "Syncing the Dify codebase safely", and the report records that SHA. Not feat/cli, not cli/README.md, not the CLI's own help text: all three drift from what shipped. Where to look:

  • exact strings and exit codes: the e2e suite cli/test/e2e/suites/**
  • flags and args: cli/src/commands/<verb>/<resource>/index.ts (verb-only commands in cli/src/commands/<verb>/index.ts)
  • error codes: cli/src/errors/codes.ts
  • env vars: cli/src/env/registry.ts

A claim you cannot verify is left out or marked {/* VERIFY: … */}, never softened into a fact. For project context (known bugs, what is shipped versus planned), ask the user.

Three rules that protect users

  • The only documented way to authenticate is the browser device flow. DIFY_TOKEN and other non-interactive tokens are never shown as working auth, because readers copy auth examples into scripts.
  • Runnable examples never contain <your-app-id>: app and workspace IDs are UUID-shaped, because a non-UUID fails validation and the reader's first attempt errors. The reader's own identity is <your-*>; values they received stay concrete.
  • The en/cli/ doc set launched CE-first. Cloud-only content, which is anything that needs more than one workspace (workspace switching and membership, --workspace, -A), carries <Badge color="blue">Cloud</Badge> on its heading or list item rather than a "Cloud only" sentence; CE prose has one workspace and no "another workspace" framing.
  • Host examples use dify.example.com, never cloud.dify.ai, and since auth login defaults to cloud.dify.ai, steer the reader to enter their host rather than stating the default. If a CE release requires removing Cloud-only sections, list the exact sections and stop for approval, then remove them in a dedicated commit so git history can restore them. The Enterprise trees have multiple workspaces, so these edition rules do not apply there.

House style

A command section opens with when and why you would run it, front-loads its key limitation, and shows real terminal output, because a reader scanning for their case decides in the first line whether to stay. The vocabulary and conventions this doc set has settled on:

  • host vs server. "host" is the connection target (--host, hosts.yml, use host, "Active host", "known hosts"); "server" is the backend acting ("the server returns", "Network or server error") or its version ("client and server versions").
  • JSON, described plainly. "A data array with the paging fields page/limit/total/has_more"; error JSON is "a structured JSON object". Never "envelope".
  • App types as the product names them: Chatbot, Chatflow, Agent, Workflow, Text Generator. API mode names (chat, advanced-chat, …) only inside literal output.
  • Configurable values. When a value can be set by flag, env var, and config, say which wins in a way that leaves no doubt; a numbered list often reads clearest for a chain. A chained "A overrides B, which overrides C" leaves the referent of "which" unclear, and a bare "or" hides the order. "Override" is fine with one clear referent ("the --limit flag overrides DIFY_LIMIT") or a named, linked target.
  • Openers stay general over volatile lists; the table carries the specifics, so a new config key changes one row rather than the opener.
  • Cross-references make the command the actor ("Run auth devices list to see your sessions"), and an owned fact is linked with a short payoff instead of re-explained.
  • Backtick the typeable token, not the category word ("list commands such as get app").
  • No version numbers in prose (the version page shows real output), no "See Also" sections, and shipped reality only, except a fix the user confirms is in flight, verified before publish.
Show full SKILL.md (412 more words)Show less

Page shape

A command reference page covers one resource, one H2 per command, headings phrased as the task ("List Your Apps", never the literal command). Read a sibling page (en/cli/reference/apps.mdx; for a task page, en/cli/common-tasks.mdx) for the shape before writing, and match it where the content is alike.

Within a command, the reader's questions come in this order, and the sections follow it:

  1. What do I type: the synopsis in <required> [optional] ...repeatable notation, plus one line on when you would reach for it.
  2. What do the positional arguments mean and where do I get them: ### Arguments, noting the source ("<app-id> from get app").
  3. What flags exist: ### Flags, a table with Flag, Type, Default, Description. A recurring flag is described in full each time, because readers land mid-page.
  4. What does an invocation look like: ### Examples, a verb-led caption and the command block, no result samples.
  5. What comes back: ### Output, stdout and stderr per mode, success included. -o commands get a | Format | What stdout gets | table with captioned samples (except export and --json-only commands). Describe failures rather than quoting error strings.
  6. What the exit codes mean: ### Exit Codes, linking Output Formats and Exit Codes for the full table.

A section that would carry a single fact becomes a sentence instead; the shape serves the reader, not the reverse.

Multi-command pages open with a one-line lead-in and an index of anchor links; a one-command page opens with a plain sentence. Page-level material (how the resource works, shared concepts) goes after the commands, unless it belongs beside one command (pause and resume stay with run), in which case it stays there.

Content ownership

Each cross-cutting fact lives on one page; everywhere else links it with a short payoff.

ContentOwner
Run dispatch across app typesApps, "Run an App"
HITL pause/resume (exit 0 + status:"paused")Apps, "When a Workflow Pauses"
Workspace resolution chainWorkspaces
-o schemas, exit codes, stdout/stderr disciplineOutput Formats and Exit Codes
Global flag inventoryGlobal Flags
Help forms and topicshelp
Agent discovery (help -o json, agentGuide)help, "Machine-Readable Help"
Sign-in and token storageAuthenticate
Env-var inventoryEnvironment Variables
Compat probe and rangeversion

Checks (S7)

After the pipeline's own checks: python3 tools/check-links.py --internal must print Broken links: 0 and Broken anchors: 0 (a <Badge> in a heading joins the anchor slug, so ## Switch Your Workspace <Badge color="blue">Cloud</Badge> is #switch-your-workspace-cloud); and confirm against the ownership table that no owned fact is re-explained on the changed page.

© 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-cli-docs of langgenius/dify-docs.

Open the folder on GitHubat commit 01f1cb6

Compare with similar skills

Dify CLI Docs 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.

Dify CLI Docs compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dify CLI Docs this skilllanggenius/dify-docs178—~1.9kAutomated safety check: PassCC-BY-4.0
Frontend Code Reviewlanggenius/dify158k—~938Automated safety check: PassCustom licence
Dify Component Writing Guidelanggenius/dify158k—~626Automated safety check: PassCustom licence
Dify Command Line with difyctllanggenius/dify158k—~1.4kAutomated safety check: PassCustom licence
Deep Research21pounder/terminalAgent1202 repos~883Automated safety check: NotesApache-2.0
Dify Frontend Testinglanggenius/dify158k—~242Automated safety check: PassCustom licence

Similar skills

  • Frontend Code Review

    langgenius/dify

    Reviews frontend changes under `web/` or `packages/dify-ui/` for concrete defects and broken project contracts, using routed rule packs and a severity scale for findings.

    158k GitHub stars~938 tokensUpdated today
    DevelopmentAuto-check passed
  • Use when implementing or refactoring React/TypeScript components and the task requires decisions about component ownership, feature boundaries, state, data…

    158k GitHub stars~626 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Base skill for the difyctl CLI: discover a Dify server's operations through help output and run them as commands, always with JSON output.

    158k GitHub stars~1.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Deep Research

    21pounder/terminalAgent

    Conduct comprehensive deep research on any topic using Dify-powered workflow - searches documentation, academic papers, tutorials, APIs, best practices, and returns structured analysis with insights.

    120 GitHub starsUsed in 2 repos~883 tokens
    Research & ScienceAuto-check: notes
  • Dify Frontend Testing

    langgenius/dify

    Use when writing or changing Vitest or React Testing Library tests under `web/` or `packages/dify-ui/`, or when the user explicitly requests frontend test…

    158k GitHub stars~242 tokensUpdated today
    Testing & QAAuto-check passed
  • Frontend Testing

    Ohh-889/skyroc

    Generate Vitest + React Testing Library tests for Dify frontend components, hooks, and utilities.

    795 GitHub starsUsed in 1 repo~2.5k tokens
    Testing & QAAuto-check passed

More from langgenius/dify-docs

All 11 skills in this repo
  • Dify Docs Feature Research

    langgenius/dify-docs

    Research a Dify feature before writing or optimizing documentation.

    178 GitHub stars~2.6k tokensUpdated 7 days ago
    Auto-check passed
  • 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.

    178 GitHub stars~2.7k tokensUpdated 7 days ago
    Auto-check passed
  • 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.

    178 GitHub stars~2.3k tokensUpdated 7 days ago
    Auto-check passed
  • 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.

    178 GitHub stars~2.5k tokensUpdated 7 days ago
    Auto-check passed
  • Dify Docs Env Vars

    langgenius/dify-docs

    Rule pack for the environment variable reference — en/self-host/deploy/configuration/environments.mdx.

    178 GitHub stars~2.5k tokensUpdated 7 days ago
    Auto-check passed
  • 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.

    178 GitHub stars~3.2k tokensUpdated 7 days ago
    Auto-check passed

Works with

Questions about Dify CLI Docs

What does Dify CLI Docs do?

Rule pack for the Dify CLI (difyctl) doc set: en/cli/ and the Enterprise develop/cli/ trees. Dify CLI Docs is an agent skill from langgenius/dify-docs. Rule pack for the Dify CLI (difyctl) doc set: en/cli/ and the Enterprise develop/cli/ trees.

How do I install Dify CLI Docs in Claude Code?

Run `npx skills add langgenius/dify-docs --skill dify-cli-docs -a claude-code`. Or copy the skill folder (.claude/skills/dify-cli-docs in langgenius/dify-docs) into .claude/skills/dify-cli-docs in your project. Claude Code loads it when a task matches its description.

How do I install Dify CLI Docs in Codex?

Run `npx skills add langgenius/dify-docs --skill dify-cli-docs -a codex`. Or copy the skill folder (.claude/skills/dify-cli-docs in langgenius/dify-docs) into .agents/skills/dify-cli-docs in your project. Codex loads it when a task matches its description.

Can I use Dify CLI Docs 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-cli-docs -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-cli-docs, .gemini/skills/dify-cli-docs, .github/skills/dify-cli-docs and .opencode/skills/dify-cli-docs in your project.

What does Dify CLI Docs need to run?

Going by SKILL.md and its folder, Dify CLI Docs needs the command-line tools its instructions call (python3) and credentials named DIFY_TOKEN. Our summary lists: Python 3; A credential in DIFY_TOKEN.

Does Dify CLI Docs 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 CLI Docs 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 CLI Docs use?

Dify CLI Docs 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 CLI Docs use?

About 1.9k tokens (SKILL.md is roughly 7.8k 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 CLI Docs?

Skills that share tags, products or a category with Dify CLI Docs: Frontend Code Review (langgenius/dify, 158k stars), Dify Component Writing Guide (langgenius/dify, 158k stars), Dify Command Line with difyctl (langgenius/dify, 158k stars) and Deep Research (21pounder/terminalAgent, 120 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dify CLI Docs?

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.