Deploy sites, configure serverless and edge functions, and verify builds on Netlify. Use when the user mentions: 'deploy preview', 'configure netlify.toml', or 'debug a failed deploy'. Trigger terms: build error, Netlify Functions, deploy logs, deploy preview
77
96%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
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 well-crafted skill description that clearly defines its scope around Netlify deployments and configuration. It provides specific actions, explicit trigger guidance with a 'Use when...' clause, and platform-specific keywords that make it highly distinguishable from other deployment-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Deploy sites', 'configure serverless and edge functions', and 'verify builds on Netlify'. These are distinct, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (deploy sites, configure functions, verify builds) and 'when' (explicit 'Use when...' clause with trigger terms and a separate trigger terms list). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'deploy preview', 'netlify.toml', 'build error', 'Netlify Functions', 'deploy logs', 'failed deploy'. These cover common variations of how users would describe Netlify-related tasks. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Netlify specifically, with platform-specific triggers like 'netlify.toml', 'Netlify Functions', and 'deploy preview'. Unlikely to conflict with generic deployment or other hosting platform skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, actionable Netlify deployment skill that efficiently covers the key workflows: configuration, serverless/edge functions, build troubleshooting, and post-deploy verification. The content is concise, provides executable examples, and includes proper validation checkpoints. The main weakness is that multiple references point to REFERENCE.md and deployment-config.md which are not present in the bundle, leaving some promised content undeliverable.
Suggestions
Ensure REFERENCE.md exists in the bundle with the referenced content (security headers, env var scoping, extended verification scripts, CI-ready function patterns) or inline the most critical pieces.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what Netlify is or how serverless functions work conceptually. Every section delivers specific configuration, commands, or code examples without padding. | 3 / 3 |
Actionability | Provides fully executable code examples (netlify.toml config, TypeScript edge/scheduled functions), specific CLI commands for building and debugging, and concrete curl commands for verification. All examples are copy-paste ready. | 3 / 3 |
Workflow Clarity | The deployment workflow is clearly sequenced (configure → build locally → push → verify → merge) with explicit validation checkpoints: local build with --debug before pushing, curl verification after deploy, and a feedback loop (inspect logs, fix, re-deploy) for failures. | 3 / 3 |
Progressive Disclosure | References to REFERENCE.md and deployment-config.md are well-signaled and one level deep, which is good structure. However, no bundle files were provided, so REFERENCE.md doesn't actually exist, making these references unverifiable. The inline content is appropriately scoped but some sections (security headers, env var scoping, extended verification scripts) are deferred to a non-existent file. | 2 / 3 |
Total | 11 / 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.
cc13aaf
Table of Contents
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.