CtrlK
BlogDocsLog inGet started
Tessl Logo

html-ppt-zhangzara-capsule

A year-end self-review for a product manager — the role, the outcomes, the learning, and the ask, all evidence-backed. Built as a decision-grade career deck for manager, review committee.

51

Quality

57%

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-zhangzara-capsule/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The body is well-structured and highly actionable with a concrete workflow and output contract, but it is weakened by broken bundle-file references and the absence of an explicit verification/critic step for a skill whose own example prompt calls for one. Some descriptive prose could also be trimmed.

Suggestions

Add a final Workflow step for a critic/verification pass (e.g. 'Re-read each claim and confirm the evidence makes it feel earned') to close the loop the example_prompt already promises.

Either ship the referenced bundle files (LICENSE, example.html, template.json, assets/deck-stage.js) or remove the references so navigation is not broken.

Tighten the 'Best for' / 'Avoid for' prose to bullet points to cut the marketing-flavored padding.

DimensionReasoningScore

Conciseness

The body is mostly efficient and avoids explaining concepts Claude already knows, but sections like 'Best for' and 'Avoid for' carry marketing-flavored prose ('a little Y2K', 'pop-art clarity instead of gravitas', 'actively soften authority') that could be tightened.

2 / 3

Actionability

The Workflow gives concrete, specific instructions ('Clone example.html', 'Replace placeholder content', 'Preserve the design system', 'duplicate an existing slide') with clear boundaries, and the Output contract specifies an exact artifact format — fully actionable for an instruction-only skill.

3 / 3

Workflow Clarity

The six Workflow steps are clearly sequenced, but there is no validation or critic checkpoint despite the skill targeting 'decision-grade' evidence-backed output; the example_prompt references a 'critic pass' that the body workflow itself omits.

2 / 3

Progressive Disclosure

The body is well-organized into clear sections, but it references bundle files (./LICENSE, template.json, example.html, assets/deck-stage.js) that do not exist in the skill directory, so the one-level-deep references are signaled but broken.

2 / 3

Total

9

/

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 clearly conveys the artifact and its audience but lacks an explicit 'Use when' trigger clause and a comprehensive action list, leaving it mid-band across all dimensions. It is third-person and free of fluff, but does not fully distinguish itself from adjacent career/portfolio skills.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g. year-end self-review, performance review, promotion deck, career portfolio).

Replace the output-description framing with concrete Claude actions (e.g. 'Drafts, structures, and critiques an evidence-backed year-end self-review deck').

Add common trigger variations such as 'promotion', 'performance review', and 'portfolio' to widen natural-term coverage.

DimensionReasoningScore

Specificity

The description names the domain and output components ('the role, the outcomes, the learning, and the ask, all evidence-backed' and 'Built as a decision-grade career deck') but does not list concrete actions Claude performs, so it stops at naming domain and some actions rather than a comprehensive action set.

2 / 3

Completeness

It clearly states what the skill produces (an evidence-backed year-end self-review career deck) but provides no explicit 'Use when...' trigger guidance, so the 'when' is only implied — capping completeness at 2 per the rubric guideline.

2 / 3

Trigger Term Quality

It includes relevant natural terms like 'year-end self-review', 'product manager', and 'career deck', but is missing common variations (e.g. 'promotion', 'performance review', 'portfolio') that a user might say, leaving coverage incomplete.

2 / 3

Distinctiveness Conflict Risk

The PM year-end self-review niche is reasonably specific, but without explicit triggers the description could overlap with broader career-deck or portfolio skills, so it is somewhat specific rather than cleanly distinct.

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: 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.