CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

html-ppt-tech-sharing

OpenDesign internals: how the agent stream, sandbox, and artifacts work — an engineering deep-dive talk. Built as a decision-grade AI literacy deck for engineers, dev community.

52

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 ./design-templates/html-ppt-tech-sharing/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 is a lean, well-sequenced pointer card with genuinely concrete operational detail — the broken-asset-URL trap and its two fix recipes are the standout. Its main weaknesses are the missing end-to-end validation step and the fact that every reference it depends on (master skill, template files, shared assets) lives outside this bundle, making the card non-executable in isolation.

Suggestions

Add an explicit final validation step, e.g., "Open index.html and confirm arrow-key/T navigation and animations activate; if styles 404, re-check the four rewritten asset paths".

Include the referenced files in the bundle (master SKILL.md, `templates/full-decks/tech-sharing/`, shared `assets/`) or inline the minimal authoring checklist so the card is self-sufficient when the parent tree is absent.

Trim the duplicated file lists in Recipe A/B (state the four files once, then the two recipes) and the spelled-out consequence of the 404s.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — no concept tutorials, just operational facts like exact paths, the four asset files, the `<link>`/`<script>` rewrite targets, and "Speaker notes go inside `<aside class=\"notes\">`". It sits at "Efficient; minor instances of over-explanation that could be trimmed": the aside "meaning the deck never activates and slide navigation is dead" spells out a consequence Claude could infer, and Recipe A/B path lists repeat the same four filenames twice. Not 5 because of that minor padding; not 3 because nothing explains concepts Claude already knows.

4 / 5

Actionability

Guidance is largely copy-paste ready: exact folders ("design-templates/html-ppt/templates/full-decks/tech-sharing/"), the four concrete asset paths, precise rewrite instructions ("from `../../../assets/...` to `assets/fonts.css`, `assets/base.css`, `assets/animations/animations.css`, `assets/runtime.js`"), and the `T`-key theme cycle. It falls short of 5 because the core authoring rules (content/audience checklist, token rules, presenter mode) are deferred entirely to `../html-ppt/SKILL.md`, which is not part of this bundle — a reader outside that tree cannot execute the full authoring workflow from what is written here.

4 / 5

Workflow Clarity

A clear numbered sequence (read master skill → copy template → fix asset URLs → pick theme → replace demo content → place speaker notes), and step 3 even pre-empts a failure mode (the 404ing `../../../assets/...` URLs) with two remediation recipes — fitting "Clear sequence with most checkpoints present; minor validation gaps". It is not 5 because there is no final validation step (e.g., "open index.html and confirm navigation/runtime activates") to verify the URL rewrite actually succeeded; it is not 3 because the risky step does include an explicit failure-mode checkpoint.

4 / 5

Progressive Disclosure

The card is well-structured as a thin pointer (title, when-picked, six-step authoring, attribution) with clearly signaled one-level references ("[`design-templates/html-ppt/SKILL.md`](../html-ppt/SKILL.md)", the full-decks catalog, the upstream repo). However, none of the referenced paths exist in this bundle — there are no `references/`, `scripts/`, or `assets/` directories and no `../html-ppt` tree — so the promised navigation targets (including the templates and runtime assets the whole workflow depends on) do not resolve. That matches "Some structure but could be better organized": structure and signaling are present, but the split is not actually navigable within this bundle, keeping it below 4.

3 / 5

Total

15

/

20

Passed

Description

48%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 topic-rich but capability-poor: it describes the deck's subject matter vividly yet never states what the skill actually does or when to invoke it. It reads more like a talk abstract than a skill description, costing it action verbs, natural trigger phrases, and any "use when" guidance.

Suggestions

State the skill's concrete actions in third person, e.g., "Builds an HTML slide deck in the tech-sharing template — copies the template, fixes shared asset URLs, applies themes, and adds speaker notes".

Add an explicit trigger clause, e.g., "Use when the user asks for an HTML presentation, tech talk, or engineering deep-dive deck, or mentions slides/decks for a dev audience".

Trim buzzword padding like "decision-grade AI literacy" — replace with the concrete deliverable (a presenter-ready HTML deck with keyboard navigation and speaker notes).

DimensionReasoningScore

Specificity

The description "OpenDesign internals: how the agent stream, sandbox, and artifacts work — an engineering deep-dive talk. Built as a decision-grade AI literacy deck for engineers, dev community" names the domain (a tech-talk deck) but offers almost no concrete actions — there is no verb describing what the skill does (e.g., builds, generates, styles HTML slides). It matches the anchor "Names the domain but actions are minimal or generic"; a score of 3 would require 1-2 concrete stated actions, which are absent.

2 / 5

Completeness

The "what" is present but topic-focused (a decision-grade deck about OpenDesign internals) rather than describing the skill's capability, and the "when" is entirely absent — no "Use when..." clause or equivalent trigger guidance appears, which caps completeness at 3 per the judging guidelines. It is not 2 because the what is stated concretely, and not 4 because the when clause is missing altogether rather than merely imprecise.

3 / 5

Trigger Term Quality

Phrases like "engineering deep-dive talk", "AI literacy deck", and "deck" are relevant, but common natural variations users would say — "presentation", "slides", "tech talk", "speaker notes", "HTML slides" — are missing from the description. This fits "Some relevant keywords but missing common variations or synonyms"; it is above 2 (more than generic jargon) but below 4 (no synonyms/extensions for the presentation domain).

3 / 5

Distinctiveness Conflict Risk

The narrow subject matter ("OpenDesign internals: how the agent stream, sandbox, and artifacts work") gives the description a clear niche unlikely to be confused with other skills, fitting "Mostly distinct; minor overlap risk with closely related skills". It is not 5 because nothing in the description itself separates it from other AI-literacy/presentation-deck skills, and the associated trigger list includes ultra-generic terms ("ai", "workflow", "copilot") that would compete with many skills.

4 / 5

Total

12

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 3 suspicious

Warning

referenced_paths_exist

Referenced path issues: 5 missing, 2 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository

nexu-io/open-design

Path

design-templates/html-ppt-tech-sharing/SKILL.md

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.