screenshot
Find and display recent screenshots. Triggers: screenshot, check screenshot, show screenshot, recent screenshot, last screenshot.
71
58%
Does it follow best practices?
Impact
98%
1.28xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xdarkmatter/claude-mods/screenshot/SKILL.mdQuality
Discovery
89%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 concise and functional description that clearly identifies its niche (screenshots) and provides explicit trigger terms. Its main weakness is that the capability description is somewhat thin—it could benefit from listing more specific actions beyond 'find and display'. Overall it performs well for skill selection purposes.
Suggestions
Expand the capability description with more specific actions, e.g., 'Find and display recent screenshots, list screenshots by date, open screenshot files from the desktop or default screenshot directory.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (screenshots) and two actions (find and display), but doesn't elaborate on specific capabilities like filtering by date, opening in viewer, listing metadata, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (find and display recent screenshots) and 'when' (explicit trigger terms listed). The 'Triggers:' clause serves as an explicit 'use when' equivalent. | 3 / 3 |
Trigger Term Quality | Includes a good set of natural trigger terms users would actually say: 'screenshot', 'check screenshot', 'show screenshot', 'recent screenshot', 'last screenshot'. These cover common variations well. | 3 / 3 |
Distinctiveness Conflict Risk | Screenshots are a distinct niche unlikely to conflict with other skills. The trigger terms are specific to screenshot-related tasks and wouldn't overlap with general file or image processing skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is significantly over-engineered for a relatively simple task (find recent screenshots and display them). It repeats information (usage examples appear twice), includes unnecessary sections (Performance, Integration, Notes), and explains things Claude can figure out on its own. The PowerShell code snippet is also malformed. The content would benefit greatly from being cut to roughly one-third its current size.
Suggestions
Cut the file to under 60 lines: remove the Performance, Integration, and Notes sections entirely; collapse the three platform-specific directory lists into a single compact table or list.
Remove the duplicated usage examples—they appear in both the 'Usage' section and the 'Arguments' section.
Fix the malformed PowerShell snippet (unclosed regex in Where-Object) and show the actual Read tool invocation syntax instead of placeholder text like '[Read tool displays image visually]'.
Move edge case output templates and custom directory configuration into a separate reference file, or remove them entirely since Claude can generate appropriate error messages on its own.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose for what is a simple task. The skill over-explains platform-specific paths, repeats the usage examples multiple times, includes unnecessary sections like 'Performance', 'Integration', and 'Notes' that add little value. Edge case output templates and the output format section are redundant. Claude doesn't need this level of hand-holding for finding and displaying files. | 1 / 3 |
Actionability | Provides concrete commands for finding files (fd, find, PowerShell) and lists specific directory paths, but the PowerShell snippet is malformed (unclosed regex), Step 3 uses placeholder '[Read tool displays image visually]' rather than showing actual tool invocation syntax, and the overall flow mixes pseudocode-level descriptions with real commands inconsistently. | 2 / 3 |
Workflow Clarity | The three-step process (detect directory, find files, display) is clearly sequenced, and edge cases are addressed. However, there are no validation checkpoints—no step to verify the directory actually contains screenshots before proceeding, and no error handling between steps. The workflow is more of a description than an executable procedure. | 2 / 3 |
Progressive Disclosure | Everything is crammed into a single monolithic file with no references to external files. The content is over 150 lines with sections like edge cases, custom directory config, integration notes, and platform-specific paths that could easily be split out or omitted entirely. The document reads as a wall of text with many sections that don't earn their place in a top-level skill file. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- NeverSight/skills_feed
- Commit
9f4534c
- 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.