CtrlK
BlogDocsLog inGet started
Tessl Logo

html-ppt-tech-sharing

Open Design 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.

57

Quality

67%

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

85%Weight 40%Scale 1-3

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 tightly scoped, highly actionable entry-point skill with a clear sequenced workflow and good one-level-deep references; its only weakness is verbosity in the asset-path explanation.

Suggestions

Trim Step 3's diagnosis of why parent-relative URLs fail to a single sentence, keeping just the two concrete recipes (copy+rewrite vs inline).

Consider a one-line verification nudge (e.g. open index.html locally to confirm slides and keyboard navigation render) after Recipe A/B.

DimensionReasoningScore

Conciseness

The body is mostly efficient, but Step 3 over-explains the asset-path failure mode ("those parent-relative URLs no longer resolve and ... will 404 — meaning the deck never activates") which Claude can infer and could be tightened.

2 / 3

Actionability

It gives copy-paste-ready specifics: exact template paths, the `.tpl-tech-sharing` body class to keep, the four asset files to copy, and concrete `<link id="theme-link">` instructions.

3 / 3

Workflow Clarity

A clear six-step sequence with concrete sub-steps and an explicit guardrail ("never put presenter-only text on the slide"); no destructive/batch operation requires a validation checkpoint here.

3 / 3

Progressive Disclosure

The body is an overview/entry point with well-signaled one-level-deep references to the master skill, the full-decks catalog, the upstream repo, and the LICENSE file.

3 / 3

Total

11

/

12

Passed

Description

50%Weight 40%Scale 1-3

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 clearly scoped to a single deck topic and stays in third person, but it reads as topic marketing copy rather than a trigger-rich capability statement and lacks an explicit "Use when" clause.

Suggestions

Add an explicit "Use when..." clause naming natural triggers like HTML tech-talk decks, engineering deep-dive slides, or AI literacy presentations.

Replace the buzzwordy "decision-grade AI literacy deck" framing with concrete actions the skill performs (e.g. "Author HTML tech-sharing decks from the tech-sharing template").

Lead with the verb/action ("Builds...", "Authors...") so the capability, not just the subject matter, is front and center.

DimensionReasoningScore

Specificity

It names a concrete domain ("Open Design internals: how the agent stream, sandbox, and artifacts work") but describes a deck subject rather than actions the skill performs, so it is not comprehensive.

2 / 3

Completeness

It answers "what" (a deck on Open Design internals) but the "when to use" is only implied; there is no explicit "Use when..." trigger clause, which caps completeness at 2.

2 / 3

Trigger Term Quality

Phrases like "engineering deep-dive talk" and "AI literacy deck" are somewhat natural but miss common variations users would say (e.g. "slides", "tech talk", "HTML deck").

2 / 3

Distinctiveness Conflict Risk

The Open Design / agent-internals framing gives it a niche, but "AI literacy deck" could still overlap with sibling html-ppt deck skills.

2 / 3

Total

8

/

12

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.

Validation13 / 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
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.