plugins/startup-superpowers/skills/whats-next/SKILL.md
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.
npx skillsauth add davepoon/buildwithclaude whats-nextInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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.
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.
startup/ existsThe 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
startup/ exists and plan.md is presentStart with a quick orientation. Only escalate to a full reassessment if the plan needs structural changes.
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:
plan.md): the ## Current Focus — the milestone-level thing the project is working toward.## 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.
Use your judgment. These are signals, not a checklist — weigh them in context:
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.
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.mdstartup/plan.md.md files in startup/hypotheses/ (if any).md files in startup/competitors/ (if any).md files in startup/interview-scripts/ (if any).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:
- [ ] to - [x])## Current Focus section## Steps section## Log with a ### {YYYY-MM-DD} headinglast_assessed in frontmatter to today's dateRead plan.md before writing.
development
Show drill-me learning progress — topics studied, cards due for review, weakest concepts, and what to study next. Use when the user asks what's due, how their learning is going, or for their drill-me status.
development
Teach the user a topic as an adaptive tutor — retrieval practice, spaced repetition with decay, and persistent memory in ~/.drill-me/. Use when the user wants to learn or be drilled on something, says "drill me on X", "teach me X", or wants to study a topic, a codebase, or a document.
development
Turn any codebase into evidence-grounded Markdown docs plus a machine-readable index.json. Every claim cites its source; never invents deployment steps.
data-ai
Use at the start of any conversation about a startup idea, product validation, founder strategy, or work inside a `startup/` workspace. Establishes file conventions, voice-input handling, subagent dispatch rules, and how to update each artifact safely. Activate before invoking any other startup-superpowers skill.