Personal Assistant Review
edonyzpc/personal-assistant
Review uncommitted or PR diffs in the personal-assistant Obsidian plugin with project-specific risk lanes, second-layer future-risk checks, severity discipline, subagent review routing, and…
Prepare and guide human inspection of an Autoform roadmap or formalization through its Obsidian graph and rendered blueprint site.
Install Human Review
$ npx skills add facebookresearch/autoform-bot --skill human-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install facebookresearch/autoform-bot human-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/human-review .claude/skills/human-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 "human-review" agent skill from https://github.com/facebookresearch/autoform-bot/tree/main/skills/human-review into .claude/skills/human-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "human-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/human-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 human-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install facebookresearch/autoform-bot human-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/human-review .agents/skills/human-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 "human-review" agent skill from https://github.com/facebookresearch/autoform-bot/tree/main/skills/human-review into .agents/skills/human-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "human-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 human-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install facebookresearch/autoform-bot human-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/human-review .cursor/skills/human-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 "human-review" agent skill from https://github.com/facebookresearch/autoform-bot/tree/main/skills/human-review into .cursor/skills/human-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "human-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/human-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 human-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install facebookresearch/autoform-bot human-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/human-review .gemini/skills/human-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 "human-review" agent skill from https://github.com/facebookresearch/autoform-bot/tree/main/skills/human-review into .gemini/skills/human-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "human-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 human-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 human-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/human-review .github/skills/human-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 "human-review" agent skill from https://github.com/facebookresearch/autoform-bot/tree/main/skills/human-review into .github/skills/human-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "human-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 human-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 human-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/human-review .opencode/skills/human-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 "human-review" agent skill from https://github.com/facebookresearch/autoform-bot/tree/main/skills/human-review into .opencode/skills/human-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "human-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
human-review- GitHub stars
- 117
- Token cost
- ~856 tokens
- SKILL.md length
- 423 words
- Files
- 2
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT
At a glance
Prepare and guide human inspection of an Autoform roadmap or formalization through its Obsidian graph and rendered blueprint site.
- A person wants to browse
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Lean artifacts visually
- Do not substitute an autonomous agent verdict for the humans judgment
What it does
Human Review is an agent skill from facebookresearch/autoform-bot. Prepare and guide human inspection of an Autoform roadmap or formalization through its Obsidian graph and rendered blueprint site. Use when a person wants to browse, approve, reject, or discuss scope, dependencies, progress, source links, or Lean artifacts visually; do not substitute an autonomous agent verdict for the human's judgment.
Its SKILL.md is about 860 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Product & Project Management, covering Autonomous loops. It works with Obsidian. The licence is MIT.
When your agent uses it
- A person wants to browse
- Lean artifacts visually
- Do not substitute an autonomous agent verdict for the humans judgment
Example prompts
- “/human-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
Human Review loads about 856 tokens when it runs. Until then it costs about 88 tokens; SKILL.md has 423 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). 423 words, ~856 tokens.
Download SKILL.mdSave it as
.claude/skills/human-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- human-review
- description
- Prepare and guide human inspection of an Autoform roadmap or formalization through its Obsidian graph and rendered blueprint site. Use when a person wants to browse, approve, reject, or discuss scope, dependencies, progress, source links, or Lean artifacts visually; do not substitute an autonomous agent verdict for the human's judgment.
Prepare a human review
Inspect the repository without changing mathematical content. Require an existing Autoform vault and site configuration; hand missing infrastructure to Setup. Keep the Markdown vault as the source of truth and regenerate only derived review views.
Regenerate the review views from <PROJECT>: validate the blueprint, refresh
the Mermaid graph with autoform-visualize so Obsidian shows current
dependencies, render the site source, then strict-build the site. Follow the
publication sequence in the CLI reference,
but omit --require-declarations: review happens while statements are still
unformalized, and a missing declaration is something for the reviewer to see
rather than a reason to refuse to render.
Stop on structural failures and present them before asking for mathematical
judgment. For vault review, point the user to blueprint/README.md, coverage,
chapter pages, and blueprint/dependencies.md in Obsidian. For browser review,
run autoform dashboard <PROJECT> --site-dir site so the same site deployed to
GitHub Pages is served on loopback with local-only live claim badges. Provide
the overview, including its progress summary, plus the project graph, relevant
chapter graph, and node-neighborhood links.
Guide the review from coarse to fine: declared scope and exclusions, milestone
book, landing-page progress summary, cross-chapter graph, chapter graph, then
individual node and Lean-source links. Record each human decision as approve, revise, or
block, with the exact page or node and rationale. Separate validator output
from the person's judgment. Do not silently apply requested revisions: hand
mathematical-plan changes and Lean implementation changes to Roadmap, which
records the decision and retracts the affected article so Formalize takes it up
under the revision contract,
and autonomous rubric scoring to Agent Review.
Show full SKILL.md (159 more words)Show less
Treat the landing page's Scoped roadmap percentage as completion among
formalizable leaf targets that are fully proved, including every dependency
recursively. This requires proofs for theorems and bodies for definitions. A
target marked mathlib: true follows the authored status contract; the marker
is an author assertion, not audit verification that the declaration is in
Mathlib. Treat the percentage never as whole-source completion. Read the
adjacent declared source coverage and its linked coverage contract before
making scope claims. A statement-only theorem remains incomplete whether it is
blocked or ready to prove. In a project that allows open statements, a
conditionally proved target, whose proof rests on an open statement without a
recorded Lean proof, is not complete either: it is never fully proved, so it
counts toward the percentage's total but not its completed share, as does
every target that depends on it. Present it as conditional, naming the open
statements in its Assumes row, never as proved or sorry-free.
© 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 1 other file in skills/human-review of facebookresearch/autoform-bot.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 89dff27
Compare with similar skills
Human 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 |
|---|---|---|---|---|---|---|
| Human Review this skillfacebookresearch/autoform-bot | 117 | — | ~856 | Automated safety check: Pass | MIT | |
| Personal Assistant Reviewedonyzpc/personal-assistant | 148 | — | ~3.2k | Automated safety check: Pass | AGPL-3.0 | |
| Obsidian Loggrandamenium/cortextos | 101 | — | ~1k | Automated safety check: Pass | MIT | |
| Bounded AutoresearchAgriciDaniel/claude-obsidian | 15k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Ralphrohunj/claude-build-workflow | 231 | 1 repos | ~2k | Automated safety check: Pass | None | |
| Ralphjulianromli/opencode-template | 144 | — | ~1.1k | Automated safety check: Pass | None |
Similar skills
Obsidian Log
grandamenium/cortextos
Write key decisions, project milestones, and feedback rules back to the Obsidian vault.
Bounded Autoresearch
AgriciDaniel/claude-obsidian
Runs a bounded, source-grounded research loop that drafts a cited dossier and can propose a separately reviewed merge into an Obsidian vault.
Ralph
rohunj/claude-build-workflow
Convert PRDs to prd.json format for the Ralph autonomous agent system.
Ralph
julianromli/opencode-template
Autonomous agent loop for completing features. An agent skill from julianromli/opencode-template.
Specify
RafaelGB/Obsidian-ZettelFlow
Stage 1 of the SDD pipeline — write a ZettelFlow spec into a GitHub issue body (problem, value, functional requirements, testable acceptance criteria, capability disclosure, out-of-scope).
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.
Agent Review
facebookresearch/autoform-bot
Judge an Autoform mathematical roadmap or Lean formalization with explicit, evidence-based rubrics.
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.
Related
Works with
Questions about Human Review
What does Human Review do?
Prepare and guide human inspection of an Autoform roadmap or formalization through its Obsidian graph and rendered blueprint site. Human Review is an agent skill from facebookresearch/autoform-bot. Prepare and guide human inspection of an Autoform roadmap or formalization through its Obsidian graph and rendered blueprint site.
When should I use Human Review?
Human Review fits situations like: A person wants to browse; lean artifacts visually; do not substitute an autonomous agent verdict for the humans judgment.
How do I install Human Review in Claude Code?
Run `npx skills add facebookresearch/autoform-bot --skill human-review -a claude-code`. Or copy the skill folder (skills/human-review in facebookresearch/autoform-bot) into .claude/skills/human-review in your project. Claude Code loads it when a task matches its description.
How do I install Human Review in Codex?
Run `npx skills add facebookresearch/autoform-bot --skill human-review -a codex`. Or copy the skill folder (skills/human-review in facebookresearch/autoform-bot) into .agents/skills/human-review in your project. Codex loads it when a task matches its description.
Can I use Human 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 human-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/human-review, .gemini/skills/human-review, .github/skills/human-review and .opencode/skills/human-review in your project.
What does Human Review need to run?
SKILL.md names no scripts, command-line tools or credentials: Human Review is instructions for the agent only.
Does Human 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 Human 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 Human Review use?
Human 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 Human Review use?
About 856 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.
What are the alternatives to Human Review?
Skills that share tags, products or a category with Human Review: Personal Assistant Review (edonyzpc/personal-assistant, 148 stars), Obsidian Log (grandamenium/cortextos, 101 stars), Bounded Autoresearch (AgriciDaniel/claude-obsidian, 15k stars) and Ralph (rohunj/claude-build-workflow, 231 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Human 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.