CtrlK
BlogDocsLog inGet started
Tessl Logo

html-ppt-zhangzara-coral

OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.

57

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./design-templates/html-ppt-zhangzara-coral/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tight, well-structured template skill: the body stays lean, gives concrete clone-and-replace workflow steps, an explicit output contract, and honest best-for/avoid-for guidance. The main gaps are the absence of any validation/critic checkpoint in the workflow itself and references to bundle files that are not verifiable in the provided bundle.

DimensionReasoningScore

Conciseness

The body is lean throughout: "At a glance", "Best for", and "Avoid for" deliver template-selection guidance in a few lines each, the workflow is six tight numbered steps, and it never explains concepts Claude already knows (no HTML/deck primers, no padding). Every section earns its tokens, matching anchor 5; it is not 4 because there is no over-explanation to trim anywhere.

5 / 5

Actionability

Guidance is concrete and executable: "Clone `example.html` into the user's workspace", "Replace placeholder content with the user's real headlines, body copy, numbers...", "duplicate an existing slide of the most appropriate layout", "If less, drop slides from the bottom. Update page-number labels", plus a copy-pasteable `<artifact identifier="zhangzara-coral" type="text/html">` output contract. It falls short of anchor 5 because there is no concrete example of the placeholder-swap or a full output sample — the artifact block is a skeleton, and steps like "Match existing dimensions when swapping image placeholders" leave details implicit.

4 / 5

Workflow Clarity

The six workflow steps are clearly sequenced (clone → replace content → preserve design system → adjust length → design missing layouts → keep navigation runtime) and each step carries specific, checkable instructions. It is not 5 because there are no explicit validation or critic checkpoints (e.g. a final pass verifying fonts/palette/decorations were preserved and the output contract is met) — the critic pass lives only in the frontmatter example_prompt. It is above 3 because the sequence itself is well defined and this is not a destructive or batch operation requiring feedback loops.

4 / 5

Progressive Disclosure

The body is a well-organized overview with clear sections, and its references are one level deep and clearly signaled ("[`LICENSE`](./LICENSE)", "See `template.json` for the upstream metadata snapshot", the conditional "if the deck ships an `assets/deck-stage.js`"). However, the referenced bundle files (LICENSE, template.json, example.html, assets/) are not present in the provided bundle, so the references cannot be verified against actual file structure, leaving minor organization gaps per anchor 4 rather than the fully verified, well-split structure of anchor 5.

4 / 5

Total

17

/

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 is specific and distinctive about its subject matter but reads more like a deck abstract than a capability description: it never states the actions the skill performs (create/plan/build a deck) and contains no explicit "use when" trigger guidance, capping both specificity and completeness at the midpoint. Natural trigger-phrase coverage is thin despite the dedicated frontmatter triggers list.

Suggestions

State the skill's actions explicitly in the description, e.g. "Creates and edits a decision-grade Marketing & GTM HTML deck..." so the what is about capabilities, not just the demo subject.

Add a "Use when..." clause to the description itself (e.g. "Use when the user asks for a marketing/GTM plan deck, community growth campaign plan, or presentation slides") to lift completeness above the cap of 3.

Include natural synonyms users would actually say — "growth plan", "marketing deck", "slide deck", "presentation" — alongside the current keywords to broaden trigger coverage.

DimensionReasoningScore

Specificity

The description names the domain clearly ("community-growth campaign across GitHub, Discord, and X", "marketing & GTM deck") and lists concrete content areas ("the loops, the content calendar, and the pipeline math"), but it describes the deck's subject matter rather than enumerating actions the skill performs. This matches anchor 3 (domain plus 1-2 concrete elements, not comprehensive); it is not score 4 because no specific capability/action list is given, and not score 2 because the domain and deliverable are named concretely, not generically.

3 / 5

Completeness

The "what" is reasonably clear (a decision-grade marketing & GTM deck covering the loops, content calendar, and pipeline math), but there is no "Use when..." clause or equivalent explicit trigger guidance in the description itself, which per the judging guidelines caps completeness at 3. The separate frontmatter `triggers:` list exists, but the description field alone only weakly implies "when", matching anchor 3 exactly; it is not 4 because the "when" is not stated in the description, and not 2 because the "what" is concrete rather than vague.

3 / 5

Trigger Term Quality

Relevant keywords appear ("community-growth campaign", "marketing & GTM deck", "content calendar", "pipeline math", "GitHub, Discord, and X") but common natural variations users would say are missing (e.g., "growth plan", "marketing deck", "slides", "presentation"). This fits anchor 3 — some relevant keywords, missing variations/synonyms; it lacks the synonym and extension coverage of anchor 4.

3 / 5

Distinctiveness Conflict Risk

The named campaign subject (OpenDesign community growth across GitHub, Discord, and X) and the "decision-grade marketing & GTM deck" framing give it a clear niche with minimal conflict risk against unrelated skills. It falls just short of anchor 5 because broad terms like "marketing", "campaign", and "deck" could overlap with other marketing/presentation skills in the same family.

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: 1 missing

Warning

referenced_paths_exist

Referenced path issues: 1 missing

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.