Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
Guide a user from an unclear idea to an actionable plan through the agent harness's native ask tool and clickable choices.
Install Ask To Plan
$ npx skills add scarletkc/agents --skill ask-to-plan -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install scarletkc/agents ask-to-plan --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/scarletkc/agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ask-to-plan .claude/skills/ask-to-plan && 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 "ask-to-plan" agent skill from https://github.com/scarletkc/agents/tree/main/skills/ask-to-plan into .claude/skills/ask-to-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ask-to-plan", 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/scarletkc/agents/tree/main/skills/ask-to-planType 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 scarletkc/agents --skill ask-to-plan -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install scarletkc/agents ask-to-plan --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scarletkc/agents.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ask-to-plan .agents/skills/ask-to-plan && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ask-to-plan" agent skill from https://github.com/scarletkc/agents/tree/main/skills/ask-to-plan into .agents/skills/ask-to-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ask-to-plan", 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 scarletkc/agents --skill ask-to-plan -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install scarletkc/agents ask-to-plan --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scarletkc/agents.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ask-to-plan .cursor/skills/ask-to-plan && 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 "ask-to-plan" agent skill from https://github.com/scarletkc/agents/tree/main/skills/ask-to-plan into .cursor/skills/ask-to-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ask-to-plan", 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/scarletkc/agents.git --path skills/ask-to-plan--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 scarletkc/agents --skill ask-to-plan -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install scarletkc/agents ask-to-plan --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scarletkc/agents.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ask-to-plan .gemini/skills/ask-to-plan && 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 "ask-to-plan" agent skill from https://github.com/scarletkc/agents/tree/main/skills/ask-to-plan into .gemini/skills/ask-to-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ask-to-plan", 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 scarletkc/agents ask-to-planInstalls 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 scarletkc/agents --skill ask-to-plan -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/scarletkc/agents.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ask-to-plan .github/skills/ask-to-plan && 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 "ask-to-plan" agent skill from https://github.com/scarletkc/agents/tree/main/skills/ask-to-plan into .github/skills/ask-to-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ask-to-plan", 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 scarletkc/agents --skill ask-to-plan -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install scarletkc/agents ask-to-plan --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scarletkc/agents.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ask-to-plan .opencode/skills/ask-to-plan && 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 "ask-to-plan" agent skill from https://github.com/scarletkc/agents/tree/main/skills/ask-to-plan into .opencode/skills/ask-to-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ask-to-plan", 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
ask-to-plan- GitHub stars
- 226
- Token cost
- ~2.4k tokens
- SKILL.md length
- 1,381 words
- Files
- 1
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Guide a user from an unclear idea to an actionable plan through the agent harness's native ask tool and clickable choices.
- The user wants a guided requirements interview
- SKILL.md covers Use the harness's actual ask…, Make each question easy to…, Narrow from outcomes to… and Derive the technical choices, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Step-by-step questions
What it does
Ask To Plan is an agent skill from scarletkc/agents. Guide a user from an unclear idea to an actionable plan through the agent harness's native ask tool and clickable choices. Use when the user wants a guided requirements interview, step-by-step questions, help deciding what to build, or a button-led path from goals to scope, solution, and technology choices. Do not turn an ordinary implementation request or a single clarification into an interview.
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development. The repository describes itself as: Shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents. The licence is Apache-2.0.
When your agent uses it
- The user wants a guided requirements interview
- Step-by-step questions
- Help deciding what to build
- A button-led path from goals to scope
Example prompts
- “/ask-to-plan”
What it can do on your machine
Read from SKILL.md and the folder at commit eb55005. 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
Ask To Plan loads about 2.4k tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 1,381 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 scarletkc/agents at commit eb55005, republished under its Apache-2.0 licence (© scarletkc). 1,381 words, ~2,448 tokens.
Download SKILL.mdSave it as
.claude/skills/ask-to-plan/SKILL.md (or your agent's skills folder).- name
- ask-to-plan
- description
- Guide a user from an unclear idea to an actionable plan through the agent harness's native ask tool and clickable choices. Use when the user wants a guided requirements interview, step-by-step questions, help deciding what to build, or a button-led path from goals to scope, solution, and technology choices. Do not turn an ordinary implementation request or a single clarification into an interview.
- license
- Apache-2.0
- metadata.author
- scarletkc
- metadata.source
- https://github.com/scarletkc/agents
- metadata.summary
- Turn a rough idea into clear goals, requirements, a solution, and an actionable plan through guided questions and native choices.
Ask to Plan
Help the user discover what they want by making one useful decision at a time. Move from broad outcomes to concrete requirements and then an implementable plan. The user should be able to make progress by choosing buttons, including when they have no idea yet or do not know technical terms.
The default deliverable is a plan. Starting this interview or accepting a solution does not itself request implementation. If the user later asks to build it, carry the settled requirements into that work.
Use the harness's actual ask tool
Identify the native structured-question tool exposed in the current session,
such as request_user_input, request_user_input_async, or the harness's
equivalent. Use the tool to present choices. Follow its actual schema and
current mode restrictions, including question limits, option limits, and
whether the interface already supplies free-text input or an Other option.
Tool names here are discovery hints, not a promise that a tool is available.
Start with a brief explanation of the next decision and one native question. Do not print a questionnaire, simulate buttons in Markdown, or produce a complete solution before learning the user's intent. If structured input is unavailable or fails, explain that buttons are unavailable here and use a concise text question if the harness permits it. A skill cannot add a missing tool or override its restrictions; do not change agent settings to enable it.
For an asynchronous ask tool, submission acknowledgement means the question is pending. Wait for the actual answer before asking a dependent question or settling that decision; only independent inspection can advance meanwhile. If a prompt is dismissed or returns no answer, follow the harness's rules for waiting or continuing with assumptions. Keep unanswered choices unresolved or explicitly provisional. A preselected option, timeout, or tool success is not the user's choice.
Make each question easy to answer
- Ask one question per round by default. Its answer should change the goal, scope, approach, or next question. Skip details that do not affect the plan.
- Offer two or three short, distinct choices within the tool's limits. Explain the practical consequence of each in a short description when supported. Ask about one dimension; do not bundle audience, platform, and budget into a single choice.
- Build options from what is already known. Use the user's language and level of detail. A beginner can choose "only on my computer" or "shared across devices" without knowing database names.
- Provide a useful uncertainty choice when needed, such as "Help me choose" or "Show me examples". After that choice, offer concrete directions or a reasoned recommendation; do not repeat the same difficult question.
- Recommend an option when the known needs support it and explain why. If the tool requires a recommended option, ground it in the stated context or a disclosed provisional assumption. Do not invent a user preference.
- Accept free-text corrections and combinations where supported. Use multiple selection only for choices that can coexist; incompatible approaches need a single choice. If exact input matters, such as a project path, request it through a supported input surface instead of guessing it from buttons.
Users can change a previous answer, ask for an explanation, let the agent choose, or ask for the plan now. Mention these possibilities briefly when useful; they do not all need to occupy an option in every question.
Narrow from outcomes to implementation
First extract what the user has already supplied. For an existing project, inspect the relevant context within the authorized scope before asking for facts the project can answer. Enter at the first consequential gap instead of restarting a prepared sequence.
Use the following progression as a map, not a mandatory questionnaire. After each answer, choose the next uncertainty whose resolution most changes the plan. Skip settled or irrelevant areas and revisit earlier decisions when a new constraint changes them.
| Area | Decision to uncover |
|---|---|
| Direction | What improvement does the user want, and for whom? If they have no idea yet, offer a few concrete outcomes to explore. |
| Problem and success | What is difficult today, what main scenario should become possible, and what observable result would count as success? |
| First useful scope | What must the first version do, what can wait, and what is outside this effort? Resolve competing priorities with a concrete tradeoff. |
| Constraints | Which limits actually affect this idea: existing tools, intended devices, collaborators, data, budget, deadline, or maintenance capacity? |
| Solution | Which approach fits the chosen outcome and constraints? Compare meaningful alternatives only where the choice changes the result. |
| Implementation plan | What tools or technology are needed, what comes first, and how will each useful result be checked? |
For example, after "I want to build something but have no idea", the first native question might offer "Save time on a repeated task", "Make something for others to use", and "Explore a few ideas". Selecting the first should lead to relevant tasks to simplify. Selecting the second should lead to an audience or problem to serve. Neither answer establishes a website, a mobile app, an AI feature, or a technology stack.
Once the purpose is clear, specialize the questions to its domain. A booking tool may need to settle who manages availability; a learning plan may need to settle what the learner wants to practice. Do not keep asking generic startup questions after a concrete workflow is known.
Show full SKILL.md (496 more words)Show less
Derive the technical choices
Ask about consequences the user can judge before asking about implementation preferences. Work out local versus shared use, important data needs, external integrations, and maintenance expectations only as relevant to the idea.
Then recommend a coherent, appropriately sized solution. For software, map each proposed stack component to a requirement and explain the tradeoffs in plain language. Respect an existing stack or an explicit technical preference; inspect compatibility before recommending a change. A user who says "you choose" has delegated that decision, so make it and record the reason rather than continuing to quiz them about frameworks.
Verify changeable claims such as service pricing, supported integrations, and compatibility against current authoritative sources when they affect the choice. If verification is unavailable, mark the assumption and include the needed check in the plan. Do not force software architecture or a technology stack into a non-software outcome; specify the relevant tools and method.
Carry decisions forward
Maintain a compact working record in conversation context: the goal, accepted decisions, constraints, agent recommendations or assumptions, and consequential open questions. Keep user choices distinct from inferred facts. Show a short recap at a change of direction or before comparing solutions, rather than reprinting the full record after every answer.
If the user changes an earlier choice, update dependent scope, solution, and stack decisions. Preserve answers that still apply. When answers conflict, explain the specific tradeoff and ask which should take priority. Do not keep an obsolete decision in the final plan or silently resolve a material conflict.
Converge and deliver the plan
Stop exploring when the goal and audience, first useful scope, major constraints, solution, and acceptance criteria are clear enough for someone to take the next step. Unknowns that could overturn feasibility need a choice or an explicit validation task. Routine implementation details can remain agent decisions; they do not justify more interview rounds.
Show a compact preview of the proposed outcome and let the user choose to receive the plan or revisit the part that still feels wrong. This is alignment on requirements, not permission to execute. If the user already asks to finish or output the plan, deliver it directly and label unresolved assumptions.
Write a self-contained plan at a depth appropriate to the task. Cover:
- The goal, intended users, and observable success criteria.
- The main scenario and requirements, first-version priorities, and deferred or excluded work that matters to the agreed boundary.
- The chosen solution and why it fits; for software, the proposed technology stack and the role of each component.
- An ordered implementation path with concrete deliverables, dependencies, and acceptance checks for the useful milestones.
- Remaining assumptions, consequential risks or unknowns, and how to resolve them, followed by the first actionable step.
Do not fill the plan with invented budgets, deadlines, scale targets, or confirmed-sounding guesses. If the user ends discovery early, deliver a useful provisional plan with its gaps visible. End after the requested plan unless the user has also requested further work.
© scarletkc, 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 skills/ask-to-plan of scarletkc/agents.
Open the folder on GitHubat commit eb55005
Compare with similar skills
Ask To Plan 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 |
|---|---|---|---|---|---|---|
| Ask To Plan this skillscarletkc/agents | 226 | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Vercel Composition Patternssupabase/supabase | 111k | 58 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 4 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
More from scarletkc/agents
All 11 skills in this repoAntigravity CLI
scarletkc/agents
Delegate bounded investigation, review, or implementation tasks to Antigravity CLI from a supervising agent.
Grok CLI
scarletkc/agents
Delegate bounded tasks to Grok Build from a supervising agent such as Codex.
Talk Like Scarletkc
scarletkc/agents
按 scarletkc 本人的自然表达习惯代写、改写、润色和翻译文本，适用于推文、评论、聊天消息、模型或工具体验文、项目介绍、GitHub 文本和正式通信。用户要求撰写可直接使用的成稿、去除 AI 腔，或在翻译中保留本人语气和立场时使用，无需明确点名本 skill。单纯的事实问答、技术分析、代码审查和任务讨论不触发。
Codex CLI
scarletkc/agents
When handing work to the Codex CLI earns its cost, and how to size the run: second-model review, bounded implementation hand-offs, sandbox permissions, model and reasoning effort.
Marketing Copy
scarletkc/agents
Write outbound promotional copy for a product or project: launch and update posts for community platforms and social media, store page descriptions and short blurbs, landing page headlines and calls…
Scoped Change
scarletkc/agents
Judgment rules for locating the correct boundary of a requested change: staying inert outside it while completing every required site inside it.
Related
Categories
Questions about Ask To Plan
What does Ask To Plan do?
Guide a user from an unclear idea to an actionable plan through the agent harness's native ask tool and clickable choices. Ask To Plan is an agent skill from scarletkc/agents. Guide a user from an unclear idea to an actionable plan through the agent harness's native ask tool and clickable choices.
When should I use Ask To Plan?
Ask To Plan fits situations like: the user wants a guided requirements interview; step-by-step questions; help deciding what to build; A button-led path from goals to scope.
How do I install Ask To Plan in Claude Code?
Run `npx skills add scarletkc/agents --skill ask-to-plan -a claude-code`. Or copy the skill folder (skills/ask-to-plan in scarletkc/agents) into .claude/skills/ask-to-plan in your project. Claude Code loads it when a task matches its description.
How do I install Ask To Plan in Codex?
Run `npx skills add scarletkc/agents --skill ask-to-plan -a codex`. Or copy the skill folder (skills/ask-to-plan in scarletkc/agents) into .agents/skills/ask-to-plan in your project. Codex loads it when a task matches its description.
Can I use Ask To Plan 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 scarletkc/agents --skill ask-to-plan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ask-to-plan, .gemini/skills/ask-to-plan, .github/skills/ask-to-plan and .opencode/skills/ask-to-plan in your project.
What does Ask To Plan need to run?
SKILL.md names no scripts, command-line tools or credentials: Ask To Plan is instructions for the agent only.
Does Ask To Plan 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 Ask To Plan 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 Ask To Plan use?
Ask To Plan is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Ask To Plan use?
About 2.4k tokens (SKILL.md is roughly 9.8k 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 Ask To Plan?
Skills that share tags, products or a category with Ask To Plan: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ask To Plan?
scarletkc (a GitHub user) maintains it in scarletkc/agents, which has 226 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 21, 2026.
Source: scarletkc/agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.