apple-notes
Manage Apple Notes via the `memo` CLI on macOS (create, view, edit, delete, search, move, and export notes). Use when a user asks OpenClaw to add a note, list notes, search notes, or manage note folders.
78
71%
Does it follow best practices?
Impact
94%
2.68xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/apple-notes/SKILL.mdQuality
Discovery
85%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 description that clearly identifies the tool, platform, and specific actions supported. It includes an explicit 'Use when' clause with reasonable trigger scenarios. The main weakness is that trigger terms could be broader to capture more natural user phrasings, and the mention of 'OpenClaw' is an odd choice that may not match typical user language.
Suggestions
Expand trigger terms to include more natural variations like 'Notes app', 'jot down', 'write a note', 'notebook', or 'memo' to improve discoverability.
Replace 'OpenClaw' with more generic phrasing (e.g., 'the user') since users are unlikely to reference that name in their requests.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: create, view, edit, delete, search, move, and export notes. Also specifies the tool ('memo' CLI) and platform (macOS). | 3 / 3 |
Completeness | Clearly answers both 'what' (manage Apple Notes via memo CLI with specific actions listed) and 'when' (explicit 'Use when' clause specifying trigger scenarios like adding, listing, searching notes, or managing folders). | 3 / 3 |
Trigger Term Quality | Includes natural terms like 'add a note', 'list notes', 'search notes', 'manage note folders', and 'Apple Notes', but misses common variations like 'reminder', 'jot down', 'write a note', 'notebook', or 'Notes app'. The reference to 'OpenClaw' is unusual and may not match what users naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific tool ('memo' CLI), a specific platform (macOS), and a specific application (Apple Notes). Very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 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.
This is a reasonably well-structured CLI reference skill that covers the main operations of the `memo` tool. Its main weaknesses are the lack of guidance on handling interactive prompts (critical for an AI agent), some redundancy between sections, and missing error handling/validation guidance. The actionability is limited by the heavy reliance on interactive mode without non-interactive alternatives.
Suggestions
Document non-interactive usage patterns or pipe-based approaches for each command, since Claude cannot interact with terminal prompts — e.g., show how to pass note body via stdin or flags if supported.
Merge the 'Limitations' and 'Notes' sections to eliminate redundancy (macOS-only is stated twice, permissions info appears in both Setup and Notes).
Add expected output examples for at least `memo notes` and `memo notes -s` so Claude knows what to parse and present to users.
Add error handling guidance — what happens when permissions are denied, a note isn't found, or the tool isn't installed — so Claude can diagnose issues.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but has some redundancy — 'macOS-only' is stated twice, and the 'Notes' section at the end largely repeats information from 'Setup' and 'Limitations'. The 'Limitations' and 'Notes' sections could be merged. Otherwise, the content is reasonably lean. | 2 / 3 |
Actionability | Provides concrete CLI commands for each operation, which is good. However, many commands just open interactive prompts (e.g., `-a`, `-e`, `-d`, `-m`, `-ex`) without showing how to use them non-interactively or what the expected output looks like. For an AI agent that may not be able to interact with terminal prompts, this is a significant gap — there's no guidance on how Claude should handle interactive mode or whether there are non-interactive alternatives. | 2 / 3 |
Workflow Clarity | For a simple CLI reference skill, the individual commands are clear. However, there's no guidance on handling the interactive prompts programmatically, no error handling or validation steps (e.g., what happens if a note doesn't exist, if permissions aren't granted), and no workflow for common multi-step scenarios like 'create a note in a specific folder'. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines with no bundle files, the content is well-organized into logical sections with clear headers. No external references are needed for this scope, and the structure supports easy scanning. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Repository
- qsimeon/openclaw-engaging
- Commit
4467e04
- 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.