ntfy-notifications
Self-hosted push notifications with ntfy — publishing, authentication, priorities, and integration patterns for scripts and monitoring
48
52%
Does it follow best practices?
Impact
—
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 niche (ntfy push notifications) which makes it distinctive, but it lacks concrete action verbs and an explicit 'Use when...' clause. The capability areas listed (publishing, authentication, priorities, integration patterns) read more like a table of contents than actionable descriptions of what the skill enables.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about sending notifications via ntfy, configuring ntfy topics, or integrating ntfy into scripts or monitoring pipelines.'
Replace category labels with concrete actions, e.g., 'Publish messages to ntfy topics, configure token-based authentication, set notification priorities and tags, integrate ntfy into shell scripts and monitoring workflows.'
Include additional natural trigger terms users might say, such as 'alerts', 'notify', 'notification server', or 'webhook notifications'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (ntfy push notifications) and lists some areas (publishing, authentication, priorities, integration patterns), but these are more like categories than concrete actions. It doesn't specify actions like 'send notifications', 'configure authentication tokens', or 'set up monitoring alerts'. | 2 / 3 |
Completeness | Describes what the skill covers (ntfy push notifications with various aspects) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also only moderately clear, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes 'ntfy', 'push notifications', 'monitoring', and 'scripts' which are relevant keywords. However, it misses common variations users might say like 'alerts', 'notify', 'self-hosted notifications', 'webhook', or 'notification server'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'ntfy' specifically makes this highly distinctive. It's unlikely to conflict with other notification or monitoring skills since ntfy is a specific self-hosted tool with a clear niche. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid reference skill with excellent actionability — nearly every section provides executable, copy-paste ready examples covering publishing, auth, deployment, and integration patterns. Its main weaknesses are length (could split into overview + referenced detail files) and lack of explicit workflow sequencing for the deployment/setup process. Some content like the emoji table and phone setup instructions add bulk without proportional value for Claude.
Suggestions
Add an explicit setup workflow sequence (e.g., '1. Deploy with Docker → 2. Create admin user → 3. Verify with `ntfy user list` → 4. Configure ACLs → 5. Generate token → 6. Test with curl') with validation checkpoints after each step.
Split into SKILL.md (overview + publishing + quick integration example) with references to separate files like DEPLOYMENT.md, ACCESS_CONTROL.md, and INTEGRATION_PATTERNS.md.
Trim the emoji/tags table to 3-4 most common entries and link to the full list, and remove the phone setup section which isn't actionable for Claude.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with concrete examples, but includes some unnecessary content Claude already knows (e.g., the phone setup section, the pronunciation note, the emoji table is quite long). The priority table's 'Use for' column and some sections like Docker deployment could be trimmed since they're tangential to the core skill of sending notifications. | 2 / 3 |
Actionability | Excellent actionability throughout — every section provides copy-paste ready curl commands, complete bash scripts, and working docker-compose configurations. The integration patterns are fully executable with real command structures and proper error handling. | 3 / 3 |
Workflow Clarity | Individual commands and scripts are clear, but the overall skill lacks a coherent workflow sequence. For deployment (Docker setup → user creation → ACL configuration → token generation → client usage), there's no explicit ordering or validation checkpoints. The troubleshooting table partially compensates but there are no verification steps after setup actions. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers, but it's a monolithic document (~200 lines) that could benefit from splitting deployment, ACL management, and integration patterns into separate referenced files. The single external link to emoji docs is good, but more content should be offloaded. | 2 / 3 |
Total | 9 / 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
808c382
- 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.