appfactory-builder
Build and deploy production apps using AppFactory's 7 pipelines (websites, mobile, dApps, AI agents, plugins, mini apps, bots). One prompt → live URL.
Install with Tessl CLI
npx tessl i github:NeverSight/skills_feed --skill appfactory-builderOverall
score
61%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
43%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description excels at specificity by naming concrete deliverables and the unique '7 pipelines' framework. However, it critically lacks explicit trigger guidance ('Use when...'), which caps its usefulness for skill selection. The product-specific 'AppFactory' term may not match natural user language.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user wants to quickly deploy a web app, mobile app, bot, or AI agent from a single prompt'
Include natural user phrases such as 'create a website', 'build an app', 'deploy to production', 'get a live URL', 'no-code deployment'
Clarify what distinguishes this from general web/app development skills - emphasize the one-prompt-to-deployment speed or AppFactory-specific context
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Build and deploy production apps' with 7 distinct pipeline types (websites, mobile, dApps, AI agents, plugins, mini apps, bots) and a clear outcome 'One prompt → live URL'. | 3 / 3 |
Completeness | Clearly answers 'what' (build/deploy apps via 7 pipelines) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Contains relevant keywords like 'websites', 'mobile', 'dApps', 'AI agents', 'plugins', 'bots', 'deploy', 'apps', but 'AppFactory' is product-specific jargon. Missing common variations users might say like 'web app', 'build app', 'create website', 'launch', 'host'. | 2 / 3 |
Distinctiveness Conflict Risk | The AppFactory branding and '7 pipelines' concept provide some distinctiveness, but terms like 'websites', 'mobile', 'AI agents', 'bots' are broad and could overlap with other web development, mobile development, or bot-building skills. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable overview of AppFactory's capabilities with good structure and clear navigation to detailed pipeline docs. However, it's weakened by marketing content (token links, social handles), missing validation steps in workflows, and over-reliance on external files for actionable guidance rather than providing inline executable examples for each pipeline.
Suggestions
Remove marketing content (token links, social media handles, showcase submission process) that doesn't help Claude build apps
Add validation checkpoints: verify local build works before deploy, check deployment succeeded, handle common errors
Include minimal inline executable examples for each pipeline type rather than just 'Follow CLAUDE.md' references
Add error handling guidance: what to do when npm run build fails, when vercel deploy fails, common issues per pipeline
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful information but includes unnecessary sections like marketing links, token information, social media handles, and verbose contributing guidelines that don't help Claude execute the core task. The design system and architecture sections add bulk without being essential for building. | 2 / 3 |
Actionability | Provides concrete bash commands for cloning, creating projects, and deploying, but relies heavily on external CLAUDE.md files for actual pipeline execution ('Follow app-factory/CLAUDE.md'). The quick start is actionable for websites but other pipelines lack inline executable guidance. | 2 / 3 |
Workflow Clarity | Steps are numbered and sequenced for the basic flow (clone → pick pipeline → build → deploy), but lacks validation checkpoints. No verification steps between build and deploy, no error handling guidance, and no feedback loops for when builds fail. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections, a summary table upfront, and appropriate references to pipeline-specific CLAUDE.md files for detailed instructions. Navigation is clear and references are one level deep. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
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.