using-screenshots

Use this to capture screen context.

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agency/plugins/nori/skills/using-screenshots/SKILL.md

Quality

Content

78%Weight 40%Scale 1-5

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

The content is highly actionable and well-structured with executable commands across platforms, though it carries some redundant explanation that could be trimmed. Workflow sequencing is clear with only a minor missing file-existence checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but padded sections like "Common Mistakes" (with "Reality" rebuttals) and the Step 5 analysis bullets explain things Claude already knows and could be trimmed.	3 / 5
Actionability	Fully executable, copy-paste-ready commands for every platform/variant (screencapture, gnome-screenshot, scrot, import) plus concrete platform and tool detection commands, covering the common cases.	5 / 5
Workflow Clarity	A clear six-step sequence with a quick-reference table and tool detection; minor gap is the absence of an explicit check that the file was written before loading it with Read.	4 / 5
Progressive Disclosure	A single self-contained, single-purpose SKILL.md with no bundle files and well-organized sections/tables; per the simple-skill note this earns a 5.	5 / 5
	Total	17 / 20 Passed

Description

25%Weight 40%Scale 1-5

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 is far too thin: a single generic clause with no concrete actions, no natural trigger phrases, and no explicit activation guidance. It would rarely surface when users actually need this skill.

Suggestions

Add concrete actions, e.g. "Capture screenshots via platform-native CLI tools and load them into context with the Read tool for visual analysis."

Include explicit trigger phrases users naturally say, e.g. "Use when the user asks to take a screenshot, look at my screen, or analyze a UI bug visually."

Use third-person voice and add distinguishing detail (platform detection, supported tools) to reduce overlap with related skills.

Dimension	Reasoning	Score
Specificity	The phrase "capture screen context" names the domain but offers only a single minimal/generic action with no concrete multi-action coverage, matching the score-2 anchor rather than score 3's "1-2 concrete actions."	2 / 5
Completeness	"Use this to capture screen context" gives both a vague "what" and a vague "when" with no explicit trigger guidance, fitting score 2 better than score 3's clearer "what".	2 / 5
Trigger Term Quality	Only one generic keyword ("capture screen context") appears; the natural phrases users actually say ("take a screenshot", "look at my screen") are absent, matching score 2.	2 / 5
Distinctiveness Conflict Risk	"capture screen context" is very broad with high overlap risk against other screen/UI skills, matching the score-2 "very broad; high overlap risk" anchor.	2 / 5
	Total	8 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: microsoft/FluidFramework
Path: .agency/plugins/nori/skills/using-screenshots/SKILL.md
Commit: f02e424

Reviewed: 3 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.