CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

54

Quality

68%

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

72%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 genuinely lean, well-sectioned template workflow with a concrete output contract — the conciseness is close to ideal for a single-file skill. Its weaknesses are the complete absence of validation/verification checkpoints in the workflow and body references that point to files not shipped alongside it, which undercut both actionability and navigation.

Suggestions

Add an explicit verification step to the workflow (e.g., 'Open the finished deck in a browser, confirm all slides render and page-number labels match the new count, and run a critic pass asking whether the evidence makes each claim feel earned') to close the workflow_clarity gap.

Ensure the referenced files — `example.html`, `LICENSE`, `template.json`, and any `assets/deck-stage.js` runtime — actually ship inside the skill bundle, or restate the guidance so it does not depend on paths that are absent.

Surface the rubric/critic pass that currently lives only in the frontmatter `example_prompt` into the body's workflow, so the quality bar is part of the documented process rather than hidden in metadata.

DimensionReasoningScore

Conciseness

The ~62-line body is lean and sectioned with no concept-explaining padding: 'At a glance', 'Best for', 'Avoid for', a 6-step workflow, an output contract, and a license note each earn their tokens. It assumes Claude's competence — no HTML or deck primer — matching the anchor 'every token earns its place'.

5 / 5

Actionability

The workflow is mostly executable ('Clone `example.html` into the user's workspace', 'duplicate an existing slide of the most appropriate layout', 'Update page-number labels') and the output contract gives copy-paste `<artifact>` syntax. Not 5: the runtime-file references are conditional and unspecific ('If the deck ships an `assets/deck-stage.js` or inline keyboard handler'), and `example.html` — the workflow's starting file — is not present in this bundle.

4 / 5

Workflow Clarity

A clear 6-step sequence (clone, replace placeholders, preserve the design system, adjust length, design missing layouts, keep the runtime) is present, but there is no validation or verification step anywhere — no render/open check, no page-number check, and the rubric-driven 'critic pass' mentioned in the frontmatter's example_prompt never appears in the body workflow. Anchor 3 (sequence present, checkpoints missing), not 4, because 'most checkpoints present' is unmet.

3 / 5

Progressive Disclosure

Sections are well organized with no nested references, but the body points to `example.html`, `LICENSE`, `template.json`, and `assets/deck-stage.js`, none of which exist in the actual bundle (no references/, scripts/, assets/, or top-level payload files) — the references resolve to nothing, breaking navigation. Scoring against the real bundle structure per the guidelines places this at anchor 3 rather than 4.

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 communicates a specific, niche deliverable in third person without padding, but it reads as a content brief rather than a capability statement: no actions, no 'Use when' clause, and thin trigger-term coverage. It is clearly better than generic filler yet well short of the model examples that pair actions with explicit usage triggers.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user asks for a year-end review, annual review, performance review, or promotion packet as a slide deck') to fix the missing trigger guidance that caps completeness at 3.

Rewrite around concrete actions (e.g., 'Builds a year-end self-review slide deck: drafts the slide plan, writes evidence-backed content slides, and packages the result as a self-contained HTML deck') rather than describing the deliverable's anatomy.

Broaden trigger terms with natural synonyms and file-type cues users actually say — 'annual review', 'performance review', 'promotion packet', 'HTML slides', '.html deck' — to lift trigger-term coverage from partial to comprehensive.

DimensionReasoningScore

Specificity

The description names the deliverable's anatomy ("the role, the outcomes, the learning, and the ask, all evidence-backed") and form ("decision-grade career deck"), but contains no concrete action verbs — it states what the output is rather than what the skill does. Fits anchor 3 (domain plus 1-2 concrete elements), not 4, since several specific actions are never enumerated.

3 / 5

Completeness

The 'what' is clear (an evidence-backed year-end self-review deck for a manager and review committee), but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description — the judging guidelines explicitly cap completeness at 3 in that case. Not 2, because the 'what' is specific rather than vague.

3 / 5

Trigger Term Quality

Relevant keywords are present ("year-end self-review", "product manager", "career deck", "review committee") but common natural variations users would actually say are missing — "annual review", "performance review", "promotion packet", "year-end summary". Anchor 3 (some relevant keywords, missing variations); not 4 because the gaps go beyond 'a few natural terms missing'.

3 / 5

Distinctiveness Conflict Risk

"A year-end self-review for a product manager... decision-grade career deck for manager, review committee" carves a clear niche, but the skill sits in a family of near-identical deck-template skills sharing broad triggers ("career", "portfolio", "html deck"), creating minor overlap risk with closely related skills. Anchor 4, not 5, because of that family overlap.

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

Path

design-templates/html-ppt-zhangzara-capsule/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.