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.
48
51%
Does it follow best practices?
Impact
—
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 concise and specific about capabilities, clearly naming the tool (AppFactory) and its 7 pipeline types with a distinctive value proposition ('One prompt → live URL'). However, it lacks an explicit 'Use when...' clause, which weakens its completeness for skill selection, and some trigger terms could be more aligned with natural user language.
Suggestions
Add a 'Use when...' clause such as 'Use when the user wants to build, deploy, or launch a website, mobile app, dApp, AI agent, plugin, mini app, or bot from a single prompt.'
Include natural user-facing synonyms like 'web app', 'create an app', 'launch a site', 'host', or 'ship' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Build and deploy production apps' across 7 named pipelines (websites, mobile, dApps, AI agents, plugins, mini apps, bots), and specifies the outcome 'One prompt → live URL.' | 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, capping this at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'websites', 'mobile', 'dApps', 'AI agents', 'plugins', 'mini apps', 'bots', and 'deploy', but misses common user phrasings like 'web app', 'build a site', 'launch', 'host', or 'create an app'. The term 'AppFactory' is product-specific jargon users may not naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'AppFactory' and its specific 7 pipelines creates a clear niche. The 'One prompt → live URL' differentiator and the enumerated pipeline types make it 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.
This skill provides a reasonable overview of AppFactory's pipelines with a functional Quick Start for the website pipeline, but suffers from significant bloat with promotional content (token links, social media, contributing guidelines) that doesn't help Claude build apps. Most pipelines lack concrete executable guidance, deferring to CLAUDE.md files that aren't included in the bundle. The skill reads more like a project README than a focused skill for Claude.
Suggestions
Remove promotional content (token links, social media handles, contributing guidelines, OpenClaw heartbeat section) — these don't help Claude build apps and waste ~40% of the token budget.
Add concrete executable steps for at least 2-3 more pipelines instead of just 'Follow CLAUDE.md' — or include those CLAUDE.md files as bundle files.
Add explicit validation checkpoints: verify build succeeds (`npm run build` exit code), verify local server starts before deploying, and add error recovery steps for common failures.
Move the Design System, Architecture, and Contributing sections to separate referenced files to keep the main skill focused on actionable build instructions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Significant bloat: the 'Contributing Back' section (~30 lines), 'For OpenClaw Agents' section, 'Links' section with token/swap links, and design system details are not actionable build instructions. The pipeline details section repeats information already in the table. Marketing language ('Ship something', 'Bloomberg terminal meets Apple hardware') wastes tokens. Much of this content is promotional rather than instructional. | 1 / 3 |
Actionability | The Quick Start provides concrete bash commands for cloning, scaffolding a Next.js project, and deploying to Vercel. However, most pipelines just say 'Follow <pipeline>/CLAUDE.md' without providing the actual instructions. The website pipeline is the only one with executable steps; the rest are vague descriptions of what gets generated rather than how to use it. | 2 / 3 |
Workflow Clarity | There's a numbered sequence (clone → pick pipeline → build → deploy) which is clear for the website pipeline. However, there are no validation checkpoints — no 'verify the build succeeded before deploying' step, no error recovery guidance, and the LOCAL_RUN_PROOF_GATE is mentioned in Architecture but never integrated into the workflow steps. For a multi-pipeline build system, missing validation caps this at 2. | 2 / 3 |
Progressive Disclosure | The skill references per-pipeline CLAUDE.md files for detailed instructions, which is good progressive disclosure in principle. However, no bundle files are provided, so we can't verify these references exist. The main file itself is monolithic — the Contributing Back, Architecture, OpenClaw Agents, and Design System sections could be separate files. Inline content that should be split keeps this at 2. | 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
e8584ad
- 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.