ntfy-notifications
Self-hosted push notifications with ntfy — publishing, authentication, priorities, and integration patterns for scripts and monitoring
68
59%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./ntfy-notifications/SKILL.mdQuality
Discovery
40%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 identifies a clear, specific tool (ntfy) which helps with distinctiveness, but lacks explicit trigger guidance and uses category labels rather than concrete actions. The absence of a 'Use when...' clause significantly weakens its utility for skill selection among many options.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user mentions ntfy, self-hosted notifications, or wants to send push alerts from scripts'
Replace abstract categories with concrete actions: 'Send push notifications via ntfy, configure authentication tokens, set message priorities' instead of 'publishing, authentication, priorities'
Include common user phrasings like 'send alerts', 'notify me', 'push messages' to improve trigger term coverage
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (ntfy push notifications) and lists some capabilities (publishing, authentication, priorities, integration patterns), but these are somewhat abstract categories rather than concrete actions like 'send notifications' or 'configure authentication tokens'. | 2 / 3 |
Completeness | Describes what the skill covers (ntfy notifications with various features) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'ntfy', 'push notifications', 'monitoring', and 'scripts' which are relevant keywords, but misses common variations users might say like 'alerts', 'notify', 'send message', or 'notification service'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific to 'ntfy' as a self-hosted solution, which creates a clear niche. The explicit mention of 'ntfy' makes it unlikely to conflict with other notification or monitoring skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, actionable skill with excellent concrete examples and efficient token usage. The main weaknesses are the monolithic structure that could benefit from splitting into referenced files, and the lack of explicit validation steps in multi-step workflows like Docker deployment and user setup.
Suggestions
Add validation checkpoints to Docker deployment section (e.g., 'Verify server is running: curl https://ntfy.example.com/health' after starting container)
Consider splitting integration patterns and Docker deployment into separate referenced files (e.g., INTEGRATIONS.md, DOCKER.md) to improve progressive disclosure
Add a verification step after user/ACL commands (e.g., 'Verify with: docker exec ntfy ntfy access USERNAME' after granting access)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, providing direct examples without explaining what ntfy is beyond a single sentence. Every section delivers actionable content without padding or explaining concepts Claude would already know. | 3 / 3 |
Actionability | All examples are fully executable curl commands and bash scripts that can be copy-pasted directly. The docker-compose.yml, server.yml, and integration scripts are complete and ready to use. | 3 / 3 |
Workflow Clarity | While individual commands are clear, multi-step processes like Docker deployment lack explicit validation checkpoints. The phone setup section has numbered steps but no verification that each step succeeded before proceeding. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but this is a lengthy monolithic document (~200 lines) that could benefit from splitting advanced topics (Docker deployment, integration patterns) into separate referenced files. | 2 / 3 |
Total | 10 / 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
- ddnetters/homelab-agent-skills
- Commit
87d2278
- 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.