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

Nui Workflow

by Nucleify in Nucleify/Nucleify

Shared Nucleify pipeline steps (plan, do, commit, push). An agent skill from Nucleify/Nucleify.

BSD-3-ClauseAuto-check: warnings

Install Nui Workflow

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add Nucleify/Nucleify --skill nui-workflow -a claude-code

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

GitHub CLI
$ gh skill install Nucleify/Nucleify nui-workflow --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/Nucleify/Nucleify.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/nui-workflow .claude/skills/nui-workflow && 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
nui-workflow
GitHub stars
171
Token cost
~833 tokens
SKILL.md length
455 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
BSD-3-Clause

At a glance

Shared Nucleify pipeline steps (plan, do, commit, push). An agent skill from Nucleify/Nucleify.

  • Works in 5 steps: Write a short plan: goal, packages (web… → Persist the plan to .ai/specs/plan.md… → If DO is also in this pipeline: write… → …
  • SKILL.md covers Paths, PLAN, DO and COMMIT, plus 1 more section
  • Calls git and pnpm

What it does

Nui Workflow is an agent skill from Nucleify/Nucleify. Shared Nucleify pipeline steps (plan, do, commit, push). Read when a workflow skill lists these steps.

Its SKILL.md is about 830 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: Build modern web applications powered by modular, nucleus-inspired elements, with override system. The licence is BSD-3-Clause.

Example prompts

  • “/nui-workflow”

Workflow steps

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

  1. Write a short plan: goal, packages (web / admin / docs / compiler / shared_modules), files, risks, out of scope.
  2. Persist the plan to .ai/specs/plan.md when the change is non-trivial (multi-file, API, or architecture). Skip the file for tiny UI polish…
  3. If DO is also in this pipeline: write the plan, then implement immediately. Do not wait for approval unless a project rule says otherwise…
  4. If PLAN is the last step: stop after the plan. Do not edit product code.
  5. Small UI-only (colour, spacing, one class, copy): a 3-line plan is enough.

What it can do on your machine

Read from SKILL.md and the folder at commit 1140bd9. 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:

    • git
    • pnpm

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

  • Network

    No URLs in SKILL.md. Its commands use git and 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 no API keys, tokens, secrets or passwords.

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

Context cost

Nui Workflow loads about 833 tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 455 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~833

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: warnings

The automated check found patterns that need a careful read before installing.

  • WarningTells the agent its actions are pre-authorized / not to stop for confirmationSKILL.md:29
    e the plan, then implement immediately. Do not wait for approval unless a project rule says otherwise (e.g. always-appli
  • NoteMentions a .env fileSKILL.md:56
    2. Stage only this batch. Never stage `.env`, credentials, or secrets.

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 Nucleify/Nucleify at commit 1140bd9, republished under its BSD-3-Clause licence (© Nucleify). 455 words, ~833 tokens.

Download SKILL.mdSave it as .claude/skills/nui-workflow/SKILL.md (or your agent's skills folder).
name
nui-workflow
description
Shared Nucleify pipeline steps (plan, do, commit, push). Read when a workflow skill lists these steps.
disable-model-invocation
true

nui-workflow

Execute only the steps named by the invoking skill, in that order. Then stop.

Work in this conversation. Do not spawn another workflow skill.

Follow .cursor/rules/ and package rules under web|admin|docs|compiler|shared_modules/.config/rules/.

Paths

ArtefactPath
Feature plan.ai/specs/plan.md
Session / change docs.ai/docs/ (markdown)
Product docs sitedocs/ (@nucleify/docs — Astro; do not use for agent notes)

Never write agent notes into docs/markdown/, docs/pdf/, or the Astro content tree unless the user asked to change the product docs site.

PLAN

  1. Write a short plan: goal, packages (web / admin / docs / compiler / shared_modules), files, risks, out of scope.
  2. Persist the plan to .ai/specs/plan.md when the change is non-trivial (multi-file, API, or architecture). Skip the file for tiny UI polish if the pipeline is DO-only.
  3. If DO is also in this pipeline: write the plan, then implement immediately. Do not wait for approval unless a project rule says otherwise (e.g. always-applied workflow awaiting approval for full features).
  4. If PLAN is the last step: stop after the plan. Do not edit product code.
  5. Small UI-only (colour, spacing, one class, copy): a 3-line plan is enough.

DO

  1. Implement the user request (against the plan when PLAN ran).
  2. Prefer existing patterns: shared_modules/nuc_*, nui-*, compiler emit/convert. No parallel app trees.
  3. Always update agent documentation before this step ends:
    • Write or extend files under .ai/docs/ (what changed, why, how to verify).
    • Create new files when a domain or area is new; edit existing ones when they would be stale.
    • Prefer dated or topic slugs, e.g. .ai/docs/home-holo-cube-glow.md, .ai/docs/2026-09-19-rainbow.md.
  4. After code edits run from repo root:
sh
pnpm -s check && pnpm -s typeslint && pnpm -s slint && pnpm -s tests

Fix failures and re-run until green. Skip the suite only for pure docs/rules/markdown — say so. 5. Do not commit unless COMMIT is in this pipeline. 6. Do not push unless PUSH is in this pipeline.

Show full SKILL.md (157 more words)Show less

COMMIT

The user invoked commit — create the commit (include .ai/docs/ updates from DO when present).

  1. Run in parallel: git status, git diff, git diff --cached, git log -8 --oneline.
  2. Stage only this batch. Never stage .env, credentials, or secrets.
  3. Message via HEREDOC, 1–2 sentences on why. Repo style: feat: / fix: / chore: / docs: (optionally scoped, e.g. fix(web): …).
  4. No --no-verify, no force, no amend unless the user asked and amend rules pass.
  5. Failed hook: fix and make a new commit. Do not amend.
  6. If there is nothing to commit, say so and skip.
  7. End with git status.

PUSH

The user invoked push — publish the current branch.

  1. Never push --force to main, master, or prod. Never --no-verify.
  2. If no upstream: git push -u origin HEAD. Else git push.
  3. Do not push if the working tree still has an incomplete COMMIT step.
  4. Report branch, remote, and whether the push succeeded.

© Nucleify, BSD-3-Clause. 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 .cursor/skills/nui-workflow of Nucleify/Nucleify.

Open the folder on GitHubat commit 1140bd9

Compare with similar skills

Nui Workflow 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.

Nui Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nui Workflow this skillNucleify/Nucleify171—~833Automated safety check: WarnBSD-3-Clause
Commit, Push, and PREveryInc/compound-engineering-plugin25k—~2kAutomated safety check: PassMIT
Commitsickn33/agentic-awesome-skills47k2 repos~1.3kAutomated safety check: PassMIT
Git Commit Pushfarm-fe/farm5.6k—~325Automated safety check: PassMIT
Commitdavila7/claude-code-templates32k3 repos~730Automated safety check: PassMIT
Commitwindmill-labs/windmill18k—~447Automated safety check: PassCustom licence

Similar skills

  • Commit, Push, and PR

    EveryInc/compound-engineering-plugin

    Commits staged changes, pushes a branch, and opens or updates a GitHub pull request, including writing its description.

    25k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed

  • Commit

    sickn33/agentic-awesome-skills

    ALWAYS use this skill when committing code changes — never commit directly without it.

    47k GitHub starsUsed in 2 repos~1.3k tokens
    DevelopmentAuto-check passed

  • Git Commit Push

    farm-fe/farm

    Commit and push repository changes safely. An agent skill from farm-fe/farm.

    5.6k GitHub stars~325 tokensUpdated 16 days ago
    DevelopmentAuto-check passed

  • Commit

    davila7/claude-code-templates

    Create commit messages following Sentry conventions. An agent skill from davila7/claude-code-templates.

    32k GitHub starsUsed in 3 repos~730 tokens
    DevelopmentAuto-check passed

  • Commit

    windmill-labs/windmill

    Create a git commit with conventional commit format. An agent skill from windmill-labs/windmill.

    18k GitHub stars~447 tokensUpdated today
    DevelopmentAuto-check passed

  • Commit

    ccusage/ccusage

    Creates atomic Conventional Commits. An agent skill from ccusage/ccusage.

    19k GitHub stars~722 tokensUpdated today
    DevelopmentAuto-check passed

More from Nucleify/Nucleify

  • Do Commit Push

    Nucleify/Nucleify

    Nucleify pipeline DO → COMMIT → PUSH: implement; update .ai/docs/; commit; push.

    171 GitHub stars~129 tokensUpdated 15 days ago
    Auto-check passed

Questions about Nui Workflow

What does Nui Workflow do?

Shared Nucleify pipeline steps (plan, do, commit, push). An agent skill from Nucleify/Nucleify. Nui Workflow is an agent skill from Nucleify/Nucleify. Shared Nucleify pipeline steps (plan, do, commit, push).

How do I install Nui Workflow in Claude Code?

Run `npx skills add Nucleify/Nucleify --skill nui-workflow -a claude-code`. Or copy the skill folder (.cursor/skills/nui-workflow in Nucleify/Nucleify) into .claude/skills/nui-workflow in your project. Claude Code loads it when a task matches its description.

How do I install Nui Workflow in Codex?

Run `npx skills add Nucleify/Nucleify --skill nui-workflow -a codex`. Or copy the skill folder (.cursor/skills/nui-workflow in Nucleify/Nucleify) into .agents/skills/nui-workflow in your project. Codex loads it when a task matches its description.

Can I use Nui Workflow 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 Nucleify/Nucleify --skill nui-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nui-workflow, .gemini/skills/nui-workflow, .github/skills/nui-workflow and .opencode/skills/nui-workflow in your project.

What does Nui Workflow need to run?

Going by SKILL.md and its folder, Nui Workflow needs the command-line tools its instructions call (git and pnpm).

Does Nui Workflow access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Nui Workflow safe to install?

Our automated static check of SKILL.md flagged 1 warning(s): tells the agent its actions are pre-authorized / not to stop for confirmation. Read the flagged lines before installing; the check is not a guarantee either way.

What licence does Nui Workflow use?

Nui Workflow is published under the BSD-3-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Nui Workflow use?

About 833 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.

What are the alternatives to Nui Workflow?

Skills that share tags, products or a category with Nui Workflow: Commit, Push, and PR (EveryInc/compound-engineering-plugin, 25k stars), Commit (sickn33/agentic-awesome-skills, 47k stars), Git Commit Push (farm-fe/farm, 5.6k stars) and Commit (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nui Workflow?

Nucleify (a GitHub organization) maintains it in Nucleify/Nucleify, which has 171 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 22, 2026.

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