appdeploy
Deploy web apps with backend APIs, database, and file storage. Use when the user asks to deploy or publish a website or web app and wants a public URL. Uses HTTP API via curl.
65
78%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/appdeploy/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates what the skill does (deploy web apps with specific infrastructure components) and when to use it (when users want to deploy/publish and get a public URL). It uses natural trigger terms, provides implementation detail (curl-based HTTP API), and occupies a distinct niche that minimizes conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete capabilities: 'Deploy web apps with backend APIs, database, and file storage' and specifies the mechanism 'Uses HTTP API via curl'. This covers specific actions and components. | 3 / 3 |
Completeness | Clearly answers both what ('Deploy web apps with backend APIs, database, and file storage') and when ('Use when the user asks to deploy or publish a website or web app and wants a public URL'). Explicit 'Use when...' clause is present. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'deploy', 'publish', 'website', 'web app', 'public URL'. These are all terms a user would naturally use when requesting deployment. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of deployment, public URL, backend APIs, database, and file storage creates a clear niche. The mention of 'curl' and 'HTTP API' further distinguishes it from general web development or coding skills. Unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 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.
The skill provides actionable, executable guidance with concrete curl commands and clear API structure, which is its strongest aspect. However, it suffers from poor progressive disclosure — all tool parameter documentation is inlined into a single large file rather than being split into a reference document. The workflow section also lacks error recovery and validation feedback loops, which are important for deployment operations that can fail.
Suggestions
Move the detailed tool parameter documentation into a separate REFERENCE.md or TOOLS.md file, keeping only the workflow-critical tools (deploy_app, get_deploy_instructions, get_app_status) summarized in the main SKILL.md.
Add explicit error handling and feedback loops to the workflow: e.g., 'If get_app_status returns failed, read error logs, fix issues, and redeploy' with a concrete retry pattern.
Remove the boilerplate Limitations section at the bottom — these are generic guardrails Claude already knows, wasting tokens.
Consolidate the 'When to Use' section to 2-3 bullet points; several entries are redundant (e.g., 'deploying an app' and 'publishing a website' and 'make this live' all mean the same thing).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes verbose parameter documentation that could be in a separate reference file. The full parameter listings for every tool (especially src_glob, src_grep, src_read) bloat the main skill file significantly. Some descriptions are redundant (e.g., explaining what 'deploy' means). | 2 / 3 |
Actionability | Provides fully executable curl commands with exact endpoints, headers, and JSON-RPC payload structure. The setup flow includes concrete API calls with example responses, and the credential storage format is explicit and copy-paste ready. | 3 / 3 |
Workflow Clarity | The workflow lists a clear sequence (get instructions → get template → deploy → check status), but lacks explicit validation/feedback loops. There's no guidance on what to do if deployment fails, no error recovery steps after get_app_status returns 'failed', and no explicit checkpoint between steps. | 2 / 3 |
Progressive Disclosure | Everything is in a single monolithic file with no references to external files. The detailed parameter documentation for 13 tools should be in a separate reference file. The main SKILL.md should be a concise overview pointing to detailed API reference docs, but instead it's a wall of tool specifications. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
fe8351e
- 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.