improve-app
Guided journey from a shipped app that works but feels rough to a product that fits the job, flows without friction, reads clearly, and persuades honestly. Orchestrates nine skills phase by phase - jobs-to-be-done, ux-heuristics, design-everyday-things, refactoring-ui, microinteractions, made-to-stick, influence-psychology, high-perf-browser, steve-jobs-design-review - asking the user questions at every decision point and recording results in the project docs/ folder (CUSTOMER.md, DESIGN.md, POSITIONING.md, IMPROVE-APP-PLAN.md) so the journey resumes across sessions. Use when the user wants to
npx skills add wondelai/skills --skill improve-app --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Guides an interactive, resumable enhancement process for an app that already works but feels rough. It orchestrates nine phase-specific skills (jobs-to-be-done, ux-heuristics, design-everyday-things, refactoring-ui, microinteractions, made-to-stick, influence-psychology, high-perf-browser, steve-jobs-design-review) to fix user experience, copy, and overall product feel. The agent asks questions at decision points and records results in project docs (CUSTOMER.md, DESIGN.md, POSITIONING.md, IMPROVE-APP-PLAN.md) so progress persists across sessions. Phase progression depends on user-confirmed decisions and a tracker-based plan.
How it works
- On first run, Intake gathers app context and builds docs/IMPROVE-APP-PLAN.md with phase statuses. The journey can resume later if a tracker exists.
- Each phase declares its purpose, invokes a corresponding skill by slug (e.g., jobs-to-be-done, ux-heuristics), and asks the user to decide with concrete options.
- The skill invocation follows a fixed flow: announce phase, present decisions, invoke the phase skill, capture decisions, and draft artifact content for sign-off.
- Artifacts (CUSTOMER.md, DESIGN.md, POSITIONING.md, etc.) are extended rather than overwritten, using uppercase files in docs/ and checkbox/list-style entries per templates.
- Evidence and experiments are recorded in docs/EXPERIMENTS.md; changes require a pre-commit metric and validated findings before shipping.
When to use it
Use when the user wants to fix a clunky product, cut UX friction, sharpen in-app copy and prompts, or improve overall product feel while keeping the app functional and resumable across sessions. Do not use for code, tests, or production hardening; use alternative skills for those scopes.
What it can touch
- Invokes phase-specific skills by slug: jobs-to-be-done, ux-heuristics, design-everyday-things, refactoring-ui, microinteractions, made-to-stick, influence-psychology, high-perf-browser, steve-jobs-design-review.
- Writes to docs/ files: CUSTOMER.md, DESIGN.md, POSITIONING.md, IMPROVE-APP-PLAN.md, PRODUCT.md, EXPERIMENTS.md as described in each phase.
Caveats
- The process relies on user confirmation to proceed through phases and to sign off artifacts.
- Phase gates and phase-skipping heuristics are defined per phase; phases may be deferred but not skipped at Phase 1.
- The approach is non-code and non-production-hardening focused; it integrates with a tracker and project docs for continuity.
# Improve an App The app already ships and works — users, screens, a real flow — but the experience feels rough where it should feel effortless. Across nine phases this journey fixes what users feel, in evidence order: re-anchor on the job, remove friction, polish the look and the moments, sharpen the words, persuade honestly, and end with a review brutal enough to cut. It is interactive (the agent asks before deciding) and resumable (state lives in `docs/`). Code-level causes route out to the code journeys — this pass fixes the product experience. ## Core Principle **Fix what users feel, in evidence order: re-anchor on the job the app is hired for, remove friction before polish, sharpen the words, persuade honestly, and end with a review brutal enough to cut.** A prettier screen on a confusing flow loses users at the same rate — the order of the phases is the whole game. This skill sequences the phases, asks the decision questions, and records what you decide. The nine constituent skills carry the method — invoke them rather than improvising their frameworks. ## Journey Map | Phase | Skill | Question it answers | Artifact | |---|---|---|---| | 1 | jobs-to-be-done | What job is the
- Core Principle
- Journey Map
- Operating Rules
- Intake
- Phases
- Phase 1 — Re-anchor on the job the app is hired for (jobs-to-be-done) — GATE
- Phase 2 — Remove the friction that makes users think (ux-heuristics)
- Phase 3 — Design out the errors (design-everyday-things)
- Phase 4 — Make it look as clear as it works (refactoring-ui)
- Phase 5 — Make every action feel alive (microinteractions)
- Phase 6 — Sharpen the in-app words (made-to-stick)
- Phase 7 — Persuade honestly at the decision points (influence-psychology)
- Phase 8 — Make it feel fast where users touch it (high-perf-browser)
- Phase 9 — Submit it to a brutal, honest review (steve-jobs-design-review)
What does the improve-app skill do?
Guided journey from a shipped app that works but feels rough to a product that fits the job, flows without friction, reads clearly, and persuades honestly. Orchestrates nine skills phase by phase - jobs-to-be-done, ux-heuristics, design-everyday-things, refactoring-ui, microinteractions, made-to-stick, influence-psychology, high-perf-browser, steve-jobs-design-review - asking the user questions at every decision point and recording results in the project docs/ folder (CUSTOMER.md, DESIGN.md, POSITIONING.md, IMPROVE-APP-PLAN.md) so the journey resumes across sessions. Use when the user wants to
How do I install it?
Run `npx skills add wondelai/skills --skill improve-app --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From wondelai/skills, a repository with 1,835 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.