using-screenshots

Use this to capture screen context.

Quality

48%

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

65%

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 with complete, per-platform executable commands and a clear step sequence, but it is padded with redundant sections and lacks validation checkpoints for its capture/cleanup workflow. As a single long inline file it is well-structured yet misses progressive disclosure beyond the simple-skill threshold.

Suggestions

Add a verification step after capture (e.g., check the file exists and is non-empty) before the Read step, and confirm before running the destructive rm cleanup.

Trim redundancy: collapse the step-5 "analyze" list and the "Common Mistakes" section, since the step-by-step and Example Workflow already convey the same guidance.

Move the per-platform command catalog and distro install instructions into a reference file (e.g. references/platforms.md) and link to it from a concise overview, keeping SKILL.md under the simple-skill threshold.

Dimension	Reasoning	Score
Conciseness	The body is mostly tight executable commands, but carries redundancy — the step-5 "analyze" list restates Claude's existing capabilities, the "Common Mistakes" section re-explains the workflow, and the Example Workflow duplicates the step-by-step — so it could be trimmed and is not fully lean.	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands per platform (uname -s, which ... \|\| ..., screencapture -i, gnome-screenshot -af, scrot -s, import), explains each flag, and includes concrete distro-specific install commands, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The detect→check→capture→load→analyze→cleanup sequence is clearly listed, but there are no validation/verification checkpoints (e.g., confirm the file exists or is non-empty before reading) for a workflow that includes a destructive rm cleanup and capture that can fail, which caps clarity at 2.	2 / 3
Progressive Disclosure	The body is well-organized into clear sections (not a wall of text), but at ~181 lines with all content inline and no one-level-deep references or navigation, it exceeds the under-50-line simple-skill exception and contains detail that could be split into reference files.	2 / 3
	Total	9 / 12 Passed

Description

32%

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 too thin: it names a domain and one action but omits the keyword "screenshot", gives no explicit use-when triggers, and leaves both the what and the when under-specified. It is specific enough to avoid being a bare abstraction but far below the strong example descriptions.

Suggestions

Add a concrete action list and the primary keyword, e.g. "Capture screenshots using platform tools and load them for visual analysis. Use when the user asks to take a screenshot, look at the screen, or visually debug a UI."

Include an explicit 'Use when ...' trigger clause naming natural user phrases such as "take a screenshot", "look at my screen", and "analyze this UI".

Reference both halves of the task — capture AND load/analyze via the Read tool — so the what is complete and distinct from generic screen-context skills.

Dimension	Reasoning	Score
Specificity	"capture screen context" names the screen-capture domain and one concrete action, but stops short of listing multiple specific actions like analysis or loading the image, so it is not comprehensive (3) yet is more concrete than vague abstractions (1).	2 / 3
Completeness	"Use this to capture screen context" gives only a weak "what" and provides no explicit "when"/trigger guidance at all, leaving both halves thin — closer to "Helps with documents" than a partial-but-clear description.	1 / 3
Trigger Term Quality	The phrase "capture screen context" contains the relevant keyword "screen" but omits the single most common natural term "screenshot", missing the dominant user phrasing without being pure jargon.	2 / 3
Distinctiveness Conflict Risk	"capture screen context" points at a fairly specific screenshot niche unlikely to broadly conflict, but lacks distinct trigger terms that would clearly set it apart from neighboring skills.	2 / 3
	Total	7 / 12 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: f9f2007

Reviewed: about 7 hours 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.