CtrlK
BlogDocsLog inGet started
Tessl Logo

current-slide

Resolve which slide, page, and (optionally) selected element the user is currently viewing in the open-slide dev server. Consult this whenever the user references "this page", "this slide", "this element", "the slide I'm on", "the current page", or any deictic reference to slide content without naming it. Re-read `node_modules/.open-slide/current.json` at the start of every such turn — the user navigates between turns, so a value you read earlier in the conversation is almost certainly stale.

72

Quality

89%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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, actionable skill body: precise field semantics, a staleness-verification ladder, explicit fallback behavior, and two concrete worked examples. The only real cost is repetition of the re-read-fresh rule, which slightly inflates length without adding new guidance.

Suggestions

Conciseness: state the 'read the file fresh every deictic turn' rule once (the section is enough) and drop its restatement in the two examples' step 1 and closing lines — the frontmatter already carries it.

Conciseness: the selection-field bullets repeat information ('this is the canonical handle — match against the source line, not the rendered DOM') that can be compressed to one line, since tagName/text already make the distinction clear.

Progressive disclosure: if the skill grows, move the annotated field reference and the two worked examples into a single reference file linked from a short SKILL.md overview.

DimensionReasoningScore

Conciseness

The body is efficient — no padding, no explanations of concepts Claude already knows, and every section (field semantics, staleness rules, when/when-not) adds skill-specific knowledge. Minor over-explanation remains: the 're-read on every deictic turn' point is stated in the frontmatter, restated in its own section, and again in the examples' step 1, so it could be trimmed — matching the 'efficient with minor instances of over-explanation' anchor.

4 / 5

Actionability

Fully actionable: the exact path, the tool to use ('Use the `Read` tool. The file is JSON.'), a complete annotated example payload, per-field usage rules (0-based pageIndex vs 1-based pageNumber), and two worked examples with numbered steps. As an instruction-only skill the guidance is copy-paste-ready without code.

5 / 5

Workflow Clarity

Both worked examples are clearly sequenced (read current.json → check staleness → read pagePath → locate page/element → edit) with an explicit validation checkpoint (the fresh/5-minute/hours staleness ladder keyed to `updatedAt`), plus explicit fallback and error-recovery branches for missing file, null selection, and stale data.

5 / 5

Progressive Disclosure

No bundle files exist, and everything present belongs inline for a skill of this scope — the structure (when to use / when NOT to use / field reference / examples) is well organized with no content that clearly belongs in a separate file. It stops short of the 5 anchor because the body runs ~110 lines; the annotated field reference and the two examples could be tightened or split were the skill to grow.

4 / 5

Total

18

/

20

Passed

Description

90%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.

A strong description: third-person, concrete, with a rich set of natural deictic trigger phrases and an explicit use-when clause. The only minor gap is that it describes a single resolve-and-read action rather than a broader set of capabilities, which is appropriate for this skill's narrow scope.

DimensionReasoningScore

Specificity

The description names the domain (open-slide dev server) and one concrete action — 'Resolve which slide, page, and (optionally) selected element the user is currently viewing' by re-reading a specific file ('node_modules/.open-slide/current.json'). It matches the anchor for naming a domain with 1-2 concrete actions: it is not vague (ruling out 1-2), but it does not list several distinct actions, so it falls short of the 4-5 anchors.

3 / 5

Completeness

It explicitly answers what ('Resolve which slide, page, and (optionally) selected element the user is currently viewing in the open-slide dev server') and when ('Consult this whenever the user references "this page"... or any deictic reference to slide content without naming it'), with concrete trigger phrases — the top anchor.

5 / 5

Trigger Term Quality

It enumerates the natural deictic phrases a user would actually say — '"this page", "this slide", "this element", "the slide I'm on", "the current page"' plus 'any deictic reference to slide content' — covering synonyms and variations comprehensively, matching the top anchor.

5 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (live cursor state in the open-slide dev server) with triggers ('deictic reference to slide content') that no generic skill would claim, and even distinguishes itself from sibling workflows. Minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
1weiho/open-slide
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.