When the user wants to build video-first cold outreach, create personalized video at scale, implement async selling, or use AI demo generation for prospecting. Also use when the user mentions 'video outreach,' 'personalized video,' 'video prospecting,' 'Tavus,' 'Sendspark,' 'HeyGen,' 'video email,' 'async selling,' 'video demo,' or 'made this for you.' This skill covers video-first outreach systems from personalization through conversion optimization. Do NOT use for technical implementation, code review, or software architecture.
78
72%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./packages/skills-catalog/skills/(gtm)/video-outreach/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured skill description with strong trigger term coverage and clear completeness, including both positive triggers and explicit exclusions. Its main weakness is that the 'what it does' portion relies on somewhat abstract category descriptions rather than listing concrete deliverables or actions the skill performs. The description effectively differentiates itself from technical skills through its exclusion clause.
Suggestions
Replace abstract phrases like 'video-first outreach systems from personalization through conversion optimization' with specific concrete actions such as 'designs video outreach sequences, writes personalized video scripts, recommends video tools, optimizes video email conversion rates.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (video-first cold outreach) and mentions some actions like 'build video-first cold outreach,' 'create personalized video at scale,' 'implement async selling,' and 'AI demo generation,' but these are more like category labels than concrete, specific actions. It lacks detail on what the skill actually produces or does (e.g., 'generates outreach scripts,' 'designs video sequences,' 'optimizes conversion funnels'). | 2 / 3 |
Completeness | The description explicitly answers both 'what' (video-first outreach systems from personalization through conversion optimization) and 'when' (detailed trigger conditions with 'When the user wants to...' and 'Also use when the user mentions...'). It also includes a helpful exclusion clause ('Do NOT use for technical implementation, code review, or software architecture'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including tool names ('Tavus,' 'Sendspark,' 'HeyGen'), user phrases ('video outreach,' 'personalized video,' 'video prospecting,' 'video email,' 'async selling,' 'video demo,' 'made this for you'). These are terms users would naturally use when seeking this type of help. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a very clear niche around video-based sales outreach with specific tool names and explicit exclusions for technical/code tasks. This is unlikely to conflict with other skills given its narrow domain focus and boundary-setting. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is exceptionally actionable with clear workflows, specific frameworks, and concrete guidance that would genuinely help someone build video outreach systems. However, it is severely bloated—the monolithic structure with inline platform comparisons, marketing statistics, pricing details, and extensive benchmark tables wastes significant context window space. The content would be far more effective split into a concise overview SKILL.md with references to detailed sub-files for tool comparisons, benchmarks, and recording best practices.
Suggestions
Split platform comparisons, benchmark tables, and recording best practices into separate referenced files (e.g., TOOLS.md, BENCHMARKS.md, RECORDING.md) and keep only the Quick Reference table and core framework in SKILL.md
Remove marketing statistics and vendor claims (e.g., 'Named #1 Fastest Growing Product of 2025 on G2', 'used by 100,000+ businesses', specific reported rate improvements) as these are promotional, time-sensitive, and not actionable
Cut the 'Before Starting' discovery questions and 'Questions to Ask' sections—these overlap significantly and Claude can infer appropriate discovery questions from the framework content
Remove pricing details (e.g., '$39/mo starter', '$12.50/user/mo') which will quickly become outdated and add no lasting value to the skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This is extremely verbose at 400+ lines. It includes extensive platform comparisons with marketing stats Claude doesn't need to memorize, detailed pricing that will become outdated, benchmark tables that could be referenced externally, and explanatory content about concepts like async selling that Claude already understands. Much of this could be condensed to 1/3 the length. | 1 / 3 |
Actionability | The skill provides highly concrete, actionable guidance throughout: specific video timing breakdowns (0:00-0:05 hook, 0:05-0:15 context), exact sequence architectures with day-by-day plans, specific tool recommendations by volume tier, and clear frameworks like the 'Made This For You' four-step process. The examples section shows clear input→output patterns. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit checkpoints. The 'Made This For You' framework has four clearly defined steps with time estimates. The sales sequence architecture provides day-by-day progression. Watch time qualification signals include specific follow-up actions. The async demo structure provides second-by-second timing. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. The platform comparisons, benchmark tables, recording best practices, and troubleshooting sections could all be split into separate reference files. Everything is inline, making this a massive document that will consume significant context window space every time it's loaded. | 1 / 3 |
Total | 8 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
906a57d
Table of Contents
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.