grow-website

Guided journey from a website with traffic it under-converts to a research-driven growth engine that captures more leads, persuades more buyers, sells a sharper offer, and earns referrals. Orchestrates eight skills phase by phase - cro-methodology, scorecard-marketing, storybrand-messaging, made-to-stick, influence-psychology, hundred-million-offers, contagious, one-page-marketing - asking the user questions at every decision point and recording results in the project docs/ folder (WEBSITE.md, OFFER.md, MARKETING.md, GROW-WEBSITE-PLAN.md) so the journey resumes across sessions. Use when the user wants to raise conversion on a site that already has traffic, capture more leads, sharpen a weak offer, add referral loops, or says 'my site gets visitors but nobody buys'. If a broken funnel or usability friction is the real blocker, run improve-website first; if there is no site yet, use create-website; for one leaking flow, conversion-optimization. For one framework in isolation, invoke that skill directly.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable 8-phase orchestrator with explicit workflow gates, validation feedback loops, and a clean one-level reference for artifact templates. Its main weakness is conciseness: the per-phase briefs re-explain known marketing frameworks and factoids that Claude already knows.

Suggestions

Trim the per-phase 'Brief (fallback)' sections to only the non-obvious method steps, dropping restatements of well-known framework acronyms (SB7, SUCCESs, STEPPS, Cialdini's seven principles) and known factoids (retention cost ratios, the 3% ready-to-buy figure) that Claude already knows.

Consider moving the full per-phase methodology into a references/ file and keeping SKILL.md phases to Purpose/Invoke/Decide/Artifact/Done-when, which would tighten conciseness and improve progressive_disclosure.

Add a one-line explicit validation/verification reminder in batch write steps (e.g. re-read the extended docs/ file after writing to confirm section preservation), to make the existing artifact-discipline checkpoint even more concrete.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and operational (Purpose/Brief/Invoke/Decide/Artifact/Done-when per phase), but each phase's Brief re-summarizes a framework Claude already knows (SB7, SUCCESs, Cialdini's seven principles, STEPPS, the Value Equation, the 3x3 grid) plus known factoids (e.g. 'retention costs 5-25x less than acquisition'), so it could be tightened.	3 / 5
Actionability	Highly concrete and executable for an instruction skill: each phase names the exact skill to invoke, what to ask for, specific decisions with options and a recommendation, exact docs/ files and section headings to extend, the install fallback command ('npx skills add wondelai/skills/<slug> --global'), and per-phase done-when criteria.	5 / 5
Workflow Clarity	A clear 8-phase sequence with explicit checkpoints and feedback loops — resume-first rule, intake-on-first-run gate, GATE phases that may defer but never skip, 'awaiting-evidence' status for missing evidence, sign-off-before-write, per-phase done-when gates, and a final exit checklist.	5 / 5
Progressive Disclosure	Well-organized sections (Journey Map, Operating Rules, Intake, Phases, Optional Phases, Common Mistakes, Completing) with a clearly signaled one-level-deep reference (references/artifact-templates.md) that holds the artifact skeletons, but the body inlines all eight phase briefs and methodology, leaving a minor organization gap versus splitting more detail out.	4 / 5
	Total	17 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that names concrete capabilities, constituent skills, and artifacts, supplies an explicit 'Use when' trigger clause with natural user phrasing, and proactively disambiguates against sibling skills. Its only weak spot is that the named actions are outcome-level rather than granular operations.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions and named artifacts ('captures more leads, persuades more buyers, sells a sharper offer, and earns referrals', 'Orchestrates eight skills phase by phase', named docs in docs/), but the actions are framed more as outcomes than granular operations, leaving a minor gap versus fully comprehensive concrete actions.	4 / 5
Completeness	Explicitly answers both what (a guided 8-phase growth-engine journey recording state in docs/) and when (an explicit 'Use when the user wants to raise conversion on a site that already has traffic...' clause with concrete triggers), matching the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say — 'raise conversion on a site that already has traffic', 'capture more leads', 'sharpen a weak offer', 'add referral loops', and the verbatim quote 'my site gets visitors but nobody buys' — with synonym coverage and clear disambiguation terms.	5 / 5
Distinctiveness Conflict Risk	Clear niche (a site with traffic that under-converts, wanting a multi-phase growth engine) with explicit routing away from siblings — 'run improve-website first', 'use create-website', 'for one leaking flow, conversion-optimization', 'For one framework in isolation, invoke that skill directly' — minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: wondelai/skills
Path: grow-website/SKILL.md
Commit: eade5d1

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.