create-slide

Use this skill when the user wants to create, draft, author, or generate new slides / a presentation in this open-slide repo. Triggers on phrases like "make slides about X", "make a deck about X", "create a presentation", "draft slides for", "new slide", "a deck with speaker notes / a script", or when the user asks to add content under `slides/`. Do NOT use for editing the framework itself — only for authoring content inside `slides/<id>/`.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%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-structured 8-step authoring workflow with strong progressive disclosure that delegates technical detail to a sibling skill. It is held back from the top band by mild verbosity in the worked examples, a delegated starter template, and an implicit rather than explicit self-review fix loop.

Suggestions

Conciseness: trim the three full worked aesthetic-direction examples to one illustration of the 'shift with topic' pattern, and consolidate the repeated 'restate your assumption' guidance into a single statement.

Actionability: inline a minimal `index.tsx` starter skeleton (or the core file-contract snippet) so the primary executable artifact is copy-paste ready here, rather than delegating the entire template to slide-authoring.

Workflow clarity: make Step 7 an explicit validate→fix→re-run loop (e.g., 'if the checklist fails, fix the issue and re-run before handing off') instead of a single 'run the checklist' instruction.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no basic-concept explanations, delegates technical detail to slide-authoring), but the three full worked aesthetic-direction examples (Rust / Q2 roadmap / kindergarten) illustrate a single calibration pattern where one would suffice, and the "restate your assumption" guidance is repeated, so it is anchor 4 rather than a lean 5.	4 / 5
Actionability	Provides concrete, copy-paste-ready code patterns (meta export with theme, `export const design: DesignSystem`, `export const notes`), specific commands (`npm run dev`), a URL, option brackets, and framework primitives, but the actual `index.tsx` starter template is delegated to slide-authoring rather than inlined, a minor gap keeping it at anchor 4.	4 / 5
Workflow Clarity	Clear 8-step numbered sequence with a Step 2 "MUST ask before writing code" gate and a Step 7 self-review validation step plus clarification feedback loops, but Step 7's validate→fix→re-run loop is implicit and the checklist content is delegated, so it is anchor 4 rather than 5.	4 / 5
Progressive Disclosure	No bundle files exist, so this is scored on reference structure: the body is a clear workflow overview that consistently delegates technical reference one level deep to the sibling slide-authoring skill with explicit, named signaling and avoids duplicating that knowledge, matching anchor 5's clear overview with well-signaled one-level-deep references.	5 / 5
	Total	17 / 20 Passed

Description

95%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 that explicitly states what it does and when to use it, with comprehensive natural trigger phrases and a clear negative boundary for distinctiveness. The only soft spot is specificity, where the lead action verbs are synonym variants of a single capability rather than a broad set of distinct actions.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("create, draft, author, or generate new slides / a presentation", "add content under `slides/`", "a deck with speaker notes / a script") plus an explicit negative boundary, but the lead verbs are synonym variants of one capability and distinct coverage is only ~3 actions, so it sits at anchor 4 rather than 5.	4 / 5
Completeness	Explicitly answers both what ("create...new slides / a presentation in this open-slide repo", "authoring content inside `slides/<id>/`") and when ("Use this skill when..." plus concrete trigger phrases and a negative boundary), fitting anchor 5's "clearly and explicitly answers both what AND when with concrete trigger phrases".	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases with synonyms users would actually say ("make slides about X", "make a deck about X", "create a presentation", "draft slides for", "new slide", "speaker notes / a script"), matching the anchor 5 example of broad synonym coverage.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche (authoring content inside `slides/<id>/` in a specific repo) reinforced by an explicit negative boundary ("Do NOT use for editing the framework itself"), giving distinct triggers with minimal conflict risk as anchor 5 requires.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: 1weiho/open-slide
Path: packages/core/skills/create-slide/SKILL.md
Commit: cc5d2ea

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.