DeepTutor CLI
HKUDS/DeepTutor
Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.
Judge an Autoform mathematical roadmap or Lean formalization with explicit, evidence-based rubrics.
Install Agent Review
$ npx skills add facebookresearch/autoform-bot --skill agent-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install facebookresearch/autoform-bot agent-review --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/facebookresearch/autoform-bot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-review .claude/skills/agent-review && 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 "agent-review" agent skill from https://github.com/facebookresearch/autoform-bot/tree/main/skills/agent-review into .claude/skills/agent-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-review", 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/facebookresearch/autoform-bot/tree/main/skills/agent-reviewType 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 facebookresearch/autoform-bot --skill agent-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install facebookresearch/autoform-bot agent-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/facebookresearch/autoform-bot.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/agent-review .agents/skills/agent-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-review" agent skill from https://github.com/facebookresearch/autoform-bot/tree/main/skills/agent-review into .agents/skills/agent-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-review", 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 facebookresearch/autoform-bot --skill agent-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install facebookresearch/autoform-bot agent-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/facebookresearch/autoform-bot.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/agent-review .cursor/skills/agent-review && 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 "agent-review" agent skill from https://github.com/facebookresearch/autoform-bot/tree/main/skills/agent-review into .cursor/skills/agent-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-review", 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/facebookresearch/autoform-bot.git --path skills/agent-review--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 facebookresearch/autoform-bot --skill agent-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install facebookresearch/autoform-bot agent-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/facebookresearch/autoform-bot.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/agent-review .gemini/skills/agent-review && 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 "agent-review" agent skill from https://github.com/facebookresearch/autoform-bot/tree/main/skills/agent-review into .gemini/skills/agent-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-review", 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 facebookresearch/autoform-bot agent-reviewInstalls 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 facebookresearch/autoform-bot --skill agent-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/facebookresearch/autoform-bot.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/agent-review .github/skills/agent-review && 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 "agent-review" agent skill from https://github.com/facebookresearch/autoform-bot/tree/main/skills/agent-review into .github/skills/agent-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-review", 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 facebookresearch/autoform-bot --skill agent-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install facebookresearch/autoform-bot agent-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/facebookresearch/autoform-bot.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/agent-review .opencode/skills/agent-review && 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 "agent-review" agent skill from https://github.com/facebookresearch/autoform-bot/tree/main/skills/agent-review into .opencode/skills/agent-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-review", 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.
Facts
- Skill name
agent-review- GitHub stars
- 117
- Token cost
- ~859 tokens
- SKILL.md length
- 416 words
- Files
- 9 (incl. references)
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT
At a glance
Judge an Autoform mathematical roadmap or Lean formalization with explicit, evidence-based rubrics.
- An independent agent audit of source coverage
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Statement faithfulness
- Proof integrity
What it does
Agent Review is an agent skill from facebookresearch/autoform-bot. Judge an Autoform mathematical roadmap or Lean formalization with explicit, evidence-based rubrics. Use for an independent agent audit of source coverage, DAG quality, statement faithfulness, proof integrity, axioms, sorries, or Mathlib contribution quality; do not use merely to prepare a visualization for a human reviewer.
Its SKILL.md is about 860 tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `agents/openai.yaml`, `references/code-quality.md` and `references/faithfulness.md`).
It sits in Education, covering Quizzes and assessments. The licence is MIT.
When your agent uses it
- An independent agent audit of source coverage
- Statement faithfulness
- Proof integrity
- Mathlib contribution quality
Example prompts
- “/agent-review”
What it can do on your machine
Read from SKILL.md and the folder at commit 89dff27. 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
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.
Network
No URLs in SKILL.md.
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
Agent Review loads about 859 tokens when it runs, and up to ~7.1k if it reads all its reference files. Until then it costs about 85 tokens; SKILL.md has 416 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.
Safety
Auto-check passed
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.
SKILL.md
The full file from facebookresearch/autoform-bot at commit 89dff27, republished under its MIT licence (© facebookresearch). 416 words, ~859 tokens.
Download SKILL.mdSave it as
.claude/skills/agent-review/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.- name
- agent-review
- description
- Judge an Autoform mathematical roadmap or Lean formalization with explicit, evidence-based rubrics. Use for an independent agent audit of source coverage, DAG quality, statement faithfulness, proof integrity, axioms, sorries, or Mathlib contribution quality; do not use merely to prepare a visualization for a human reviewer.
Judge Autoform work as an agent
Select the rubric from the artifact under review.
- For a roadmap or blueprint, read roadmap quality, inspect its declared sources and coverage boundary, and validate the Markdown DAG.
- For Lean code, read faithfulness, proof integrity, code quality, and Mathlib style. Compile the relevant target, inspect the proof chain, and compare the complete public statement with the original source.
- For a read-back, an auditor's English account of what Lean declarations assert, read read-back faithfulness. A trusted coordinator supplies its hash-bound review item. Judge only the supplied testimony against the cited source passage, without opening Lean, and return exactly the reference's JSON verdict.
Keep objective evidence separate from judgment. Never claim compilation, declaration resolution, axiom cleanliness, source coverage, or dependency correctness without showing how it was checked. If required sources are absent, return insufficient evidence rather than guessing. In a project that allows open statements, a proof resting on declared open statements is conditional: name the statements it assumes and never call it axiom-clean.
Except in the isolated read-back-judge role, regenerate skeleton evidence from the exact candidate after its Lean build. Do that only in a trusted checkout or an operating-system sandbox: the command evaluates Lake configuration and project Lean metaprograms, and its resource bounds are not a security boundary. A read-back judge must not regenerate or inspect that evidence; its coordinator does so before dispatch. Treat a stale-build refusal as insufficient evidence; never approve a current source excerpt paired with an older compiled declaration. Record the skeleton hash as a drift checksum for the elaborated declaration and trust context, and the evidence hash for the exact packet that was read. For a source-faithfulness verdict, record the article review hash that binds the joint packet to the cited passage, its locator, and the skeleton hash. These hashes are provenance evidence, not reviewer authentication or an approval key. A read-back verdict also copies its raw read-back hashes as specified by its rubric. Candidate code runs during extraction and can forge process output, so treat its report as advisory when the checkout is not trusted.
Show full SKILL.md (69 more words)Show less
Report findings first, ordered by severity and tied to files or nodes. Then give the rubric scores, weighted verdict, commands run, unresolved questions, and a short remediation list. The read-back rubric's exact JSON output replaces this general report layout. Do not edit the reviewed work unless the user separately asks for fixes.
Use the short Cabannes thesis review case when a concrete Lean example helps distinguish faithfulness from integrity.
© facebookresearch, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 8 other files (references) in skills/agent-review of facebookresearch/autoform-bot.
- SKILL.md
- agents/openai.yaml
- references/code-quality.md
- references/faithfulness.md
- references/mathlib-style.md
- references/proof-integrity.md
- references/readback-faithfulness.md
- references/roadmap-quality.md
- references/thesis-review-case.md
Open the folder on GitHubat commit 89dff27
Compare with similar skills
Agent Review 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 |
|---|---|---|---|---|---|---|
| Agent Review this skillfacebookresearch/autoform-bot | 117 | — | ~859 | Automated safety check: Pass | MIT | |
| DeepTutor CLIHKUDS/DeepTutor | 41k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| AI Engineering Placement Quizrohitg00/ai-engineering-from-scratch | 66k | — | ~2k | Automated safety check: Pass | MIT | |
| Codebase to Coursezarazhangrui/codebase-to-course | 5.7k | — | ~4.4k | Automated safety check: Pass | None | |
| AI Engineering Phase Quizrohitg00/ai-engineering-from-scratch | 66k | — | ~2.1k | Automated safety check: Pass | MIT | |
| Scholar EvaluationK-Dense-AI/claude-scientific-writer | 2.4k | 2 repos | ~2.9k | Automated safety check: Notes | MIT |
Similar skills
AI Engineering Placement Quiz
rohitg00/ai-engineering-from-scratch
Runs a 10-question quiz across five areas to place a learner in the AI Engineering from Scratch curriculum, so they skip what they already know.
Codebase to Course
zarazhangrui/codebase-to-course
Turns a codebase into an interactive single-page HTML course for non-technical learners, with scroll modules, animated diagrams, quizzes and plain-English code translations.
AI Engineering Phase Quiz
rohitg00/ai-engineering-from-scratch
Quizzes you on a completed phase of the AI Engineering from Scratch course, taking a phase number or name and mapping it to that phase's directory.
Scholar Evaluation
K-Dense-AI/claude-scientific-writer
Provide qualitative-first, evidence-traceable developmental review of scholarly works and audit low-stakes research-assessment rubrics with optional local quality controls.
Evaluation
guanyang/open-agent-hub
This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and…
More from facebookresearch/autoform-bot
Setup
facebookresearch/autoform-bot
Set up, inspect, or repair repository infrastructure for an Autoform Lean project, including the Lean/Mathlib shell, an in-repository Obsidian-compatible blueprint vault, ignore rules, MkDocs…
Roadmap
facebookresearch/autoform-bot
Build, continue, inspect, or visualize a source-grounded mathematical roadmap and theorem DAG in an existing Autoform Markdown blueprint.
Develop Plugin
facebookresearch/autoform-bot
Maintain AutoformBot's code, skills, tests, examples, and installation.
Formalize
facebookresearch/autoform-bot
Formalize ready leaves from an existing Autoform Markdown roadmap in Lean, using native agents, fail-closed claims, and verified Markdown progress.
Human Review
facebookresearch/autoform-bot
Prepare and guide human inspection of an Autoform roadmap or formalization through its Obsidian graph and rendered blueprint site.
Related
Categories
Questions about Agent Review
What does Agent Review do?
Judge an Autoform mathematical roadmap or Lean formalization with explicit, evidence-based rubrics. Agent Review is an agent skill from facebookresearch/autoform-bot. Judge an Autoform mathematical roadmap or Lean formalization with explicit, evidence-based rubrics.
When should I use Agent Review?
Agent Review fits situations like: an independent agent audit of source coverage; statement faithfulness; proof integrity; mathlib contribution quality.
How do I install Agent Review in Claude Code?
Run `npx skills add facebookresearch/autoform-bot --skill agent-review -a claude-code`. Or copy the skill folder (skills/agent-review in facebookresearch/autoform-bot) into .claude/skills/agent-review in your project. Claude Code loads it when a task matches its description.
How do I install Agent Review in Codex?
Run `npx skills add facebookresearch/autoform-bot --skill agent-review -a codex`. Or copy the skill folder (skills/agent-review in facebookresearch/autoform-bot) into .agents/skills/agent-review in your project. Codex loads it when a task matches its description.
Can I use Agent Review 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 facebookresearch/autoform-bot --skill agent-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-review, .gemini/skills/agent-review, .github/skills/agent-review and .opencode/skills/agent-review in your project.
What does Agent Review need to run?
SKILL.md names no scripts, command-line tools or credentials: Agent Review is instructions for the agent only.
Does Agent Review access the network?
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.
Is Agent Review safe to install?
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.
What licence does Agent Review use?
Agent Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agent Review use?
About 859 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.3k tokens, read only when the agent opens those files.
What are the alternatives to Agent Review?
Skills that share tags, products or a category with Agent Review: DeepTutor CLI (HKUDS/DeepTutor, 41k stars), AI Engineering Placement Quiz (rohitg00/ai-engineering-from-scratch, 66k stars), Codebase to Course (zarazhangrui/codebase-to-course, 5.7k stars) and AI Engineering Phase Quiz (rohitg00/ai-engineering-from-scratch, 66k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Review?
facebookresearch (a GitHub organization) maintains it in facebookresearch/autoform-bot, which has 117 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 8, 2026.
Source: facebookresearch/autoform-bot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.