Manage stickies as markdown files — create new, read, list, or delete. Use when the user mentions "sticky", "stickies", or wants to take a quick note or save a reminder.
93
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
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 concisely covers all key dimensions. It specifies concrete actions (create, read, list, delete), uses natural trigger terms users would actually say, and clearly delineates both what the skill does and when to use it. The description is concise without being vague, and the 'stickies as markdown files' framing gives it a distinct identity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'create new, read, list, or delete' stickies as markdown files. Clear and actionable. | 3 / 3 |
Completeness | Clearly answers both what ('Manage stickies as markdown files — create new, read, list, or delete') and when ('Use when the user mentions "sticky", "stickies", or wants to take a quick note or save a reminder'). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'sticky', 'stickies', 'quick note', 'save a reminder'. These cover common variations of how users would phrase such requests. | 3 / 3 |
Distinctiveness Conflict Risk | The concept of 'stickies' as markdown-based quick notes is a clear niche. The trigger terms 'sticky', 'stickies', 'quick note', 'reminder' are distinct enough to avoid conflicts with general note-taking or document management skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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, concise skill that clearly defines four CRUD-like actions with proper sequencing and edge case handling. The sticky format section with concrete filename and frontmatter examples is valuable. The main gap is the lack of explicit tool/command usage — Claude must infer which tools to use for file operations, though this is a minor issue given Claude's capabilities.
Suggestions
Consider adding brief explicit tool references (e.g., 'use Write tool to create the file' or show the exact path like `<cwd>/.ai/stickies/2026-03-22-fix-login-redirect.md`) to make the actions fully copy-paste actionable.
Add a note about ensuring the `.ai/stickies` directory exists before creating the first sticky (e.g., 'create the directory if it doesn't exist').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what stickies are conceptually or how markdown works — it jumps straight into actionable instructions. Every section earns its place with no padding. | 3 / 3 |
Actionability | The instructions are clear and specific about what to do (filename conventions, frontmatter format, table output), but there are no executable code/commands — no actual shell commands for creating directories, listing files, or deleting. The guidance is concrete but relies on Claude inferring the tool usage (file write, file read, file delete, directory listing). | 2 / 3 |
Workflow Clarity | Each action has a clearly numbered sequence of steps with appropriate branching (e.g., multiple matches → ask user, no matches → stop). The delete action explicitly states not to ask for confirmation. Error/edge cases are handled (no stickies, partial matches, multiple matches). | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines with no need for external references, the content is well-organized with clear sections: actions overview, individual action instructions, and the sticky format specification. The structure is flat and easy to navigate. | 3 / 3 |
Total | 11 / 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 | |
3c16e2d
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.