pitch-deck

当执行 BD/IR 任务需要对外演示材料时创建精美的 HTML 演示文稿——路演 PPT、合作提案、客户 Demo、产品介绍。零依赖单文件输出，可直接通过邮件/微信发送或浏览器演示。

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./crews/main/skills/pitch-deck/SKILL.md

Quality

Content

57%

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

Highly actionable and well-structured with concrete commands and validation gates, but it is undermined by a missing critical reference file (STYLE_PRESETS.md) and lacks error-recovery checkpoints for its fragile headless-rendering pipeline. Fixing the broken reference is the highest-impact improvement.

Suggestions

Create the missing STYLE_PRESETS.md referenced four times in the body, or inline the viewport-safe CSS base, density limits, and preset catalog so the skill is self-contained.

Add a validation/recovery checkpoint for the conversion scripts: detect missing playwright/chromium or render failures and instruct re-install or fallback rather than failing silently.

Tighten redundancy between the workflow's delivery step and the standalone 'HTML → 长图转换' / 'HTML → PPTX 转换' sections to reduce token cost.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with actionable tables and command blocks and no teaching of basic concepts, but the long-image/PPTX conversion rationale is restated across the workflow and dedicated sections and could be tightened.	2 / 3
Actionability	Provides copy-paste-ready commands with full flags, per-deck-type standard structures, exact viewport CSS rules, required JS/CSS elements, and a density-limit table — fully executable guidance.	3 / 3
Workflow Clarity	Seven clearly sequenced steps with an explicit viewport acceptance gate and delivery checklist, but the headless-Chromium conversion pipeline lacks any validate/recover checkpoint for missing dependencies or render failures, capping a fragile batch operation at 2.	2 / 3
Progressive Disclosure	The body leans on STYLE_PRESETS.md four times for critical viewport CSS, density limits, and preset catalog, but that referenced file does not exist in the bundle — a broken, heavily-leveraged navigation path.	1 / 3
	Total	8 / 12 Passed

Description

100%

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 tight, specific, third-person description with explicit 'Use when'-style triggering and good natural-keyword coverage across pitch-deck scenarios. It clearly distinguishes the skill's niche without over-claiming.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and artifacts — '创建精美的 HTML 演示文稿', '路演 PPT、合作提案、客户 Demo、产品介绍', '零依赖单文件输出' — in third-person voice.	3 / 3
Completeness	Explicit '当…时' trigger answers 'when', and '创建…HTML 演示文稿' answers 'what' — both present with explicit trigger guidance.	3 / 3
Trigger Term Quality	Covers natural terms users would actually say: '路演 PPT', '合作提案', '客户 Demo', '产品介绍', 'BD/IR'.	3 / 3
Distinctiveness Conflict Risk	Clear BD/IR HTML pitch-deck niche with distinct triggers; unlikely to fire for general document or PPT skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: TeamWiseFlow/xiaobei
Path: crews/main/skills/pitch-deck/SKILL.md
Commit: bcef823

Reviewed: 3 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.