agentleFS
Sign inStart free
durchnulldurchnull/render/skills/new/SKILL.md

new

Skill0 starsChanged 3 months agoMITView on GitHub

Add a page to the project's .render/ — a section page under pages/ (dashboard, report, checklist), a data-driven kind page that renders one output per data file, or a standalone page_api script when the page must live outside the config. Use when the project needs another HTML page.

20 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use upgrade, gate and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • agenticnotetakingSkill

    upgrade

    Apply plugin knowledge base updates to an existing generated system. Consults the Ars Contexta research graph for methodology improvements, proposes skill upgrades with research justification. Never auto-implements. Triggers on "/upgrade", "upgrade skills", "check for improvements", "update methodology".

    Also in 4 projects that use this

  • synaptiaiSkill

    gate

    Create a BDSK review_gate artifact. Defines a checkpoint that controls whether generated output may proceed toward acceptance. Use when defining quality, security, or scope gates for execution plans.

    Also in 3 projects that use this

  • kt057Skill

    check

    lint, typecheck, test を一括実行して結果をサマリーする

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 5 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If .render/ does not exist yet, run /render:init first.

    line 15

“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Add a page on the render engine

The project needs another self-contained HTML page. Pages are the unit the engine thinks in: a project declares any number, each designed by the project itself. The plugin brings the shell, the fragment cache, the design system and the checks; the page brings its content — and what earns a place in that content is a decision, made before markup (design-manual.md 5.1; the section-page file opens with the content-budget step).

If .render/ does not exist yet, run /render:init first.

Which of the three

The page is…Use
one output, content the project assembles from files and its own codea section page — the default
one output per data file, all built the same way from a spec (a questionnaire per topic, a report per client, a checklist per year)a kind page
output that must land outside the config directory, or that other tooling generates on its own schedulea standalone script

Reach for a section page unless one of the other two clearly fits. The standalone script is genuinely last: it is the only one the hook does not keep fresh, and the only one the index page cannot list.

Pick the branch, scaffold it, then read only that branch's file — it carries the contract and the steps:

  • Section page — read ${CLAUDE_PLUGIN_ROOT}/skills/new/section-page.md, then:
    python3 "${CLAUDE_PLUGIN_ROOT}/engine/scaffold.py" --new-page <id> --section <sid> --section <sid> --title "…"
  • Kind page — read ${CLAUDE_PLUGIN_ROOT}/skills/new/kind-page.md, then:
    python3 "${CLAUDE_PLUGIN_ROOT}/engine/scaffold.py" --new-page <id> --kind <kind> --sources '<glob>' --title "…"
  • Standalone script — read ${CLAUDE_PLUGIN_ROOT}/skills/new/standalone.md, then:
    python3 "${CLAUDE_PLUGIN_ROOT}/engine/scaffold.py" --standalone <name> --title "…"

The scaffold writes starter content only — everything it emits is the project's from the first byte and is never refreshed or overwritten.

Never

  • Never copy or modify engine code — the engine is imported from the installation; a copy forks silently and never receives another update.
  • Never touch the plugin's installation directory — it is read-only for consumers and the next sync would discard any change.
  • No custom hex values and no CSS that bypasses the design system — colors, typography, spacing and components come exclusively from the tokens. Page-specific CSS goes into the page's EXTRA_CSS (declared pages) or page_shell(extra_css=…) (standalone scripts) and uses tokens only (var(--s4), var(--ink-2), …). Interactive pages pull in FORM_CSS / APP_CSS there — they are opt-in so a dashboard never carries form styling it has no use for.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free