skill-visual-feedback

Process screenshot-based UI/UX feedback to fix visual issues — use when users share screenshots of bugs

Quality

61%

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 ./skills/skill-visual-feedback/SKILL.md

Quality

Content

48%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 lays out a clear, well-sequenced visual-feedback workflow with verification, but it is over-templated and padded and relies on placeholder rather than executable fix guidance. Splitting boilerplate into reference files and tightening templates would materially raise the score.

Suggestions

Replace placeholder fix templates ('Change: [what to change]', 'After: [...]') with a concrete worked example showing an actual Edit, so the implementation phase is executable rather than illustrative.

Move the reusable markdown templates (acknowledge/categorize/root-cause/scope/verification checklists) into a references/ file and keep SKILL.md as a lean overview with one-level-deep links, improving both conciseness and progressive disclosure.

Add an explicit re-validation step after batch 'fix everywhere' edits (re-run the verification checklist per changed file) to lift workflow_clarity from 4 to 5.

Dimension	Reasoning	Score
Conciseness	The body is heavily padded with fill-in-the-blank markdown templates (acknowledge, categorize, root-cause, scope, fix-plan, verification) that Claude could generate itself, matching the noticeably-verbose anchor; it is not severe enough for a 1 but well below efficient.	2 / 5
Actionability	Concrete search guidance (Glob globs, Grep patterns, 'npm run dev') is present, but the core fix steps are placeholder templates ('Change: [what to change]', 'After: [code snippet or description]') rather than executable code, matching the some-concrete-but-incomplete anchor.	3 / 5
Workflow Clarity	A clear five-phase sequence with an explicit Phase 5 verification checklist and user-confirmation checkpoint is present; it is not a 5 because some batch ('fix everywhere') steps lack an explicit re-validate-after-batch loop.	4 / 5
Progressive Disclosure	The skill has clear section headers and tables but is a single ~440-line monolithic file with no bundle files (references/scripts/assets absent) and inline content (patterns, best practices) that could be split out, matching the some-structure-but-inline anchor.	3 / 5
	Total	12 / 20 Passed

Description

73%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 well-formed: third person, explicit what-and-when, and a distinct trigger niche. Its main gap is breadth of concrete actions and trigger synonyms, which keeps specificity and completeness just below the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('screenshot-based UI/UX feedback') and one to two concrete actions ('Process ... feedback', 'fix visual issues'), matching the anchor for naming a domain with limited concrete actions; it does not enumerate several specific actions so it is not a 4.	3 / 5
Completeness	Explicitly answers both 'what' ('Process screenshot-based UI/UX feedback to fix visual issues') and 'when' ('use when users share screenshots of bugs'); the single when-clause is concrete but not a multi-trigger enumeration, so it is a 4 rather than 5.	4 / 5
Trigger Term Quality	Includes natural user phrasing ('screenshots of bugs', 'UI/UX feedback', 'share screenshots') giving good keyword coverage; it misses common synonyms like 'mockup' or 'design', so it sits above 3 but below 5.	4 / 5
Distinctiveness Conflict Risk	The screenshot-driven visual-feedback niche is clearly distinct with specific triggers and minimal overlap with other skills, matching the clear-niche anchor.	5 / 5
	Total	16 / 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: nyldn/claude-octopus
Path: skills/skill-visual-feedback/SKILL.md
Commit: 242e51d

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.