stickies

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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A clean, well-structured, actionable skill body that respects token budget and organizes content effectively. The only weakness is the Delete workflow, which performs a destructive operation without an explicit verification checkpoint before removal.

Suggestions

Add a pre-delete verification step in the Delete action (e.g., re-confirm the matched filename and briefly state what will be removed) to provide a validate-before-act feedback loop for the destructive operation, even if confirmation prompts are intentionally suppressed.

Clarify the match step shared by Read/Delete — specify whether partial title matching is prefix, substring, or case-insensitive, so the 'find the matching file' step is unambiguous.

For the New action, state explicitly where the date comes from (today's date) and how to handle title collisions in the stickies folder, to remove ambiguity in edge cases.

Dimension	Reasoning	Score
Conciseness	The body is lean and direct — numbered steps, a filename syntax spec, and minimal illustrative examples — with no explanation of concepts Claude already knows; every section earns its place, matching the top anchor. It is not the mid anchor because there is no padding to tighten.	3 / 3
Actionability	Guidance is concrete and specific for an instruction-only skill: filename pattern "YYYY-MM-DD-title-in-snake-case.md", required frontmatter block, snake-case→sentence-case conversion, and a ready-to-use markdown table template. It is not the mid anchor because the examples are complete and copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	Each action is a clearly numbered sequence with match/no-match checkpoints, but the destructive Delete action explicitly states "do not ask for confirmation" and lacks a verification step before removal, which the rubric caps at 2 for destructive operations. It is not score 1 because sequences and some checkpoints are present, and not score 3 because the destructive step omits an explicit validate-before-act feedback loop.	2 / 3
Progressive Disclosure	The skill is short with no external references needed and is organized into clear sections (Actions, Sticky format) with concrete examples, matching the rubric's allowance that simple well-organized skills score 3 without external file references.	3 / 3
	Total	11 / 12 Passed

Description

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.

A strong description: concise, third-person imperative voice, with concrete enumerated actions and an explicit 'Use when' trigger clause covering natural terms. It clearly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	The phrase "create new, read, list, or delete" lists multiple concrete actions on a named artifact, matching the top anchor ("Lists multiple specific concrete actions"); it is not the mid-level anchor because it is comprehensive rather than naming only some actions.	3 / 3
Completeness	It states what ("Manage stickies as markdown files — create new, read, list, or delete") and an explicit "Use when..." trigger clause, hitting the anchor requiring both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	Natural user terms are well covered — "sticky", "stickies", "take a quick note", "save a reminder" — phrases a user would actually say, matching the top anchor rather than the partial-coverage mid anchor.	3 / 3
Distinctiveness Conflict Risk	"Stickies" is a clear niche with distinct triggers unlikely to fire for unrelated skills, matching the top anchor; it does not read generically enough to risk overlap like the mid anchor.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: shillem/cc-marketplace
Commit: 56f705f

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.