Agent skill

Whats Next

by davepoon in davepoon/buildwithclaude

Assesses the current state of the startup project and recommends what to focus on next.

MITAuto-check passed

Install Whats Next

skills CLI
$ npx skills add davepoon/buildwithclaude --skill whats-next -a claude-code

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

GitHub CLI
$ gh skill install davepoon/buildwithclaude whats-next --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/davepoon/buildwithclaude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/startup-superpowers/skills/whats-next .claude/skills/whats-next && 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
whats-next
GitHub stars
3.6k
Token cost
~1.7k tokens
SKILL.md length
821 words
Files
6 (incl. references)
Skills in repo
247
Repo updated
First seen
Licence
MIT

At a glance

Assesses the current state of the startup project and recommends what to focus on next.

  • There is a need
  • SKILL.md covers Before you start, When no startup/ exists and When startup/ exists and…
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • A question from the user to understand what the next steps are

What it does

Whats Next is an agent skill from davepoon/buildwithclaude. Assesses the current state of the startup project and recommends what to focus on next. Use when there is a need or a question from the user to understand what the next steps are or what to focus on next.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/b2b-painkiller.md`, `references/b2c-painkiller.md` and `references/initialization.md`).

The repository describes itself as: A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw. The licence is MIT.

When your agent uses it

  • There is a need
  • A question from the user to understand what the next steps are
  • What to focus on next

Example prompts

  • “Use the whats-next skill to assess the current state of the startup project and recommends what to focus on next”
  • “/whats-next”

What it can do on your machine

Read from SKILL.md and the folder at commit 616deb5. 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

Whats Next loads about 1.7k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 54 tokens; SKILL.md has 821 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

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 davepoon/buildwithclaude at commit 616deb5, republished under its MIT licence (© davepoon). 821 words, ~1,714 tokens.

Download SKILL.mdSave it as .claude/skills/whats-next/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
whats-next
description
Assesses the current state of the startup project and recommends what to focus on next. Use when there is a need or a question from the user to understand what the next steps are or what to focus on next.

What's Next

Orient the user on where their project stands and what to focus on next. Most of the time this is a quick read of the plan and a conversational nudge — the user just needs reminding. When the plan itself needs structural changes, escalate to the lean-startup-advisor subagent for a full reassessment.

Before you start

Check whether ./startup/core.md exists in the current working directory. Use a relative path. Do not list parent directories or absolute paths — the project is always the current working directory.


When no startup/ exists

The project hasn't been initialized yet. Load the initialization workflow:

.claude/skills/whats-next/references/initialization.md

The reference file's instructions take over from this point. For founders who already have materials or progress, initialization.md will route to:

.claude/skills/whats-next/references/with-progress.md

When startup/ exists and plan.md is present

Start with a quick orientation. Only escalate to a full reassessment if the plan needs structural changes.

Quick orientation (default)

Read startup/plan.md and startup/core.md. List the artifact directories (hypotheses/, competitors/, interview-scripts/, interviews/) to get a sense of what exists and what's changed. Also read the ## Next Action sections from startup/hypotheses/*.md — these are the per-assumption validation moves written by the last hypothesis assessment.

Then orient the user across two altitudes, so the strategic and the tactical don't compete:

  • Strategic (from plan.md): the ## Current Focus — the milestone-level thing the project is working toward.
  • Tactical (from the hypothesis ## Next Action sections): the single sharpest concrete move right now — the smallest observable next step. Pick it with simple judgment: weigh hypothesis status, stakes, and tag (a foundational untested assumption with nothing behind it, or one close to flipping, usually wins). If a recent assessment flagged a Top pick, prefer that.

Phrase it as both, e.g.: "Strategically you're on {Current Focus}. The sharpest concrete move right now is {next action from hypothesis X}." If the user completed something since last time, check it off in plan.md. Offer to jump into whatever the current focus or the next action points to.

Keep this lightweight: read the ## Next Action sections that already exist on disk — do not dispatch the hypotheses-manager just to refresh them. Those sections are refreshed during full reassessments and after interview analysis, which is where assessments belong.

Quick orientation does not restructure the plan — no adding, removing, or reordering steps, no changing the Current Focus. It works with the plan as-is.

When to escalate to full reassessment

Use your judgment. These are signals, not a checklist — weigh them in context:

  • The plan's current milestone is complete (all or nearly all steps checked off)
  • The user says something has fundamentally changed or explicitly asks to reassess
  • The user changed core.md's foundational fields (Audience/ICP, Problem, or Solution) — a potential pivot
  • Artifacts appear to contradict the plan's assumptions (e.g., interviews revealed a different problem than what the plan is built around)
  • The Current Focus no longer makes sense given what exists in the project
  • The user is questioning direction ("is this the right approach?"), not asking for next steps

When none of these apply — uncompleted steps remain that still make sense, the Current Focus is clear and not invalidated, the user is just resuming or needs a reminder — stay in quick orientation.

Show full SKILL.md (299 more words)Show less
Full reassessment

When the plan needs structural changes, dispatch the lean-startup-advisor subagent.

Step 1 — Gather all project state:

Read these files and collect their contents:

  • startup/core.md
  • startup/plan.md
  • All .md files in startup/hypotheses/ (if any)
  • All .md files in startup/competitors/ (if any)
  • All .md files in startup/interview-scripts/ (if any)
  • All .md files in startup/interviews/ (if any, excluding transcripts/)

Step 2 — Dispatch the subagent:

Send a single Task call to the lean-startup-advisor agent. Include all file contents in the prompt:

Assess the current state of this startup project and recommend updates to the plan.

## Project definition (startup/core.md)
{full contents of core.md}

## Current plan (startup/plan.md)
{full contents of plan.md}

## Hypotheses (startup/hypotheses/)
{for each file: filename + full contents, or "No hypothesis files yet."}

## Competitors (startup/competitors/)
{for each file: filename + full contents, or "No competitor files yet."}

## Interview scripts (startup/interview-scripts/)
{for each file: filename + full contents, or "No interview script files yet."}

## Interview analyses (startup/interviews/)
{for each file: filename + full contents, or "No interview analysis files yet."}

Step 3 — Present recommendations:

When the subagent returns, present its assessment and recommended changes to the user. Walk through the key points conversationally — don't just dump the raw output.

Step 3a — If the advisor flagged a pivot:

If the advisor's response includes an Artifact Relevance section, a pivot was detected — foundational fields in core.md changed substantially. Before updating the plan, load the pivot impact workflow:

.claude/skills/whats-next/references/pivot-impact.md

The reference file's instructions take over for the artifact walk-through. Return here for the plan update after it completes.

Step 4 — Update the plan:

After presenting the recommendations, tell the founder specifically what you're writing — then write it. Don't ask for blanket permission; state the update and do it. For example: "Updating the plan: marking [step] done, setting focus to [X], adding two new steps. Writing now." Then write the file.

Only pause for explicit confirmation if the advisor recommended removing existing steps or the direction change is significant enough that the founder might want to redirect first.

Update startup/plan.md:

  • Check off completed steps (change - [ ] to - [x])
  • Update the ## Current Focus section
  • Add new steps to the ## Steps section
  • Remove steps only if the advisor explicitly recommended it and you've surfaced this to the founder
  • Append the log entry under ## Log with a ### {YYYY-MM-DD} heading
  • Update last_assessed in frontmatter to today's date

Read plan.md before writing.

© davepoon, 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 5 other files (references) in plugins/startup-superpowers/skills/whats-next of davepoon/buildwithclaude.

  • SKILL.md
  • references/b2b-painkiller.md
  • references/b2c-painkiller.md
  • references/initialization.md
  • references/pivot-impact.md
  • references/with-progress.md

Open the folder on GitHubat commit 616deb5

Compare with similar skills

Whats Next 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.

Whats Next compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Whats Next this skilldavepoon/buildwithclaude3.6k—~1.7kAutomated safety check: PassMIT
Startup Canvasphuryn/pm-skills27k—~1.6kAutomated safety check: PassMIT
Acreadiness Assessgithub/awesome-copilot40k1 repos~839Automated safety check: PassMIT
Relsa Severity AssessmentK-Dense-AI/scientific-agent-skills48k1 repos~5.2kAutomated safety check: NotesMIT
Claude Code Skill Assessmentluongnv89/claude-howto42k—~5.5kAutomated safety check: PassMIT
Measure Startup RequestsTriliumNext/Trilium38k—~1.5kAutomated safety check: PassAGPL-3.0

Similar skills

  • Startup Canvas

    phuryn/pm-skills

    Generate a Startup Canvas combining Product Strategy (9 sections) and Business Model (costs + revenue) for a new product.

    27k GitHub stars~1.6k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Acreadiness Assess

    github/awesome-copilot

    Official

    Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html.

    40k GitHub starsUsed in 1 repo~839 tokens
    Legal & ComplianceAuto-check passed
  • Relsa Severity Assessment

    K-Dense-AI/scientific-agent-skills

    Supports multivariate severity assessment and exploratory endpoint-time score forecasting for laboratory animal studies using the RELSA (RELative Severity Assessment) score and ARIMA-based foRcast…

    48k GitHub starsUsed in 1 repo~5.2k tokens
    Data & AnalyticsAuto-check: notes
  • Claude Code Skill Assessment

    luongnv89/claude-howto

    Runs a quick or deep quiz on Claude Code skills, scores ten feature areas and generates a personalized learning path with prioritized next steps.

    42k GitHub stars~5.5k tokensUpdated 10 days ago
    EducationAuto-check passed
  • Measure Startup Requests

    TriliumNext/Trilium

    A skill your agent uses when measuring what the Trilium client loads at startup — "what loads at boot?", "did this change reduce the startup bundle?", "is <dependency lazy?", or any before/after…

    38k GitHub stars~1.5k tokensUpdated today
    Testing & QAAuto-check passed
  • Recommend

    agenticnotetaking/arscontexta

    Get research-backed architecture advice for your knowledge system.

    3.5k GitHub stars~5.1k tokensUpdated 7 mo ago
    Auto-check passed

More from davepoon/buildwithclaude

All 247 skills in this repo
  • iOS Hig Design Guide

    davepoon/buildwithclaude

    Build, update, and apply iOS design specifications using Apple Human Interface Guidelines (HIG) source data.

    3.6k GitHub stars~735 tokensUpdated yesterday
    Auto-check passed
  • Video Downloader

    davepoon/buildwithclaude

    Download YouTube videos with customizable quality and format options.

    3.6k GitHub starsUsed in 1 repo~871 tokens
    Auto-check passed
  • Qwen Vision

    davepoon/buildwithclaude

    A skill your agent uses when the user asks to "analyze video", "watch this video", "what happens in this video", "describe this clip", "review this footage", "classify these videos", "compare…

    3.6k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Atlas Cloud Media

    davepoon/buildwithclaude

    Discover Atlas Cloud image and video models, inspect their live schemas, and submit one confirmed media generation request with bounded GET polling.

    3.6k GitHub stars~852 tokensUpdated yesterday
    Auto-check passed
  • Browser Extension Launch

    davepoon/buildwithclaude

    面向没有编程经验的用户,把想法做成可试用的浏览器插件,并完成检查、商店材料、审核提交和上线验证;也用于继续已有插件、排错和发布新版。用户说“帮我做个插件”“把插件上架”“继续我的插件”时使用。普通网站开发、仅查询插件知识不触发。

    3.6k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Slack Gif Creator

    davepoon/buildwithclaude

    Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives.

    3.6k GitHub starsUsed in 12 repos~4.3k tokens
    Auto-check passed

Questions about Whats Next

What does Whats Next do?

Assesses the current state of the startup project and recommends what to focus on next. Whats Next is an agent skill from davepoon/buildwithclaude. Assesses the current state of the startup project and recommends what to focus on next.

When should I use Whats Next?

Whats Next fits situations like: there is a need; A question from the user to understand what the next steps are; what to focus on next.

How do I install Whats Next in Claude Code?

Run `npx skills add davepoon/buildwithclaude --skill whats-next -a claude-code`. Or copy the skill folder (plugins/startup-superpowers/skills/whats-next in davepoon/buildwithclaude) into .claude/skills/whats-next in your project. Claude Code loads it when a task matches its description.

How do I install Whats Next in Codex?

Run `npx skills add davepoon/buildwithclaude --skill whats-next -a codex`. Or copy the skill folder (plugins/startup-superpowers/skills/whats-next in davepoon/buildwithclaude) into .agents/skills/whats-next in your project. Codex loads it when a task matches its description.

Can I use Whats Next 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 davepoon/buildwithclaude --skill whats-next -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/whats-next, .gemini/skills/whats-next, .github/skills/whats-next and .opencode/skills/whats-next in your project.

What does Whats Next need to run?

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

Does Whats Next 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 Whats Next 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 Whats Next use?

Whats Next 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 Whats Next use?

About 1.7k tokens (SKILL.md is roughly 6.9k 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 9.4k tokens, read only when the agent opens those files.

What are the alternatives to Whats Next?

Skills that share tags, products or a category with Whats Next: Startup Canvas (phuryn/pm-skills, 27k stars), Acreadiness Assess (github/awesome-copilot, 40k stars), Relsa Severity Assessment (K-Dense-AI/scientific-agent-skills, 48k stars) and Claude Code Skill Assessment (luongnv89/claude-howto, 42k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Whats Next?

davepoon (a GitHub user) maintains it in davepoon/buildwithclaude, which has 3,610 GitHub stars. The repository holds 247 skills in this directory. The repository was last updated on October 9, 2026.

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