siege SKILL.md skillA

siege from anthropics/claude-plugins-official is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add anthropics/claude-plugins-official/siege@git:20260930.aa5654b

Pins git:20260930.aa5654b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
anthropics/claude-plugins-official
Path
plugins/math-proof/skills/siege/SKILL.md
Versions recorded
1
Latest version
git:20260930.aa5654b, committed Sep 30, 2026
Size
75,513 bytes
Repository stars
43,118
License
Apache-2.0

Work on one hard mathematics problem in rounds: each round a judge writes a few self-contained questions, independent workers answer them, and the judge keeps a ledger of what is proved, refuted and open, until the judge concludes or the rounds run out, and then a proof.md says plainly what is and is not proved. A run takes hours and dozens of worker runs. Usage: /math-proof:siege [NAME=value settings] <the problem, stated in full, or the path of a file holding it>.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# math-proof: siege

## The approach
The skill works on one problem in at most MAX_ROUNDS rounds. Each round a judge writes a few self-contained
questions, at most WAVE of them before round ESC_ROUND. The steps below call them queries. Each question goes
to a fresh worker that sees only that question and the problem statement. The judge reads the answers,
rewrites the running summary, and adds to a ledger of claims marked PROVED, REFUTED or OPEN. One claim is the
goal, set in round 1; the judge may set a new goal at a later round, and in particular may raise it to a more
significant statement once it is proved (the proved goal then stays in the ledger as the fallback result, to
which the judge returns if two waves bring the raised goal no nearer; when the goal is raised you tell the user and
copy the proved result to DIR/result-so-far.md). When an answer holds a complete written proof or disproof of the goal, two more workers check that exact text
line by line. Once both pass, the judge concludes or raises the goal. Before round MIN_ROUNDS, that is the only
way to conclude. From round ESC_ROUND on, if no complete proof or disproof is in hand, a round may
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add anthropics/claude-plugins-official/siege@sha256:f40134d3b418b256

The line at the top of this page pins the label git:20260930.aa5654b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_yksx22dt5uaa5s6b.svg)](https://markdownregistry.com/a/art_yksx22dt5uaa5s6b)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 30, 2026.

versioncommittedcommitsizeaudit
git:20260930.aa5654b latest2026-09-30 aa5654b 75,513 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (75513 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

anthropics/claude-plugins-official · 43,118 stars · license Apache-2.0 · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_yksx22dt5uaa5s6b
GET https://markdownregistry.com/api/v1/resolve?ref=anthropics/claude-plugins-official/siege
GET https://markdownregistry.com/api/v1/blob/f40134d3b418b256656777ad89d1cee93ad9b8a8a1aa84754262752e91d6b542

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from anthropics/claude-plugins-official

access SKILL.md skill
anthropics/claude-plugins-official · external_plugins/discord/skills/access/SKILL.md · Manage Discord channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to pair…
git:20260318.4796148 · audit A · 43,118 stars
configure SKILL.md skill
anthropics/claude-plugins-official · external_plugins/discord/skills/configure/SKILL.md · Set up the Discord channel — save the bot token and review access policy. Use when the user pastes a Discord bot token…
git:20260320.8140fba · audit B · 43,118 stars
access SKILL.md skill
anthropics/claude-plugins-official · external_plugins/imessage/skills/access/SKILL.md · Manage iMessage channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to…
git:20260318.1c95fc6 · audit A · 43,118 stars
configure SKILL.md skill
anthropics/claude-plugins-official · external_plugins/imessage/skills/configure/SKILL.md · Check iMessage channel setup and review access policy. Use when the user asks to configure iMessage, asks "how do I set…
git:20260318.1c95fc6 · audit A · 43,118 stars
access SKILL.md skill
anthropics/claude-plugins-official · external_plugins/telegram/skills/access/SKILL.md · Manage Telegram channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to…
git:20260813.1e96c6b · audit A · 43,118 stars
configure SKILL.md skill
anthropics/claude-plugins-official · external_plugins/telegram/skills/configure/SKILL.md · Set up the Telegram channel — save the bot token and review access policy. Use when the user pastes a Telegram bot…
git:20260813.1e96c6b · audit B · 43,118 stars
claude-automation-recommender SKILL.md skill
anthropics/claude-plugins-official · plugins/claude-code-setup/skills/claude-automation-recommender/SKILL.md · Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when…
git:20260528.fc49e68 · audit A · 43,118 stars
claude-md-improver SKILL.md skill
anthropics/claude-plugins-official · plugins/claude-md-management/skills/claude-md-improver/SKILL.md · Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix…
git:20260116.a86e346 · audit A · 43,118 stars
claude-security SKILL.md skill
anthropics/claude-plugins-official · plugins/claude-security/skills/claude-security/SKILL.md · Claude Security: scan the codebase (the whole repository or a scoped part of it), scan changes (this branch's or a pull…
git:20260925.ca08d5e · audit A · 43,118 stars
cardputer-buddy SKILL.md skill
anthropics/claude-plugins-official · plugins/cwc-makers/skills/cardputer-buddy/SKILL.md · Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already…
git:20260506.574a879 · audit A · 43,118 stars
m5-onboard SKILL.md skill
anthropics/claude-plugins-official · plugins/cwc-makers/skills/m5-onboard/SKILL.md · End-to-end onboarding for a freshly-plugged-in M5Stack ESP32 device (Cardputer, Cardputer-Adv, Core, CoreS3, Stick) —…
git:20260506.06f52cd · audit A · 43,118 stars
example-command SKILL.md skill
anthropics/claude-plugins-official · plugins/example-plugin/skills/example-command/SKILL.md · An example user-invoked skill that demonstrates frontmatter options and the skills/<name>/SKILL.md layout
git:20260317.6b70f99 · audit A · 43,118 stars

Every file in anthropics/claude-plugins-official

Other files named siege

siege SKILL.md skill
simota/agent-skills · siege/SKILL.md · Verifying system resilience via load testing, contract testing, chaos engineering, and mutation testing. Use for limit…
git:20261012.27f6d8a · audit A · 93 stars

Browse by kind, by grade A, or by owner.