MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
How to read a working agent's changes and write the review it will be handed.
Apache-2.0Auto-check passed
Install Review Notes
$ npx skills add humanfia/humanize --skill review-notes -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install humanfia/humanize review-notes --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/humanfia/humanize.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/hmz/flows/builtin/rlar/skills/review-notes .claude/skills/review-notes && 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 "review-notes" agent skill from https://github.com/humanfia/humanize/tree/main/src/hmz/flows/builtin/rlar/skills/review-notes into .claude/skills/review-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-notes", 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/humanfia/humanize/tree/main/src/hmz/flows/builtin/rlar/skills/review-notesType 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 humanfia/humanize --skill review-notes -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install humanfia/humanize review-notes --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/humanfia/humanize.git skills-src && mkdir -p .agents/skills && cp -r skills-src/src/hmz/flows/builtin/rlar/skills/review-notes .agents/skills/review-notes && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "review-notes" agent skill from https://github.com/humanfia/humanize/tree/main/src/hmz/flows/builtin/rlar/skills/review-notes into .agents/skills/review-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-notes", 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 humanfia/humanize --skill review-notes -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install humanfia/humanize review-notes --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/humanfia/humanize.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/src/hmz/flows/builtin/rlar/skills/review-notes .cursor/skills/review-notes && 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 "review-notes" agent skill from https://github.com/humanfia/humanize/tree/main/src/hmz/flows/builtin/rlar/skills/review-notes into .cursor/skills/review-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-notes", 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/humanfia/humanize.git --path src/hmz/flows/builtin/rlar/skills/review-notes--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 humanfia/humanize --skill review-notes -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install humanfia/humanize review-notes --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/humanfia/humanize.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/src/hmz/flows/builtin/rlar/skills/review-notes .gemini/skills/review-notes && 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 "review-notes" agent skill from https://github.com/humanfia/humanize/tree/main/src/hmz/flows/builtin/rlar/skills/review-notes into .gemini/skills/review-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-notes", 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 humanfia/humanize review-notesInstalls 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 humanfia/humanize --skill review-notes -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/humanfia/humanize.git skills-src && mkdir -p .github/skills && cp -r skills-src/src/hmz/flows/builtin/rlar/skills/review-notes .github/skills/review-notes && 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 "review-notes" agent skill from https://github.com/humanfia/humanize/tree/main/src/hmz/flows/builtin/rlar/skills/review-notes into .github/skills/review-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-notes", 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 humanfia/humanize --skill review-notes -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install humanfia/humanize review-notes --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/humanfia/humanize.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/src/hmz/flows/builtin/rlar/skills/review-notes .opencode/skills/review-notes && 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 "review-notes" agent skill from https://github.com/humanfia/humanize/tree/main/src/hmz/flows/builtin/rlar/skills/review-notes into .opencode/skills/review-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-notes", 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
review-notes- GitHub stars
- 277
- Token cost
- ~453 tokens
- SKILL.md length
- 283 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
How to read a working agent's changes and write the review it will be handed.
- Works in 5 steps: A test weakened, skipped, or narrowed… → A branch special-cased on the exact… → A function stubbed with a TODO, a pass,… → …
- Reviewing work in a repository
- SKILL.md covers Read the repository, not the…, Look for the work that only… and Write it as an instruction
- Calls git
What it does
Review Notes is an agent skill from humanfia/humanize. How to read a working agent's changes and write the review it will be handed. Use when reviewing work in a repository, checking a change against the task it was for, or looking for work that was faked, stubbed or special-cased to pass.
Its SKILL.md is about 450 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It works with Python. The repository describes itself as: The agent flow system for token maxxing. The licence is Apache-2.0.
When your agent uses it
- Reviewing work in a repository
- Checking a change against the task it was for
- Looking for work that was faked
- Special-cased to pass
Example prompts
- “/review-notes”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- A test weakened, skipped, or narrowed until it passes.
- A branch special-cased on the exact input the test uses.
- A function stubbed with a TODO, a pass, or a hard-coded return.
- An error swallowed so a failure reads as a success.
- A file written but never reached from anything that runs.
What it can do on your machine
Read from SKILL.md and the folder at commit e16e329. 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
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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
Review Notes loads about 453 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 283 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 humanfia/humanize at commit e16e329, republished under its Apache-2.0 licence (© humanfia). 283 words, ~453 tokens.
Download SKILL.mdSave it as
.claude/skills/review-notes/SKILL.md (or your agent's skills folder).- name
- review-notes
- description
- How to read a working agent's changes and write the review it will be handed. Use when reviewing work in a repository, checking a change against the task it was for, or looking for work that was faked, stubbed or special-cased to pass.
Reviewing a round of work
The review is not a report for a person. It is the next prompt of the agent that did the work, word for word, and it is everything that agent will hear about this round.
Read the repository, not the summary
What the working agent said it did is a claim. What the repository holds is the evidence.
git statusandgit difffor what actually changed this round.- Read the changed files themselves, and the files they call into.
- Run what the project runs -- its tests, its linter, its build -- rather than trusting a line saying they pass.
Look for the work that only looks done
In order of how often it is the answer:
- A test weakened, skipped, or narrowed until it passes.
- A branch special-cased on the exact input the test uses.
- A function stubbed with a
TODO, apass, or a hard-coded return. - An error swallowed so a failure reads as a success.
- A file written but never reached from anything that runs.
Any of these means the round is not done, however much else was built.
Write it as an instruction
Cite the file and the line. Say what is wrong, and what to do next. Leave nothing to be inferred: the agent reading this cannot ask a follow-up question, and has no memory of your last review beyond what the code now holds.
Say it is finished only when everything asked for is implemented, it works, nothing was faked, and there is no next step worth taking. When it is finished, say what was built and how it was checked -- that is what the run ends on.
© humanfia, 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
Files
Just SKILL.md in src/hmz/flows/builtin/rlar/skills/review-notes of humanfia/humanize.
Open the folder on GitHubat commit e16e329
Compare with similar skills
Review Notes 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 |
|---|---|---|---|---|---|---|
| Review Notes this skillhumanfia/humanize | 277 | — | ~453 | Automated safety check: Pass | Apache-2.0 | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| PDF Processinganthropics/skills | 180k | 47 repos | ~2k | Automated safety check: Pass | Proprietary | |
| NotebookLM Research AssistantPleasePrompto/notebooklm-skill | 7.8k | 14 repos | ~2.4k | Automated safety check: Notes | MIT | |
| Manim Video Productionbrowser-use/video-use | 29k | 6 repos | ~3k | Automated safety check: Pass | MIT | |
| PPT Masterhugohe3/ppt-master | 59k | 1 repos | ~2.5k | Automated safety check: Pass | MIT |
Similar skills
- Official
- Official
PDF Processing
anthropics/skills
Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.
NotebookLM Research Assistant
PleasePrompto/notebooklm-skill
Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources.
Manim Video Production
browser-use/video-use
Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.
PPT Master
hugohe3/ppt-master
Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.
Scikit Learn
zLanqing/codex-claude-academic-skills
Machine learning in Python with scikit-learn. An agent skill from zLanqing/codex-claude-academic-skills.
Related
Works with
Questions about Review Notes
What does Review Notes do?
How to read a working agent's changes and write the review it will be handed. Review Notes is an agent skill from humanfia/humanize. How to read a working agent's changes and write the review it will be handed.
When should I use Review Notes?
Review Notes fits situations like: reviewing work in a repository; checking a change against the task it was for; looking for work that was faked; special-cased to pass.
How do I install Review Notes in Claude Code?
Run `npx skills add humanfia/humanize --skill review-notes -a claude-code`. Or copy the skill folder (src/hmz/flows/builtin/rlar/skills/review-notes in humanfia/humanize) into .claude/skills/review-notes in your project. Claude Code loads it when a task matches its description.
How do I install Review Notes in Codex?
Run `npx skills add humanfia/humanize --skill review-notes -a codex`. Or copy the skill folder (src/hmz/flows/builtin/rlar/skills/review-notes in humanfia/humanize) into .agents/skills/review-notes in your project. Codex loads it when a task matches its description.
Can I use Review Notes 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 humanfia/humanize --skill review-notes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-notes, .gemini/skills/review-notes, .github/skills/review-notes and .opencode/skills/review-notes in your project.
What does Review Notes need to run?
Going by SKILL.md and its folder, Review Notes needs the command-line tools its instructions call (git).
Does Review Notes access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Review Notes 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 Review Notes use?
Review Notes 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.
How many tokens does Review Notes use?
About 453 tokens (SKILL.md is roughly 1.8k 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 Review Notes?
Skills that share tags, products or a category with Review Notes: MCP Server Builder (anthropics/skills, 180k stars), PDF Processing (anthropics/skills, 180k stars), NotebookLM Research Assistant (PleasePrompto/notebooklm-skill, 7.8k stars) and Manim Video Production (browser-use/video-use, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Review Notes?
humanfia (a GitHub organization) maintains it in humanfia/humanize, which has 277 GitHub stars. The repository was last updated on October 11, 2026.
Source: humanfia/humanize on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.