kami-deck

A lab-meeting deck on gut-microbiome links to sleep quality — the design, the results, the caveats, and the next experiment. Built as a decision-grade academic research deck for lab group, PI.

Quality

63%

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 ./design-templates/kami-deck/SKILL.md

Quality

Content

77%

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

The body is concise, well-organized, and gives a clear workflow with a self-check validation checklist, but actionability is held back by the absence of embedded code and a referenced example.html that is not bundled.

Suggestions

Include the example.html file in the bundle (or inline a minimal executable HTML/CSS skeleton) so the 'mirror the structure of example.html' instruction is self-contained.

Add a short copy-paste-ready HTML/CSS snippet showing the core tokens and slide-track structure so Claude does not depend solely on external files.

Verify the ../../design-systems/kami/DESIGN.md and ../open-design-landing-deck/scripts/compose.ts references resolve from where the skill is installed, and note if they are optional.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-structured — it does not explain concepts Claude already knows and every section (slide-type table, workflow, self-check, boundaries) earns its place with specific tokens like #1B365D and #f5f4ed.	3 / 3
Actionability	It gives concrete specs (hex tokens, font stacks, typed slide fields, an 11-slide layout), but contains no executable code and leans on mirroring example.html / compose.ts, so the guidance is incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	A clear four-step sequence (gather brief → language stack → write index.html → self-check) ends with an explicit validation checklist covering contrast, resize, and navigation behavior.	3 / 3
Progressive Disclosure	Sections are clearly organized with one-level-deep, well-signaled references, but the key referenced bundle file ./example.html is not present in the skill directory, so a pointed-to detail artifact is missing.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 conveys the deck's subject and audience clearly but reads as a description of an example artifact rather than the skill's general capability, and it omits any explicit 'Use when...' trigger guidance.

Suggestions

Add an explicit trigger clause, e.g. 'Use when preparing a lab-meeting or group-meeting research deck, journal-club slides, or a decision-grade academic research presentation.'

Reframe the description around the skill's actions (e.g. 'Produces a self-contained HTML lab-meeting deck: slide plan, written slides, visual direction, and a critic pass') rather than the example topic.

Broaden trigger terms to common phrasings users would actually say (group meeting slides, research presentation, journal club) to improve distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and content sections ("the design, the results, the caveats, and the next experiment") but describes the artifact rather than the skill's concrete actions, so it is not a comprehensive action list.	2 / 3
Completeness	It conveys what the deck is, but there is no "Use when..." clause or equivalent explicit trigger guidance, so the "when" half is only implied — capping completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Relevant terms like "lab-meeting deck" and "academic research deck" appear, but common variations (e.g., "group meeting slides", "journal club", "research presentation") are missing and no explicit trigger clause is given.	2 / 3
Distinctiveness Conflict Risk	The academic-research / lab-meeting niche is fairly specific, but it could overlap with sibling deck skills (kami-landing, guizang-ppt) given the shared deck framing.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing, 8 suspicious	Warning

	Total	14 / 16 Passed

Repository: nexu-io/open-design
Path: design-templates/kami-deck/SKILL.md
Commit: f2760fd

Reviewed: 4 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.