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.
61
51%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xaxiom/appfactory/appfactory-builder/SKILL.mdQuality
Discovery
67%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 is strong in specificity and distinctiveness, clearly naming the AppFactory platform and its 7 pipeline types with a memorable tagline. However, it lacks an explicit 'Use when...' clause, which is critical for Claude to know when to select this skill, and the trigger terms could better match natural user language patterns.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to create, build, or deploy a website, mobile app, bot, plugin, dApp, AI agent, or mini app, or mentions AppFactory.'
Include more natural user phrasings as trigger terms, such as 'create a website', 'launch an app', 'web app', 'deploy to production', or 'generate a live URL'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and domains: 7 named pipelines (websites, mobile, dApps, AI agents, plugins, mini apps, bots), plus 'build and deploy production apps' and 'One prompt → live URL' which describes a concrete outcome. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (build and deploy apps using AppFactory's pipelines), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes some natural keywords like 'websites', 'mobile', 'bots', 'AI agents', 'deploy', and 'dApps', but misses common user phrasings like 'create a website', 'launch an app', 'web app', or 'hosting'. The term 'AppFactory' is product-specific jargon that users may not naturally use. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'AppFactory' as a specific platform with '7 pipelines' and the 'One prompt → live URL' workflow creates a clear niche that is unlikely to conflict with generic coding or deployment skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill covers a broad set of pipelines with a clear table overview and concrete website pipeline commands, but suffers from significant bloat with promotional content (token links, social media, contributing guidelines) that doesn't help Claude build apps. Most pipelines lack inline actionable guidance, deferring to CLAUDE.md files that aren't provided in the bundle. The workflow lacks validation checkpoints despite involving deployment operations.
Suggestions
Remove promotional content (token launchpad links, social media handles, contributing guidelines, OpenClaw heartbeat section) — these don't help Claude build or deploy apps and waste token budget.
Add inline validation steps to the workflow: verify `npm run build` succeeds before deploying, check `npx vercel` output for errors, confirm the live URL returns 200.
For non-website pipelines, include at least a minimal executable example inline rather than just 'Follow CLAUDE.md' — even 2-3 key commands would make them actionable.
Move the design system, architecture overview, and pipeline details into separate referenced files to keep SKILL.md focused on the quick-start workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Significant bloat: the 'Contributing Back' section (~30 lines), 'For OpenClaw Agents' section, design system details, links to token launchpads, and social media handles are not actionable build instructions. The pipeline details section repeats information already in the table. Much of this content is promotional rather than instructional. | 1 / 3 |
Actionability | The Quick Start provides concrete clone/scaffold/deploy commands, but most pipelines just say 'Follow <pipeline>/CLAUDE.md' without giving any inline executable guidance. The website pipeline has real commands; the others are essentially pointers. Deploy commands are concrete and copy-paste ready. | 2 / 3 |
Workflow Clarity | Steps are numbered and sequenced for the basic clone→build→deploy flow, but there are no validation checkpoints or error recovery steps. The LOCAL_RUN_PROOF_GATE and Ralph QA System are mentioned in the architecture section but never integrated into the actual workflow steps. For a build-and-deploy skill, missing 'verify build succeeded' or 'check deploy status' steps is a gap. | 2 / 3 |
Progressive Disclosure | References to per-pipeline CLAUDE.md files provide one-level-deep navigation, which is good. However, there are no bundle files to support these references, and substantial content that should be in separate files (contributing guidelines, architecture details, design system) is inlined, bloating the main skill file. | 2 / 3 |
Total | 7 / 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.
- Repository
- NeverSight/skills_feed
- Commit
aa009ea
- 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.