shader-dev

GLSL shader techniques for ray marching, fluid simulation, particle systems, and procedural generation. Useful for hero visuals and motion stills.

Quality

46%

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/shader-dev/SKILL.md

Quality

Content

35%

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

The body is lean and section-organized but functions almost entirely as a pointer to an external repo: it restates the description, offers no executable shader guidance, and provides no in-bundle detail layer or validation. It reads as a catalogue stub rather than a self-contained, actionable skill.

Suggestions

Add at least one concrete, executable example of the skill's actual work (e.g., a minimal GLSL ray-marching snippet or a command that runs/compiles a shader) so the body is actionable instead of a pointer to an external README.

Provide a real install/invocation step with an explicit command rather than 'inspect the upstream README for exact paths', and include a validation checkpoint (e.g., how to confirm the skill loaded) to raise workflow clarity.

Either bring the key upstream reference content into local bundle files (references/) and link to them clearly from the body, or restructure the body so the description is not duplicated and the upstream pointer is signaled as the single source of detail.

Dimension	Reasoning	Score
Conciseness	The body is short and free of concept-explaining padding, but it restates the frontmatter description verbatim in 'What it does' and repeats the upstream URL in both frontmatter and '## Source', so several tokens are redundant rather than earning their place, matching the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	The only instruction is 'open https://github.com/MiniMax-AI/skills' and 'Inspect the upstream README for exact paths' — vague direction that describes where to look rather than providing any concrete, executable shader guidance, matching the 'vague or abstract; no concrete code/commands; describes rather than instructs' anchor.	1 / 3
Workflow Clarity	A loose sequence is present (catalogue entry → install upstream bundle → invoke by name or trigger), but there is no actual install command, no validation, and no checkpoints — steps are implicit and delegated to an external README, matching the 'steps listed but validation gaps; checkpoints missing or implicit' anchor.	2 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and all detail lives in an external GitHub repo, so while the short body is organized into clear sections, there is no in-bundle one-level-deep reference layer to navigate, matching the 'some structure but could be better organized; references not clearly signaled' anchor.	2 / 3
	Total	7 / 12 Passed

Description

57%

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 clearly identifies a specific, distinctive shader niche and includes some natural trigger terms, but it relies on topic categories rather than concrete actions and lacks an explicit 'Use when...' trigger clause, leaving the 'when' only implied. It is solid but not exemplary.

Suggestions

Rewrite the description around concrete actions the skill performs (e.g., 'Generates, compiles, and optimizes GLSL shaders for...') rather than listing topic categories, to lift specificity toward a 3.

Add an explicit 'Use when...' clause naming concrete user scenarios (e.g., 'Use when the user wants ray-marched scenes, fluid effects, or procedural visuals for hero shots or motion stills.') to satisfy the completeness 'when' requirement.

Expand the trigger list with common colloquial variations users would actually say, such as 'fragment shader', 'vertex shader', 'Shadertoy', 'SDF', and 'shader art', to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'GLSL shader techniques for ray marching, fluid simulation, particle systems, and procedural generation' — it names a clear domain and several concrete sub-areas, but these are topic categories rather than enumerated concrete actions the skill performs, so it sits at the 'names domain and some actions' anchor rather than the 'multiple specific concrete actions' level.	2 / 3
Completeness	The 'what' is clearly stated ('GLSL shader techniques for ray marching, fluid simulation, particle systems, and procedural generation') but the 'when' is only weakly implied via 'Useful for hero visuals and motion stills' rather than an explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Triggers list 'shader', 'glsl', 'ray marching', 'fluid simulation', 'procedural generation' — the first few are natural user terms, but common colloquial variations like 'fragment shader', 'Shadertoy', 'SDF', or 'shader art' are missing, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	GLSL shaders / ray marching / fluid simulation is a narrow, specialized 3D-graphics niche with distinct technical triggers unlikely to overlap with unrelated skills, matching the 'clear niche with distinct triggers; unlikely to conflict' anchor.	3 / 3
	Total	9 / 12 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/shader-dev/SKILL.md
Commit: a2ba3ee

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.