CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-visual-feedback

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

58

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-visual-feedback/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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.

A well-structured process skill: the five-phase workflow is clearly sequenced with genuine validation checkpoints and a user feedback loop, and the search commands are concrete and executable. It is held back by padded, mutually-redundant summary sections and by keeping ~450 lines in one file with no reference bundle — including a dangling cross-reference to a missing host-adapter file.

Suggestions

Cut the redundant summary sections — 'Quick Reference', 'The Bottom Line', and the overlapping halves of 'Red Flags'/'Best Practices' restate the process table and patterns already covered; keep one.

Move the Common Patterns library and the output-format markdown templates into a references/ file (e.g., references/patterns.md), leaving SKILL.md a lean overview with one-level-deep pointers.

Fix or remove the dangling reference to 'skills/blocks/codex-host-adapter.md' — no such file exists in this bundle, so the host-adaptation guidance it promises is unreachable.

DimensionReasoningScore

Conciseness

The core process, Glob/Grep patterns, and root-cause tables are efficient, but 'Quick Reference', 'Common Patterns', 'The Bottom Line', and the 'Red Flags' table substantially duplicate one another, and Good/Poor pairs ('I'll fix the button') explain things Claude already knows. Mostly efficient with sections that clearly could be tightened or cut.

3 / 5

Actionability

Provides concrete executable material — Glob patterns ('**/*settings*.{tsx,jsx,ts,js,vue,svelte}'), Grep patterns, 'npm run dev', root-cause/indicator tables, and per-file fix reporting. Falls short of fully copy-paste ready because the bash blocks contain only comments and many templates are '[placeholder]' pseudocode.

4 / 5

Workflow Clarity

Five clearly sequenced phases with an explicit verification checklist (run dev server, navigate, check each item, compare with original screenshot) and a user-confirmation feedback loop that supports error recovery ('Let me know if the visual issues are resolved or if further adjustments are needed'). Matches the top anchor: clear sequence, explicit validation, feedback loops, and a checklist.

5 / 5

Progressive Disclosure

The body is well-sectioned but is a ~450-line monolith with no references/ directory at all; the patterns library and output-format templates are inlined content that would fit better in separate reference files, and the one cross-reference ('skills/blocks/codex-host-adapter.md') points at a file that does not exist in the bundle. Some structure, but content that should be separate is inline.

3 / 5

Total

15

/

20

Passed

Description

62%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.

A solid description that clearly pairs a what-clause with an explicit 'use when' trigger and occupies a distinct screenshot-feedback niche. Its main weakness is narrow trigger coverage and thin action enumeration — one trigger case and two generic verbs rather than the fuller set of capabilities and synonyms the body actually delivers.

Suggestions

Enumerate the concrete capabilities in the what-clause (e.g., 'analyze screenshots, categorize visual issues, locate the responsible code, fix systematically, and verify') to raise specificity.

Broaden the when-clause with natural trigger variations users actually say: 'share screenshots or images of UI bugs, mockups that don't match, or complaints like "the UI looks wrong/messy"'.

DimensionReasoningScore

Specificity

"Process screenshot-based UI/UX feedback to fix visual issues" names the domain and two actions (process, fix) but stops short of the sub-capabilities (locate code, categorize issues, verify), matching the '1-2 concrete actions, not comprehensive' anchor. It is above a bare 'Processes screenshots' but below an enumerated list of specific actions.

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 'when' clause is present and explicit but covers a single narrow trigger case rather than the concrete multi-phrase triggers of the top anchor.

4 / 5

Trigger Term Quality

Includes natural terms a user would say — "screenshot", "UI/UX", "bugs" — but misses common variations and synonyms like "image", "mockup", "design feedback", or "looks wrong". Coverage is relevant but incomplete, matching 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

"Screenshot-based UI/UX feedback" carves a mostly distinct niche unlikely to fire on unrelated skills, with only minor overlap risk against closely related frontend/debugging skills. It lacks the fully distinct multi-trigger phrasing of the top anchor.

4 / 5

Total

14

/

20

Passed

Validation

100%

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
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.