New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Regenerating AI Content

by Comfy-Org in Comfy-Org/workflow_templates

Manages AI content generation for the ComfyUI template site.

MITAuto-check passedAI & LLM Engineering

Install Regenerating AI Content

skills CLI
$ npx skills add Comfy-Org/workflow_templates --skill regenerating-ai-content -a claude-code

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

GitHub CLI
$ gh skill install Comfy-Org/workflow_templates regenerating-ai-content --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/Comfy-Org/workflow_templates.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/regenerating-ai-content .claude/skills/regenerating-ai-content && 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
regenerating-ai-content
GitHub stars
1.3k
Token cost
~922 tokens
SKILL.md length
349 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Manages AI content generation for the ComfyUI template site.

  • Asked to: regenerate content
  • SKILL.md covers Overview, All commands must be run from…, Common Commands and Requirements, plus 4 more sections
  • Calls pnpm; needs OPENAI_API_KEY
  • Refresh AI content

What it does

Regenerating AI Content is an agent skill from Comfy-Org/workflow_templates. Manages AI content generation for the ComfyUI template site. Regenerates descriptions, clears cache, debugs placeholder content, and runs the AI pipeline. Use when asked to: regenerate content, refresh AI content, clear cache, fix placeholder text, re-run AI generation, update generated descriptions, force regenerate, check cache status, debug AI content, why is content missing, content looks wrong, run the AI pipeline, generate descriptions, update AI text, rebuild content, fix generated content, content not…

Its SKILL.md is about 920 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 AI & LLM Engineering, covering Diffusion and image models. It works with ComfyUI and pnpm. The repository describes itself as: ComfyUI template workflows. The licence is MIT.

When your agent uses it

  • Asked to: regenerate content
  • Refresh AI content
  • Fix placeholder text
  • Re-run AI generation

Example prompts

  • “Use the regenerating-ai-content skill to manage AI content generation for the ComfyUI template site”
  • “/regenerating-ai-content”

Requirements

  • A credential in OPENAI_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 8be1f8c. 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:

    • pnpm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • OPENAI_API_KEY

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

Context cost

Regenerating AI Content loads about 922 tokens when it runs. Until then it costs about 180 tokens; SKILL.md has 349 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~180
When it runs · the whole SKILL.md, loaded when a task matches
~922

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 Comfy-Org/workflow_templates at commit 8be1f8c, republished under its MIT licence (© Comfy-Org). 349 words, ~922 tokens.

Download SKILL.mdSave it as .claude/skills/regenerating-ai-content/SKILL.md (or your agent's skills folder).
name
regenerating-ai-content
description
Manages AI content generation for the ComfyUI template site. Regenerates descriptions, clears cache, debugs placeholder content, and runs the AI pipeline. Use when asked to: regenerate content, refresh AI content, clear cache, fix placeholder text, re-run AI generation, update generated descriptions, force regenerate, check cache status, debug AI content, why is content missing, content looks wrong, run the AI pipeline, generate descriptions, update AI text, rebuild content, fix generated content, content not showing, stale content, outdated descriptions. Triggers on: regenerate, AI content, clear cache, placeholder, generate descriptions, content pipeline, refresh content, rebuild AI.

Regenerating AI Content

Overview

The site at site/ uses an AI pipeline (site/scripts/generate-ai.ts) that generates the following fields for each template page:

  • extendedDescription
  • howToUse
  • metaDescription
  • suggestedUseCases
  • faqItems

Results are cached in site/.content-cache/ and written to site/src/content/templates/ (git-ignored).

All commands must be run from the site/ directory

Ensure pnpm is installed before running any commands.

Common Commands

TaskCommand
Regenerate ALL contentpnpm run generate:ai
Regenerate one templatepnpm run generate:ai -- --template <name>
Force regenerate (ignore cache)pnpm run generate:ai -- --force
Force one templatepnpm run generate:ai -- --template <name> --force
Test mode (first template only)pnpm run generate:ai:test
Skip AI (use placeholders)pnpm run generate:ai -- --skip-ai
Dry run (preview changes)pnpm run generate:ai -- --dry-run
View cache statspnpm run cache:status
Clear all cachepnpm run cache:clear --force
Preview what cache clear would deletepnpm run cache:clear --dry-run

Requirements

  • OPENAI_API_KEY environment variable must be set (unless using --skip-ai).

How Caching Works

  • Cache lives in site/.content-cache/ with a _manifest.json tracking hashes.
  • Cache invalidates when:
    • Template metadata changes (hash mismatch)
    • Prompt files change (prompts hash)
    • Cache version is bumped
  • --force bypasses all cache checks.
  • --dry-run shows what would be regenerated without making changes.

Debugging Common Issues

Placeholder text showing

Template was generated with --skip-ai.

Fix: Run pnpm run generate:ai -- --template <name>.

Content is stale/outdated

Cache hit on old content.

Fix: Run with --force flag: pnpm run generate:ai -- --template <name> --force.

OPENAI_API_KEY not set

Set the environment variable or use --skip-ai for development.

Content doesn't match override

Overrides in site/overrides/templates/ merge on top of AI content. Check if there's an override file conflicting with expectations.

humanEdited template not regenerating

By design. Templates with humanEdited: true in their override file skip AI generation entirely. Remove the override file or set humanEdited: false to re-enable.

Content Template Types

The pipeline auto-selects one of the following types based on template metadata:

  • tutorial
  • showcase
  • comparison
  • breakthrough

These correspond to prompt files in site/knowledge/prompts/.

Rules

  • Always run commands from the site/ directory.
  • Never manually edit files in site/src/content/templates/ — they are generated.
  • Never manually edit site/.content-cache/ — use the CLI commands.
  • The site/overrides/templates/ directory is for human overrides, not AI content.

© Comfy-Org, MIT. 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/regenerating-ai-content of Comfy-Org/workflow_templates.

Open the folder on GitHubat commit 8be1f8c

Compare with similar skills

Regenerating AI Content 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.

Regenerating AI Content compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Regenerating AI Content this skillComfy-Org/workflow_templates1.3k—~922Automated safety check: PassMIT
Docs I18n TranslateComfy-Org/docs300—~3.2kAutomated safety check: NotesGPL-3.0
Cms Changelog SyncComfy-Org/docs300—~5.2kAutomated safety check: WarnGPL-3.0
Comfyui Skill OpenclawHuangYuChuh/ComfyUI_Skills_OpenClaw413—~2.7kAutomated safety check: PassApache-2.0
ComfyUI Custom Node BuilderConstantineB6/comfy-pilot230—~897Automated safety check: PassMIT
Docs I18n ReviewComfy-Org/docs300—~926Automated safety check: NotesGPL-3.0

Similar skills

  • Docs I18n Translate

    Comfy-Org/docs

    Translate ComfyUI Mintlify docs from English MDX to ja/zh/ko using translate-i18n.ts.

    300 GitHub stars~3.2k tokensUpdated today
    Frontend & DesignAuto-check: notes

  • Cms Changelog Sync

    Comfy-Org/docs

    Sync ComfyUI release notes to Strapi CMS: LLM-simplify English changelog for in-app popup, translate to zh/ja/ko/fr/ru/es in staging, push drafts to CMS.

    300 GitHub stars~5.2k tokensUpdated today
    DevelopmentAuto-check: warnings

  • Comfyui Skill Openclaw

    HuangYuChuh/ComfyUI_Skills_OpenClaw

    Run registered ComfyUI workflows through the fast comfyui-skill CLI, and use the official local Comfy MCP for live template, node, model, validation, and orchestration capabilities.

    413 GitHub stars~2.7k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • ComfyUI Custom Node Builder

    ConstantineB6/comfy-pilot

    Helps an agent write ComfyUI custom nodes in Python, including wrapping an existing script, mapping data types and handling image batches.

    230 GitHub stars~897 tokensUpdated 7 mo ago
    AI & LLM EngineeringAuto-check passed

  • Docs I18n Review

    Comfy-Org/docs

    Review ComfyUI docs translation quality with LLM-as-a-judge (review-i18n.ts).

    300 GitHub stars~926 tokensUpdated today
    Frontend & DesignAuto-check: notes

  • Continuity Render

    roadmaus/ComfyUI-Continuity

    Render videos and pictures on a ComfyUI server that has the Continuity node pack (MiniMax H3, LTX 2.5, Krea 2, Ideogram 4, Qwen Image, Flux 2 Klein) with one command, the render.py bundled in this…

    133 GitHub stars~1.7k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

More from Comfy-Org/workflow_templates

All 10 skills in this repo

  • Editing Site Content

    Comfy-Org/workflow_templates

    Edits, updates, rewrites, or adds content on the ComfyUI template site pages.

    1.3k GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Importing Subgraphs

    Comfy-Org/workflow_templates

    Imports and registers subgraph blueprints into the ComfyUI workflowtemplates repository.

    1.3k GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Managing Bundles

    Comfy-Org/workflow_templates

    Manages template bundles, categories, and ordering in the ComfyUI template repository.

    1.3k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Managing MCP Index

    Comfy-Org/workflow_templates

    Builds and maintains templates/index.mcp.json for Comfy Cloud MCP tools.

    1.3k GitHub stars~1.9k tokensUpdated today
    Auto-check: notes

  • Managing Releases

    Comfy-Org/workflow_templates

    Manages releases for this repository: how version bumps, PyPI publishing, and GitHub releases work.

    1.3k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Managing Templates

    Comfy-Org/workflow_templates

    Manages ComfyUI workflow templates end-to-end: add new templates and rename existing ones (files, index metadata, bundles, i18n, package sync).

    1.3k GitHub stars~2.8k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Regenerating AI Content

What does Regenerating AI Content do?

Manages AI content generation for the ComfyUI template site. Regenerating AI Content is an agent skill from Comfy-Org/workflow_templates. Manages AI content generation for the ComfyUI template site.

When should I use Regenerating AI Content?

Regenerating AI Content fits situations like: asked to: regenerate content; refresh AI content; fix placeholder text; re-run AI generation.

How do I install Regenerating AI Content in Claude Code?

Run `npx skills add Comfy-Org/workflow_templates --skill regenerating-ai-content -a claude-code`. Or copy the skill folder (.claude/skills/regenerating-ai-content in Comfy-Org/workflow_templates) into .claude/skills/regenerating-ai-content in your project. Claude Code loads it when a task matches its description.

How do I install Regenerating AI Content in Codex?

Run `npx skills add Comfy-Org/workflow_templates --skill regenerating-ai-content -a codex`. Or copy the skill folder (.claude/skills/regenerating-ai-content in Comfy-Org/workflow_templates) into .agents/skills/regenerating-ai-content in your project. Codex loads it when a task matches its description.

Can I use Regenerating AI Content 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 Comfy-Org/workflow_templates --skill regenerating-ai-content -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/regenerating-ai-content, .gemini/skills/regenerating-ai-content, .github/skills/regenerating-ai-content and .opencode/skills/regenerating-ai-content in your project.

What does Regenerating AI Content need to run?

Going by SKILL.md and its folder, Regenerating AI Content needs the command-line tools its instructions call (pnpm) and credentials named OPENAI_API_KEY. Our summary lists: A credential in OPENAI_API_KEY.

Does Regenerating AI Content 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 Regenerating AI Content 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 Regenerating AI Content use?

Regenerating AI Content is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Regenerating AI Content use?

About 922 tokens (SKILL.md is roughly 3.7k 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 Regenerating AI Content?

Skills that share tags, products or a category with Regenerating AI Content: Docs I18n Translate (Comfy-Org/docs, 300 stars), Cms Changelog Sync (Comfy-Org/docs, 300 stars), Comfyui Skill Openclaw (HuangYuChuh/ComfyUI_Skills_OpenClaw, 413 stars) and ComfyUI Custom Node Builder (ConstantineB6/comfy-pilot, 230 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Regenerating AI Content?

Comfy-Org (a GitHub organization) maintains it in Comfy-Org/workflow_templates, which has 1,278 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 10, 2026.

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