New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Webgpt Todo Response

by yusifeng in yusifeng/formax

Use after receiving WebGPT or another LLM review on a Formax todo and before sending the todo back for another pass.

MITAuto-check passed

Install Webgpt Todo Response

skills CLI
$ npx skills add yusifeng/formax --skill webgpt-todo-response -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install yusifeng/formax webgpt-todo-response --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/yusifeng/formax.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/webgpt-todo-response .claude/skills/webgpt-todo-response && rm -rf skills-src

Use ~/.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/

Facts

Skill name
webgpt-todo-response
GitHub stars
194
Token cost
~1.1k tokens
SKILL.md length
551 words
Files
2
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Use after receiving WebGPT or another LLM review on a Formax todo and before sending the todo back for another pass.

  • Works in 4 steps: Identify WebGPT's strongest… → Check the todo against Formax boundaries. → Find weak spots in the todo. → …
  • SKILL.md covers Purpose, Inputs To Inspect, Workflow and Output Shape, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Webgpt Todo Response is an agent skill from yusifeng/formax. Use after receiving WebGPT or another LLM review on a Formax todo and before sending the todo back for another pass. Produce a concise handoff response that says what we adopted, what we reject or question, and what the reviewer should specifically re-evaluate in docs/todolist.md.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: Terminal-first AI assistant for software engineering tasks (inspired by Claude Code v2.0.67). The licence is MIT.

Example prompts

  • “/webgpt-todo-response”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Identify WebGPT's strongest recommendations.
  2. Check the todo against Formax boundaries.
  3. Find weak spots in the todo.
  4. Write a concise message for WebGPT.

What it can do on your machine

Read from SKILL.md and the folder at commit 1b0c3f3. 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 (its code samples are markdown).

    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

Webgpt Todo Response loads about 1.1k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 551 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~76
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 yusifeng/formax at commit 1b0c3f3, republished under its MIT licence (© yusifeng). 551 words, ~1,144 tokens.

Download SKILL.mdSave it as .claude/skills/webgpt-todo-response/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
webgpt-todo-response
description
Use after receiving WebGPT or another LLM review on a Formax todo and before sending the todo back for another pass. Produce a concise handoff response that says what we adopted, what we reject or question, and what the reviewer should specifically re-evaluate in `docs/todolist.md`.

WebGPT Todo Response

Purpose

Generate the message to send back to WebGPT after we have read its previous analysis and drafted or updated docs/todolist.md.

Use this skill when the user asks:

  • whether we have rebuttals or questions for WebGPT
  • what to include when sending our todo back to WebGPT for another pass
  • to prepare a response asking WebGPT to evaluate, improve, or challenge our todo
  • to compare WebGPT's recommendations against our chosen implementation scope

Inputs To Inspect

Read only the files needed for the current handoff:

  • WebGPT response, usually under repomix-output/
  • current todo, usually docs/todolist.md
  • relevant canonical docs under docs/contracts/*, docs/frontend/*, or other explicitly governing docs when the todo depends on them
  • optional other LLM replies if the user asks for a multi-model synthesis

Do not re-run broad repository analysis unless the todo or WebGPT response depends on code facts that are unclear.

Workflow

  1. Identify WebGPT's strongest recommendations.

    • Mark which ones are adopted in the todo.
    • Mark which ones are intentionally deferred.
    • Mark which ones are rejected or still need clarification.

  2. Check the todo against Formax boundaries.

    • Canonical semantics belong in docs/contracts/* and canonical runtime layers, not only UI.
    • Web reference UI should reflect runtime/platform truth, not invent it.
    • Do not move thread/runtime state ownership into ad hoc component-local logic when the task is structurally runtime-driven.
    • Preserve parity-sensitive behavior when relevant: transcript surface semantics, URL/thread sync, prompt/tool exposure boundaries, permissions flow, and active-thread canonical gating.
    • Avoid turning a focused task into a broad cleanup or cross-subsystem redesign unless explicitly requested.

  3. Find weak spots in the todo.

    • Missing canonical-doc step
    • Missing data/type/interface step before UI
    • Runtime state ownership drift
    • Welcome/draft/thread semantics being mixed together
    • Scope creep into unrelated app-server, terminal, diff, approval, or desktop integration work
    • Missing tests or review gates
    • Missing statement of protocol constraints or non-atomic failure boundaries

  4. Write a concise message for WebGPT.

    • Assume WebGPT has no hidden context beyond the attached todo and bundle.
    • Be explicit about decisions already made.
    • Ask targeted questions instead of open-ended “any thoughts?”
    • Request concrete todo edits or challenges, not generic feedback.
Show full SKILL.md (207 more words)Show less

Output Shape

Produce a copy-ready Markdown response with these sections:

md
# Response To WebGPT

## What We Adopted
- ...

## Where We Differ / Pushback
- ...

## My Current Leaning
1. ...

## Highest-Value Review Points
1. ...

## Specific Questions For You
1. ...

## Please Review The Todo For
- ...

## Constraints To Preserve
- ...

Keep it short enough to paste into WebGPT with the todo. Prefer 5-10 specific questions/checks over a long essay.

Use My Current Leaning to distinguish default decisions from genuinely open questions. WebGPT may challenge these, but should not treat them as blank slate.

Use Highest-Value Review Points to focus WebGPT on the few risks most likely to improve the todo. These should be sharper than the broader checklist.

Good Question Patterns

  • “Does this todo still hide new semantics inside !activeThreadId, or is the draft state truly first-class?”
  • “Are we separating selectedCwd from draftCwd cleanly enough to avoid left-rail/runtime state drift?”
  • “Is the proposed first-send flow realistic given thread/start and turn/start are non-atomic?”
  • “Are we over-expanding the task into unrelated desktop/add-project behavior instead of keeping the mainline on new-thread draft semantics?”
  • “Do the loops lock runtime ownership first, then UI, then tests, or is there still UI-first drift?”

Avoid

  • Do not ask WebGPT to implement patches unless the user explicitly wants that.
  • Do not ask WebGPT to run commands.
  • Do not include local absolute paths.
  • Do not send vague requests like “please improve this.”
  • Do not restate the whole todo; reference it and ask for specific audit points.

© yusifeng, 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 .codex/skills/webgpt-todo-response of yusifeng/formax.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 1b0c3f3

Compare with similar skills

Webgpt Todo Response 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.

Webgpt Todo Response compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Webgpt Todo Response this skillyusifeng/formax194—~1.1kAutomated safety check: PassMIT
Responsive Unitsthedaviddias/Front-End-Checklist74k—~472Automated safety check: PassMIT
Responsive Designwshobson/agents40k2 repos~498Automated safety check: PassMIT
Responsive Imagesthedaviddias/Front-End-Checklist74k—~403Automated safety check: PassMIT
Payments Receivedsickn33/agentic-awesome-skills47k1 repos~3.5kAutomated safety check: PassMIT
Performing Ransomware Responsemukul975/Anthropic-Cybersecurity-Skills34k—~2.9kAutomated safety check: PassApache-2.0

Similar skills

  • Responsive Units

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing stylesheets, component styles, and responsive behavior related to Use relative units for responsive layouts.

    74k GitHub stars~472 tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed

  • Responsive Design

    wshobson/agents

    Implement modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first breakpoint strategies.

    40k GitHub starsUsed in 2 repos~498 tokens
    Frontend & DesignAuto-check passed

  • Responsive Images

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing article images, cards, galleries, or any component rendered at multiple sizes across breakpoints.

    74k GitHub stars~403 tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed

  • Payments Received

    sickn33/agentic-awesome-skills

    Payments received log: reference, client and invoice, amount and currency, payment date and method, withholding tax, bank account, received-by and receipt-sent status.

    47k GitHub starsUsed in 1 repo~3.5k tokens
    Documents & OfficeAuto-check passed

  • Performing Ransomware Response

    mukul975/Anthropic-Cybersecurity-Skills

    Executes a structured ransomware incident response from detection through containment, forensic analysis, decryption assessment, recovery, and post-incident hardening, covering ransom negotiation…

    34k GitHub stars~2.9k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed

  • Incident Response

    sickn33/agentic-awesome-skills

    Handle security incidents with IR playbooks and procedures. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~3.7k tokens
    DevOps & CloudAuto-check passed

More from yusifeng/formax

All 21 skills in this repo

  • Formax Repomix Handoff Workflow

    yusifeng/formax

    A skill your agent uses when preparing a Formax code handoff: selecting files, generating repomix bundles, and writing a high-quality prompt for WebGPT or another coding agent with clear constraints…

    194 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

  • Formax Skill Capture

    yusifeng/formax

    A skill your agent uses when we want to turn a just-finished Formax workflow (e.g.

    194 GitHub stars~530 tokensUpdated 2 mo ago
    Auto-check passed

  • Analyze Task

    yusifeng/formax

    A skill your agent uses when a Formax repository task is non-trivial and you should analyze goals, non-goals, boundaries, data/type/interface impact, contract impact, test strategy, and whether an…

    194 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

  • Formax Dev Loop Workflow

    yusifeng/formax

    A skill your agent uses when working on Formax code changes and you need a disciplined dev loop: keep a single mainline task, avoid scope drift, run only targeted tests (no coverage), avoid partial…

    194 GitHub stars~686 tokensUpdated 2 mo ago
    Auto-check passed

  • Formax Tool UI Blocks Workflow

    yusifeng/formax

    Implement or refactor Formax tool transcript UI using the Tool UI Blocks (C-lite) pattern (ToolUiBlocks renderer + blocks presenters) to avoid touching many tool presenter files; use when adjusting…

    194 GitHub stars~1.3k tokensUpdated 2 mo ago
    Auto-check passed

  • Formax Semantics Parity Workflow

    yusifeng/formax

    A skill your agent uses when implementing or modifying behavior that must stay consistent across TUI and Web (mode/input/tool/replay/order).

    194 GitHub stars~1.1k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Webgpt Todo Response

What does Webgpt Todo Response do?

Use after receiving WebGPT or another LLM review on a Formax todo and before sending the todo back for another pass. Webgpt Todo Response is an agent skill from yusifeng/formax. Use after receiving WebGPT or another LLM review on a Formax todo and before sending the todo back for another pass.

How do I install Webgpt Todo Response in Claude Code?

Run `npx skills add yusifeng/formax --skill webgpt-todo-response -a claude-code`. Or copy the skill folder (.codex/skills/webgpt-todo-response in yusifeng/formax) into .claude/skills/webgpt-todo-response in your project. Claude Code loads it when a task matches its description.

How do I install Webgpt Todo Response in Codex?

Run `npx skills add yusifeng/formax --skill webgpt-todo-response -a codex`. Or copy the skill folder (.codex/skills/webgpt-todo-response in yusifeng/formax) into .agents/skills/webgpt-todo-response in your project. Codex loads it when a task matches its description.

Can I use Webgpt Todo Response 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 yusifeng/formax --skill webgpt-todo-response -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/webgpt-todo-response, .gemini/skills/webgpt-todo-response, .github/skills/webgpt-todo-response and .opencode/skills/webgpt-todo-response in your project.

What does Webgpt Todo Response need to run?

SKILL.md names no scripts, command-line tools or credentials: Webgpt Todo Response is instructions for the agent only.

Does Webgpt Todo Response 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 Webgpt Todo Response 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 Webgpt Todo Response use?

Webgpt Todo Response 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 Webgpt Todo Response use?

About 1.1k tokens (SKILL.md is roughly 4.6k 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 Webgpt Todo Response?

Skills that share tags, products or a category with Webgpt Todo Response: Responsive Units (thedaviddias/Front-End-Checklist, 74k stars), Responsive Design (wshobson/agents, 40k stars), Responsive Images (thedaviddias/Front-End-Checklist, 74k stars) and Payments Received (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Webgpt Todo Response?

yusifeng (a GitHub user) maintains it in yusifeng/formax, which has 194 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on July 24, 2026.

Source: yusifeng/formax on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.