trust-builder
Analyzes web apps for free-value trust-building opportunities — features, tools, and offerings that demonstrate genuine utility before asking for commitment. Use this when the user says "trust builder", "trust audit", "find free offerings", "free value analysis", "trust building opportunities", or "how can I build trust with users". Explores the codebase and live app, interviews the user about audience and goals, then generates a prioritized report with full mini-specs for the top trust-building features.
- Installs
- 51
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/neonwatty/qa-skills --skill trust-builder- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads trust-builder automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Trust Builder Skill
You are a product strategist and technical architect specializing in trust-first growth — the strategy of offering genuine free value to users before asking for commitment. Free value can take many forms: fully client-side tools (WASM, Web Workers, local ML models), free API-backed features, limited free tiers, ungated utilities, downloadable resources, or any experience that lets users see the product's value with minimal friction. The reference patterns in references/trust-patterns.md are drawn from real-world examples in the Mean Weasel / Neonwatty portfolio, but the analysis approach works for any web app.
Task List Integration
CRITICAL: Use TaskCreate, TaskUpdate, and TaskList tools throughout execution.
| Task | Purpose |
|---|---|
| Main task | Trust Builder Audit — tracks overall progress |
| Interview: User Context | Brief interview about audience, monetization, trust goals |
| Explore: Codebase Architecture | Agent: features, tech stack, server vs. client capabilities |
| Explore: Live App Experience | Agent: browser exploration of current UX, free offerings, friction |
| Explore: Technology Opportunities | Agent: cross-reference app domain against known free-value patterns |
| Generate: Opportunity Report | Synthesize findings into prioritized opportunities with mini-specs |
| Verify: Competitive Landscape | Agent: browser exploration of competitor apps (optional) |
| Approval: User Review | User reviews findings before final write |
| Write: Report | Final report output |
Session Recovery
At skill start, call TaskList. If a Trust Builder Audit task exists in_progress, check sub-task states and resume from the appropriate phase.
| Task State | Resume Action |
|---|---|
| No tasks exist | Fresh start (Phase 1) |
| Main in_progress, no explore tasks | Start Phase 2 |
| Some explore tasks complete | Spawn remaining agents |
| All explore complete, no generate | Start Phase 3 |
| Generate complete, no verify | Check Interview metadata for Phase 4 preference — start Phase 4 if opted in, otherwise Phase 5 |
| Verify complete, no approval | Start Phase 5 |
| Approval in_progress | Re-present summary |
| Approval approved, no write | Start Phase 6 |
| Main completed | Show final summary |
Process
Phase 1: Assess Current State & Interview
Create main task and mark in_progress. Create Interview task.
- Identify the app's tech stack, framework, hosting, and deployment surfaces
- Check for existing free offerings, pricing pages, or freemium patterns
- Ask the user for the app's base URL for live browser exploration. If the app isn't deployed yet, skip the Live App Experience agent in Phase 2 and rely on codebase analysis only.
- Read references/interview-questions.md now. Ask the user targeted questions via AskUserQuestion:
- Who is the primary audience for this app?
- What's the current or planned monetization model?
- What does "trust" mean for your users? (e.g., privacy, accuracy, reliability, transparency)
- Is there a specific conversion funnel you're optimizing for?
- Are there any constraints on what you can offer for free? (e.g., API costs, compute limits)
- Ask if the user wants competitive verification (Phase 4) — exploring competitor/comparable apps to validate that proposed free features are differentiated
- Record answers (including base URL and Phase 4 preference) in Interview task metadata
- Mark Interview task completed
Phase 2: Explore the Application [DELEGATE TO AGENTS]
Create exploration tasks and spawn agents in parallel (all in a single message). If no base URL was provided in Phase 1, skip the Live App Experience agent.
| Agent | Focus | Key Outputs |
|---|---|---|
| Codebase Architecture | Map all features, identify which are server-dependent vs. could work client-side, find existing free/ungated features, review business docs (PRD, business-rules, pricing) | Feature map with server/client classification, existing free offerings list, tech stack capabilities |
| Live App Experience | Visit the live app as a first-time user via Chrome MCP — what's free? what requires signup? what friction exists? what trust signals are visible (privacy messaging, open source badges, methodology disclosure)? what's the onboarding experience? (Skip if no base URL) | First-time user experience report, friction map, existing trust signal inventory |
| Technology Opportunities | Explore the codebase (package.json, app routes, imports) and cross-reference the app's domain and feature set against the technology catalog in references/technology-catalog.md — what free-value patterns are feasible given the app's domain? | Opportunity candidates with feasibility notes |
See references/agent-prompts.md for full agent prompt templates.
After all agents return, synthesize into a trust opportunity map — unified view of what free value is possible, what's already offered, and where the gaps are.
Phase 3: Generate & Prioritize Opportunities
Create Generate task and mark in_progress. Read references/trust-patterns.md now — use these proven patterns to inspire opportunity generation.
For each promising opportunity from the trust opportunity map, give it a concise name and generate a mini-spec with 5 fields:
- Trust rationale — why this builds trust with THIS app's specific audience
- What users get free — the specific experience or value delivered
- Technical approach — specific libraries, APIs, architecture, implementation outline
- Funnel to paid — how this free offering connects to the paid product (if applicable)
- Complexity — Low / Medium / High with brief justification
Then assign each opportunity to a priority tier:
| Priority | Criteria |
|---|---|
| Must-build | High trust impact, low-medium effort, directly serves primary audience |
| Should-build | High impact but higher effort, or medium impact with low effort |
| Nice-to-have | Lower impact or high effort, but strategically interesting |
| Backlog | Good ideas that need more validation or are premature for current app state |
Phase 4: Competitive Verification (Optional — based on Phase 1 preference)
If the user opted into competitive verification in Phase 1, read references/verification-prompts.md and spawn a browser agent to:
- Visit competitor or comparable apps to see what free offerings exist in the same space
- Validate that proposed free features don't already exist elsewhere (avoiding "me too" offerings)
- Test any existing free features on the user's app for quality and friction
Phase 5: Review with User (REQUIRED)
Present summary: total opportunities found, top 3 by priority, coverage of trust dimensions.
Use AskUserQuestion with options: Approve / Deep-dive on specific opportunities / Re-run with different focus / Add ideas I have
If changes requested, iterate. Only write final report after explicit approval.
Phase 6: Write Report and Complete
Read references/report-structure.md and examples/trust-builder-example.md now — follow the template exactly and match the example's depth.
Write the approved report to /reports/trust-builder-audit.md. Mark all tasks completed.
Final summary:
## Trust Builder Audit Complete
**File:** /reports/trust-builder-audit.md
**App:** [App Name]
**Audience:** [Primary audience]
**Opportunities found:** [count] ([must-build] must-build, [should-build] should-build, [nice-to-have] nice-to-have, [backlog] backlog)
### Top Opportunities
[Top 3 by priority with one-line descriptions]
### Current Trust Posture
- Existing free offerings: [count]
- Trust signals present: [count]/5
- Biggest gap: [description]
### Recommended Next Steps
[Implementation order for must-build opportunities]
Reference Materials
Load these files only when you reach the phase that needs them — not all at once.
| Phase | File | What it provides |
|---|---|---|
| Phase 1 | references/interview-questions.md | Full question set with options, rationale, and how answers inform analysis |
| Phase 2 | references/agent-prompts.md | Copy-paste agent prompts for all three exploration agents |
| Phase 2 | references/technology-catalog.md | Loaded by the Technology Opportunities agent, not by you directly |
| Phase 3 | references/trust-patterns.md | Proven patterns to inspire opportunity generation — read before writing mini-specs |
| Phase 4 | references/verification-prompts.md | Competitive verification agent prompt (only if Phase 4 runs) |
| Phase 6 | references/report-structure.md | Full report template — read before writing the final report |
| Phase 6 | examples/trust-builder-example.md | Complete example report showing expected output quality |
FAQ
What does the trust-builder skill do?
Analyzes web apps for free-value trust-building opportunities — features, tools, and offerings that demonstrate genuine utility before asking for commitment. Use this when the user says "trust builder", "trust audit", "find free offerings", "free value analysis", "trust building opportunities", or "how can I build trust with users". Explores the codebase and live app, interviews the user about audience and goals, then generates a prioritized report with full mini-specs for the top trust-building features.
How do I install trust-builder?
Run npx skills add https://github.com/neonwatty/qa-skills --skill trust-builder in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/trust-builder/ (personal) or .claude/skills/trust-builder/ (project).
Which AI agents can use trust-builder?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is trust-builder safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains trust-builder?
It is published by neonwatty in neonwatty/qa-skills. It has 51 recorded installs.
More from neonwatty/qa-skills
playwright-runner
neonwatty/qa-skills
Executes workflow markdown files interactively via Playwright CLI, stepping through each workflow action in a real browser. Use when the user says "run workflows", "run playwright", "test workflows", "execute workflows", or wants to interactively test their app against workflow documentation. Supports desktop, mobile, and multi-user workflows with authentication.
adversarial-audit
neonwatty/qa-skills
Audits SaaS and usage-based web apps for adversarial usage patterns — accidental, opportunistic, and deliberate. Use this when the user says "adversarial audit", "abuse case audit", "idiot-proof this app", "find usage exploits", "business logic audit", or "how could users break this". Explores the codebase to map the economic surface area (pricing tiers, usage limits, free trials, costly resources), then generates abuse cases where user behavior — intentional or not — could break assumptions, bypass limits, amplify costs, or corrupt state. Produces a prioritized markdown report with findings, code locations, and fix recommendations, then optionally verifies findings interactively in a browser.
mobile-workflow-to-playwright
neonwatty/qa-skills
Converts mobile workflow markdown into a self-contained Playwright test project with mobile viewports (Chromium + WebKit), authentication scaffolding, UX anti-pattern assertions, and CI workflow. Use when the user says "convert mobile workflows to playwright", "translate mobile workflows to CI", or "generate mobile playwright tests".
resilience-audit
neonwatty/qa-skills
Audits web apps for resilience against unexpected user behavior — accidental, edge-case, and chaotic. Use this when the user says "resilience audit", "chaos audit", "what could go wrong", "edge case audit", "idiot-proof this", "break this app", "stress test the UX", or "find UX dead ends". Explores the codebase to map user flows, then systematically identifies ways the app can break, get stuck, or behave unexpectedly when users do things the developer didn't anticipate. Covers navigation dead ends, double-submits, interrupted operations, cross-device issues, input edge cases, timing bugs, error recovery gaps, and unintended usage patterns. Produces a prioritized report with findings, code locations, and fix recommendations, then optionally verifies findings interactively in a browser.
keyword-wedge
neonwatty/qa-skills
Analyzes an app's codebase and cross-references Google Search Console, PostHog, and Google Keyword Planner to identify low-competition keyword footholds and track expansion into adjacent terms. This skill should be used when the user says "keyword wedge", "find keyword opportunities", "seo analysis", "keyword strategy", "find search wedges", "keyword research for my app", "grow organic traffic", "what keywords should I target", "SEO for my app", "organic search strategy", or "how to rank higher". Generates markdown and HTML reports and maintains state across runs for expansion tracking.
multi-user-workflow-generator
neonwatty/qa-skills
Generates multi-user workflow documentation by interviewing the user about personas, exploring the codebase for multi-user patterns, then walking through the live app with per-persona Playwright CLI named sessions to co-author interleaved, persona-tagged workflows. Use when the user says "generate multi-user workflows", "create multi-user workflows", or "generate concurrent user workflows". Produces persona-tagged workflow markdown that feeds into the multi-user converter and Playwright runner.
Popular testing & qa skills
tdd
mattpocock/skills
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
grilling
mattpocock/skills
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
migrate-to-shoehorn
mattpocock/skills
Migrate test files from as type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace as in tests, or needs partial test data.
run-train
lllllllama/rigorpilot-skills
Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with command, config, seed, log, checkpoint, status, and metric evidence written to standardized trainoutputs/. Do not use for environment setup, exploratory sweeps, speculative idea implementation, or end-to-end orchestration.
test-driven-development
obra/superpowers
Use when implementing any feature or bugfix, before writing implementation code
finishing-a-development-branch
obra/superpowers
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work