Proof Run Orchestrator
wanshuiyin/Auto-claude-code-research-in-sleep
Runs a mathematical proof project as a stateful pipeline of run directories: a local attempt first, then a manual GPT Pro handoff package, with an optional DeepSeek audit.
Solves one hard mathematics problem in a single session without subagents, keeping settled steps in a notes file and ending with a self-contained proof.md.
$ npx skills add anthropics/claude-plugins-official --skill solo -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install anthropics/claude-plugins-official solo --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/anthropics/claude-plugins-official.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/math-proof/skills/solo .claude/skills/solo && rm -rf skills-srcUse ~/.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/
Install the "solo" agent skill from https://github.com/anthropics/claude-plugins-official/tree/main/plugins/math-proof/skills/solo into .claude/skills/solo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "solo", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/anthropics/claude-plugins-official/tree/main/plugins/math-proof/skills/soloType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add anthropics/claude-plugins-official --skill solo -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install anthropics/claude-plugins-official solo --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-plugins-official.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/math-proof/skills/solo .agents/skills/solo && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "solo" agent skill from https://github.com/anthropics/claude-plugins-official/tree/main/plugins/math-proof/skills/solo into .agents/skills/solo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "solo", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add anthropics/claude-plugins-official --skill solo -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install anthropics/claude-plugins-official solo --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-plugins-official.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/math-proof/skills/solo .cursor/skills/solo && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "solo" agent skill from https://github.com/anthropics/claude-plugins-official/tree/main/plugins/math-proof/skills/solo into .cursor/skills/solo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "solo", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/anthropics/claude-plugins-official.git --path plugins/math-proof/skills/solo--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add anthropics/claude-plugins-official --skill solo -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install anthropics/claude-plugins-official solo --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-plugins-official.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/math-proof/skills/solo .gemini/skills/solo && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "solo" agent skill from https://github.com/anthropics/claude-plugins-official/tree/main/plugins/math-proof/skills/solo into .gemini/skills/solo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "solo", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install anthropics/claude-plugins-official soloInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add anthropics/claude-plugins-official --skill solo -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/anthropics/claude-plugins-official.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/math-proof/skills/solo .github/skills/solo && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "solo" agent skill from https://github.com/anthropics/claude-plugins-official/tree/main/plugins/math-proof/skills/solo into .github/skills/solo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "solo", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add anthropics/claude-plugins-official --skill solo -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install anthropics/claude-plugins-official solo --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-plugins-official.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/math-proof/skills/solo .opencode/skills/solo && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "solo" agent skill from https://github.com/anthropics/claude-plugins-official/tree/main/plugins/math-proof/skills/solo into .opencode/skills/solo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "solo", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
soloSolves one hard mathematics problem in a single session without subagents, keeping settled steps in a notes file and ending with a self-contained proof.md.
You give the skill a problem as text or as the path to a file, optionally with a DIR=path prefix to choose the run directory, which otherwise defaults to ./math-proof-solo. The agent keeps the problem in problem.md, reasons in stages, and records each settled step in notes.md so nothing is lost if a response is cut off.
The deliverable is proof.md, written to stand on its own. If notes.md already exists in the directory, the agent first compares problem.md with the problem it was given. Settings such as rounds and waves belong to a separate /math-proof:siege command, and the allowed tools are file reading and writing plus mkdir, cp and cmp.
Read from SKILL.md and the folder at commit 315c4e4. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditGlobGrepBash(mkdir *)Bash(cp *)Bash(cmp *)From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Math Proof Solo loads about 1.5k tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 942 words of instructions outside code blocks.
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.
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.
The full file from anthropics/claude-plugins-official at commit 315c4e4, republished under its Apache-2.0 licence (© anthropics). 942 words, ~1,545 tokens.
.claude/skills/solo/SKILL.md (or your agent's skills folder).You solve the problem yourself, in this session. There are no sub-agents and no rounds: just you, a notes file and, at the end, proof.md.
Arguments. The invoking message reads: $ARGUMENTS
It gives the problem and, optionally, the run directory. Read it this way. A token of the form DIR=path at its
start sets the run directory (the path quoted if it contains spaces); remove it. Any other leading token of the
form NAME=value, where NAME is a word of two or more capital letters and underscores and value is a whole number,
is a setting this skill does not have: tell the user in one sentence that /math-proof:solo takes only DIR=path
before the problem (round and wave settings belong to /math-proof:siege), and that if the token is part of the
problem itself the problem can be given as a file path instead, and stop. If what remains is a single line
that, taken as a whole — surrounding whitespace and one pair of enclosing quotation marks removed,
backslash-escaped spaces read as spaces — is the path of an existing file (it may contain spaces; check with
Read or Glob, not the shell), that file is the problem file; if no such file exists and what remains can only
be a file path — a single line ending in .md, .txt or .tex, or a single token (no spaces once the quotes are
removed) containing "/" or "" — tell the user in one sentence that no file exists at the absolute path you
looked for (give it) and that the problem can instead be given in full as text after the command, and stop;
otherwise everything that remains, to the end of the message, IS the problem statement, verbatim — mathematics,
line breaks and all ("n=3", "N=pq" and "AB=AC" are mathematics, not settings). The run directory DIR defaults to
./math-proof-solo under the current directory; use DIR's absolute path everywhere below. If the message holds
neither a readable problem file nor any problem text, say so in one sentence — with the usage,
/math-proof:solo <problem statement, or the path of a file holding it> — and stop.
Setup. The run's files are DIR/problem.md (the problem), DIR/notes.md (your notes) and DIR/proof.md (the
deliverable). Create DIR with mkdir -p. If DIR/notes.md already exists, this problem was already being
worked on in DIR: check that DIR/problem.md is the same problem you were given (compare the text, ignoring
differences in whitespace and line endings; for a file, cmp) — if it differs, say in one sentence that DIR
holds work on a different problem and that DIR=<another directory> selects a fresh one, and stop; if it is
the same, read DIR/notes.md, and DIR/proof.md if it exists. If they record the solution as complete (proof.md
written and nothing in the notes still to do), the earlier session finished: say where proof.md is and that
DIR=<another directory> starts a fresh attempt, and stop. Otherwise the earlier session ended before it
finished, and whatever reasoning it had not written down is lost: continue from the last point recorded there
rather than starting over. If DIR/notes.md does not exist yet, put the problem at DIR/problem.md: if it came as
a file, copy that file there byte for byte with cp; if it came as text in the invoking message, Write
exactly that text (nothing added, removed or reworded). Then Read DIR/problem.md in full; it is the authoritative text of the problem. Use the shell for
nothing but that mkdir, cp and cmp.
The task. Solve the problem stated in DIR/problem.md; the deliverable is DIR/proof.md. After reasoning, write your answer. This task runs as a conversation that can span many messages, each with a bounded output allowance; a message that is cut off is normally followed by a request to continue, and only what you have WRITTEN (not unwritten reasoning) is guaranteed to carry into the next message. So write your work product out as you go, in a notes file, DIR/notes.md: whenever you settle something — a lemma and its proof, a reduction, a dead end and why it is dead, the precise statement you are now attempting — write it down before reasoning further. A partial answer is much more useful than none. Writing to the notes is not finishing — keep going after each write. Important: each message's output allowance also covers your private reasoning, and it is far smaller than a hard problem deserves — a message spent entirely on reasoning, with nothing written, gets cut off, and unwritten reasoning should be assumed lost. So do not try to finish in one message. Work in stages: early in EVERY message, before any long derivation, write your current plan and the precise statement you are attempting to DIR/notes.md; then reason toward the next concrete intermediate result, append it to the notes as soon as you have it, and continue. Many short written steps beat one long unwritten one. If a message of yours is cut off, re-read DIR/notes.md and continue from the last thing written there; never start over. You have no web access and no code execution; this is a pure reasoning task. When the problem is resolved, or you have taken it as far as you can, write your complete solution to DIR/proof.md. proof.md is read on its own by a referee who cannot open any other file (not your notes either), so it must be self-contained: every argument the solution relies on is written out in full there. Work unattended: there is no one to answer questions, so never stop to ask.
When DIR/proof.md is written, reply briefly: where proof.md is, and whether it resolves the problem completely or, in proof.md's own words, what it leaves open.
© anthropics, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in plugins/math-proof/skills/solo of anthropics/claude-plugins-official.
Open the folder on GitHubat commit 315c4e4
Math Proof Solo 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Math Proof Solo this skillanthropics/claude-plugins-official | 38k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Proof Run Orchestratorwanshuiyin/Auto-claude-code-research-in-sleep | 17k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| Recent Conjecture Evaluationsmorluto/jacobian | 211 | — | ~816 | Automated safety check: Pass | MIT | |
| Harbor Benchmarksmorluto/jacobian | 211 | — | ~690 | Automated safety check: Pass | MIT | |
| Audit Public Operation Contractsmorluto/jacobian | 211 | — | ~2k | Automated safety check: Pass | MIT | |
| Learn From Math Agent Trajectoriesmorluto/jacobian | 211 | — | ~848 | Automated safety check: Pass | MIT |
wanshuiyin/Auto-claude-code-research-in-sleep
Runs a mathematical proof project as a stateful pipeline of run directories: a local attempt first, then a manual GPT Pro handoff package, with an optional DeepSeek audit.
morluto/jacobian
Evaluate Jacobian reliability using recently resolved conjectures as held-out probes.
morluto/jacobian
Author, package, validate, or run mathematical evaluations as Jacobian Harbor datasets.
morluto/jacobian
Design or audit a Jacobian operation’s mathematical contract, boundedness, exact results, and composition.
morluto/jacobian
Review mathematical agent trajectories for evidence-backed Jacobian improvements; do not resume solving.
morluto/jacobian
Design, audit, or repair mathematical benchmark verifiers, submission contracts, and scoring.
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
anthropics/claude-plugins-official
Shows how Claude Code plugins keep per-project settings and state in .claude/plugin-name.local.md files with YAML frontmatter and a markdown body.
anthropics/claude-plugins-official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
anthropics/claude-plugins-official
Explains how to write Claude Code slash commands: Markdown files with YAML frontmatter, arguments, file references, bash context and interactive prompts.
anthropics/claude-plugins-official
Explains the directory layout, plugin.json manifest and component organization of a Claude Code plugin, including auto-discovery and portable paths.
Categories
Solves one hard mathematics problem in a single session without subagents, keeping settled steps in a notes file and ending with a self-contained proof.md. /math-proof-solo.md so nothing is lost if a response is cut off.
Math Proof Solo fits situations like: working through a hard proof with one agent doing all the reasoning; keeping a written trail of settled steps so a cut-off response loses nothing; producing a self-contained proof document for a stated problem.
Run `npx skills add anthropics/claude-plugins-official --skill solo -a claude-code`. Or copy the skill folder (plugins/math-proof/skills/solo in anthropics/claude-plugins-official) into .claude/skills/solo in your project. Claude Code loads it when a task matches its description.
Run `npx skills add anthropics/claude-plugins-official --skill solo -a codex`. Or copy the skill folder (plugins/math-proof/skills/solo in anthropics/claude-plugins-official) into .agents/skills/solo in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add anthropics/claude-plugins-official --skill solo -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/solo, .gemini/skills/solo, .github/skills/solo and .opencode/skills/solo in your project.
SKILL.md names no scripts, command-line tools or credentials: Math Proof Solo is instructions for the agent only. Our summary lists: A writable directory for problem.md, notes.md and proof.md. Its frontmatter pre-approves these tools: Read, Write, Edit, Glob, Grep, Bash(mkdir *), Bash(cp *), Bash(cmp *).
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.
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.
Math Proof Solo is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.5k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Math Proof Solo: Proof Run Orchestrator (wanshuiyin/Auto-claude-code-research-in-sleep, 17k stars), Recent Conjecture Evaluations (morluto/jacobian, 211 stars), Harbor Benchmarks (morluto/jacobian, 211 stars) and Audit Public Operation Contracts (morluto/jacobian, 211 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
anthropics (a GitHub organization, an official publisher) maintains it in anthropics/claude-plugins-official, which has 37,566 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 8, 2026.
Source: anthropics/claude-plugins-official on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.