Tessl • The package manager for agent skills

SkillPublic

plan-design-review

Senior Designer review: rates each design dimension 0-10, explains what a 10 looks like, and flags AI Slop signals. Useful as a gate before merging UI work.

Quality

60%

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/plan-design-review/SKILL.md

Quality

Content

36%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 body functions as a catalogue advertisement rather than a usable skill: it contains no rating criteria, no AI Slop heuristics, and no executable install instructions, deferring everything to an external repo via a single 'open' command. Sections are organized but largely redundant with the frontmatter. Without the upstream bundle vendored in or its key guidance summarized, an agent invoking this skill cannot perform the advertised review.

Suggestions

Vendor the upstream bundle's core review procedure into the skill: enumerate the design dimensions to rate, define the 0-10 scale anchors, and list concrete AI Slop signals (e.g., generic gradients, inconsistent spacing) so the skill works without fetching the external repo.

Replace 'install the upstream bundle into your active agent's skills directory' with the actual install command (e.g., a git clone into the skills path) and remove the duplicate 'What it does'/'Source' content that restates the frontmatter.

Add a short validation step after installation (e.g., verify the skill's files are present before invoking it by name or trigger phrase) so the workflow has a checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is short, but it duplicates the frontmatter description verbatim in 'What it does' and repeats the upstream URL in both the 'Source' section and the frontmatter, so it could be tightened.	3 / 5
Actionability	The only executable command is 'open https://github.com/garrytan/gstack'; the instruction to 'install the upstream bundle into your active agent's skills directory' gives no command or path, and the actual review procedure (rating dimensions, AI Slop criteria) is entirely absent.	2 / 5
Workflow Clarity	A rough sequence exists (inspect upstream README, install bundle, invoke by name or trigger), but the critical install step is undefined and there are no validation checkpoints or error-recovery guidance.	2 / 5
Progressive Disclosure	Sections are clear and the body is short, but the entire substantive content is offloaded to an external GitHub repo with no bundled reference files, making the body a stub rather than an organized overview.	3 / 5
	Total	10 / 20 Passed

Description

67%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 concrete and well-scoped: it names three specific actions, uses third person, and gives an explicit use context as a pre-merge gate for UI work. Its weaknesses are unnamed design dimensions and missing natural trigger variations users would actually say.

Suggestions

Name the design dimensions being rated (e.g., typography, spacing, hierarchy, color) so the scope of the 0-10 review is unambiguous.

Add natural trigger phrasing such as 'Use when asked to critique, rate, or polish a UI design before merging' to broaden when-clause coverage.

Briefly characterize the AI Slop signals checked (e.g., generic gradients, inconsistent spacing) to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	The description lists several specific actions ('rates each design dimension 0-10, explains what a 10 looks like, and flags AI Slop signals'), but the dimensions themselves are never named, leaving minor gaps in coverage.	4 / 5
Completeness	The 'what' is explicit and concrete, and a 'when' is stated ('Useful as a gate before merging UI work'), but the trigger context is narrow and not phrased as an explicit 'Use when...' clause.	4 / 5
Trigger Term Quality	Terms like 'design', 'UI', 'merging', and 'review' are present, but common natural variations a user would say ('critique my design', 'design feedback', 'polish this UI') are missing.	3 / 5
Distinctiveness Conflict Risk	The niche is distinct — numeric design-dimension rating plus AI Slop flagging as a pre-merge gate — with only minor overlap risk against generic code-review or quality-gate skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/plan-design-review/SKILL.md
Revision: 78d5637

Reviewed: 17 days ago

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.

plan-design-review

Table of Contents

Is this your skill?