CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/_official/examples/html-ppt-hermes-cyber-terminal/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.

A well-crafted pointer card: concise, actionably specific about paths and the asset-URL pitfall, and sequenced clearly. Its main weakness is that it is entirely dependent on an external master skill whose files are not part of this bundle, so progressive disclosure cannot be confirmed and the workflow's foundational step ("read the master skill first") leads outside the skill itself.

Suggestions

Add a brief post-copy validation step, e.g. "open the deck and confirm keyboard navigation and animations activate before replacing demo content", to close the workflow's implicit checkpoint.

If this card must stand alone (shipped without the html-ppt tree), inline the minimal authoring rules it defers to the master skill, or bundle the master SKILL.md and template files so the referenced paths resolve within the skill.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: it never explains what HTML or a slide deck is, and every step carries non-obvious information (e.g. the parent-relative asset URL breakage in step 3). Minor trimmable spots exist — "meaning the deck never activates and slide navigation is dead" and "Default tokens look fine" add explanation a competent reader could infer — so it matches anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Guidance is concrete and executable: exact paths to copy ("design-templates/html-ppt/templates/full-decks/hermes-cyber-terminal/ — copy `index.html` and `style.css`"), the exact four asset files to bring along, and exact source→target URL rewrites ("../../../assets/..." to "assets/fonts.css", etc.). It falls short of anchor 5 only because no literal before/after `<link>` snippet or command is shown and the core authoring rules are deferred to the external master skill.

4 / 5

Workflow Clarity

Six steps in a clear, ordered sequence: read master skill → copy template → fix asset URLs (two explicit recipes) → theme → swap demo content → speaker notes. Step 3 calls out the failure mode (404s, dead navigation) with two remediation recipes, functioning as error-avoidance guidance. It is not a 5 because there is no explicit post-build verification step (e.g. "open the deck and confirm navigation activates") — validation is preventive rather than a checkpoint.

4 / 5

Progressive Disclosure

The card is well structured as a thin entry point with clearly signaled, one-level-deep references to the master skill ([`../html-ppt/SKILL.md`](../html-ppt/SKILL.md)) and the full-decks catalog. However, the actual bundle contains only SKILL.md — no references/, scripts/, or assets/ — and every referenced path lives outside the bundle, so the references cannot be verified from this skill's own files. Per the guideline to score against the actual bundle structure, this lands at anchor 3: references present and reasonably clear, but the organization depends on files that are not part of this bundle.

3 / 5

Total

15

/

20

Passed

Description

53%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 conveys a clear topic niche (BYOK model choice, cost/quality/routing) but reads as marketing copy rather than a capability statement: it never states what the skill actually does (build an HTML deck), omits any 'Use when' trigger guidance, and leans on buzzwords like "decision-grade" and "hands-on". It is distinct within its niche but would not reliably fire from a natural user request.

Suggestions

State the concrete action up front, e.g. "Creates an HTML slide deck in the hermes-cyber-terminal template about BYOK model choice..." — replace "decision-grade" and "hands-on" with what the skill actually produces.

Add an explicit trigger clause: "Use when the user asks for a deck, slides, or presentation on BYOK, model selection, or choosing/wiring an LLM API key."

Include natural user phrasings ("model selection", "pick a model", "bring your own key", "slides", "presentation") alongside the jargon so the description matches how users actually ask.

DimensionReasoningScore

Specificity

The description names the domain and a couple of concrete topics — "choosing and wiring your own model, hands-on — cost, quality, and the routing decision" and "Built as a decision-grade AI literacy deck" — but never states the skill's actual actions (authoring an HTML slide deck in a specific template). It sits between anchor 2 (minimal/generic actions, plus buzz like "decision-grade" and "hands-on") and anchor 4 (several specific actions, which it never lists), so 3 is the best fit.

3 / 5

Completeness

The "what" is reasonably clear (a deck about BYOK model choice covering cost, quality, routing), but there is no "Use when..." clause or equivalent trigger guidance anywhere in the description — the only audience hint is "for engineers, IT, applied-AI teams", which describes the audience, not when to use it. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3; it does not fall to 2 because the what is more than vague.

3 / 5

Trigger Term Quality

Some relevant keywords appear ("BYOK", "model", "cost", "quality", "routing decision", "deck"), but common natural variations are missing — users would say "model selection", "pick an LLM", "bring your own key", "slides", or "presentation", none of which appear. This matches anchor 3 (some relevant keywords, missing common variations) rather than 4, where coverage would be broad.

3 / 5

Distinctiveness Conflict Risk

The BYOK/model-routing niche plus the deck framing ("OpenDesign + BYOK: choosing and wiring your own model") is a fairly clear niche with distinct triggers. It is not a 5 because "OpenDesign" is undefined jargon and the card belongs to a family of similar AI-literacy deck skills (its own tags list sibling deck skills), creating minor overlap risk with closely related skills — exactly anchor 4.

4 / 5

Total

13

/

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

plugins/_official/examples/html-ppt-hermes-cyber-terminal/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.