agentleFS
mlk010173mlk010173/sitejack/skill/SKILL.md

skill

Skill1 starsChanged 25 days agoMITView on GitHub

You now know how to clone any website's public interface, byte-faithfully, and deploy it as a live copy on GitHub Pages. Follow this file exactly. Single-file CLI at skill/sitejack.py (Python 3.8+ stdlib only). Run with python3 skill/sitejack.py <command>. When a user says "clone this site and put it online":

  • Reads credentials

66 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ai-slop-cleaner, ralplan and 10 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.
  • Jurel89Skill

    ai-slop-cleaner

    Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

    Also in 5 projects that use this

  • ibahgatSkill

    ralplan

    Create a strict, quality-first execution plan with explicit gates and rollback-ready sequencing.

    Also in 5 projects that use this

  • ibahgatSkill

    hud

    Control omi visual HUD profile and keep status output readable in normal, compact, or hidden mode.

    Also in 5 projects that use this

  • Jurel89Skill

    ultraqa

    QA cycling loop — build/lint/test, fix, retry up to 5 cycles

    Also in 3 projects that use this

  • LucasCooperBeySkill

    visual-verdict

    Structured visual QA verdict for screenshot-to-reference comparisons. Returns JSON scores driving edit iterations. Use after any UI implementation to verify visual fidelity.

    Also in 3 projects that use this

  • Yeachan-HeoSkill

    ultragoal

    Create and execute durable repo-native multi-goal plans over Codex goal mode artifacts.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 48 edited versions we read keep these.

  • 4

    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. Distinctive:

    When a user says "clone this site and put it online":

    line 22
  2. Distinctive:

    Never try to clone authenticated content, paid content, or anything behind a login.

    line 33
  3. Distinctive:

    Never print a secret the scan finds — it prints masked.

    line 34
  4. Very specific:

    Never claim byte-fidelity without running verify.

    line 35
  5. Distinctive:

    If the user seems to want to impersonate someone's brand/site, ask what the clone is for and suggest legal alternatives (backup, study, …

    line 37

“Common” is measured: kept by at least 6 in 10 of the 48 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

sitejack — agent skill

You now know how to clone any website's public interface, byte-faithfully, and deploy it as a live copy on GitHub Pages. Follow this file exactly.

Tool

Single-file CLI at skill/sitejack.py (Python 3.8+ stdlib only). Run with python3 skill/sitejack.py <command>.

Command contract

commanduse it whenon failure
recon <url>the user names a site they want studied or clonedreport the HTTP status honestly; do not guess the stack
clone <url>the user wants the interface copied; mirror lands in ./<host>-clone/ with manifest.jsona partial report in the manifest is normal for huge sites — say how deep it went
clone <url> --waybackthe site is down or returns errorswayback mirrors are best-effort; say so
scan <dir>ALWAYS between clone and deploy — non-negotiableif it exits with code 2, STOP: there are secrets. Show the masked findings, propose removal, never deploy
deploy <dir> <repo>the user asks to publish; requires GITHUB_TOKEN env (repo scope)if Pages build hasn't finished, say it is building — never claim live without HTTP 200
verify <dir> <url>the user doubts the copy, or before claiming "perfect clone"exit code 2 means hash mismatch — report exactly which files

The canonical run

When a user says "clone this site and put it online":

  1. recon <url> — tell them the stack, fonts, palette, and roughly how many assets.
  2. clone <url>.
  3. scan the clone dir. If secrets: STOP and report.
  4. deploy <dir> <repo-name> — picks a repo name close to the brand; asks the user only if the name matters.
  5. Report the live URL and the repo URL. Offer verify as proof.

Guardrails (hard rules)

  • Public frontends only. https-only. Private/internal hosts are blocked by the tool — never work around it.
  • Never try to clone authenticated content, paid content, or anything behind a login.
  • Never print a secret the scan finds — it prints masked; keep it masked in your replies.
  • Never claim byte-fidelity without running verify.
  • Clones are static: API calls still point to the original domain. Say this when the user expects functionality, not just the interface.
  • If the user seems to want to impersonate someone's brand/site, ask what the clone is for and suggest legal alternatives (backup, study, redesign, demo).

Reading the outputs

  • manifest.json — every saved file with size and SHA-1; skipped explains every absence; partial: true means the cap hit before the graph closed.
  • scan output — file, secret family (Mapbox, OpenAI…), masked fragment. This mirrors what GitHub Push Protection blocks, so a clean scan ≈ a push that goes through.
  • deploy — prints LIVE: <url> only after an HTTP 200 check on the Pages URL.

Known gotchas the tool already handles (don't reintroduce them)

  • GitHub Pages runs Jekyll, which silently ignores folders starting with _ (like SvelteKit's _app or Next's _next) — deploy writes .nojekyll for you.
  • Routes without extensions (/pricing) must land in pricing/index.html, or they 404 on Pages.
  • Absolute URLs in the source must stay absolute (they point at the original); only same-origin paths become clone files.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.