CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-cold-outreach

When the user wants to build an AI-powered outreach system, write cold emails, improve deliverability, or scale personalized outreach. Also use when the user mentions 'cold email,' 'cold outreach,' 'outreach automation,' 'Instantly,' 'Smartlead,' 'Clay,' 'email sequences,' 'deliverability,' 'personalization at scale,' 'reply rate,' or 'outreach stack.' This skill covers the complete AI cold outreach system from signal detection through conversion. Do NOT use for technical implementation, code review, or software architecture.

76

Quality

70%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./packages/skills-catalog/skills/(gtm)/ai-cold-outreach/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

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 strong skill description with excellent trigger term coverage and completeness. It clearly defines both when to use and when not to use the skill, and includes specific tool names that create a distinct identity. The main weakness is that the 'what' portion could be more specific about the concrete actions the skill performs beyond high-level domain descriptions.

Suggestions

Add more specific concrete actions to improve specificity, e.g., 'configure email warmup schedules, set up DNS authentication (SPF/DKIM/DMARC), build lead enrichment workflows, write multi-step email sequences, analyze campaign metrics.'

DimensionReasoningScore

Specificity

The description mentions some actions like 'build an AI-powered outreach system, write cold emails, improve deliverability, scale personalized outreach' and references 'signal detection through conversion,' but these are more domain-level than concrete specific actions. It lacks the granularity of listing multiple discrete operations (e.g., 'set up email warmup, configure DNS records, write email sequences, build lead lists').

2 / 3

Completeness

Clearly answers both 'what' (build AI-powered outreach system, write cold emails, improve deliverability, scale personalized outreach, complete system from signal detection through conversion) and 'when' (explicit 'Use when' equivalent with detailed trigger terms). Also includes a helpful negative boundary ('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 ('Instantly,' 'Smartlead,' 'Clay'), common phrases ('cold email,' 'cold outreach,' 'outreach automation,' 'email sequences'), and outcome-oriented terms ('deliverability,' 'reply rate,' 'personalization at scale,' 'outreach stack'). These are terms users would naturally use.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche in cold email outreach and specific tool names (Instantly, Smartlead, Clay). The explicit exclusion of technical implementation/code review further reduces conflict risk with developer-oriented skills. Unlikely to be confused with general email or marketing skills.

3 / 3

Total

11

/

12

Passed

Implementation

50%

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

This skill is exceptionally actionable and comprehensive, providing specific metrics, formulas, frameworks, and tool comparisons that would genuinely help Claude guide users through cold outreach. However, it is far too verbose for a SKILL.md file — it reads more like a complete playbook than an overview with references. The content quality is high but the token efficiency is poor; roughly 60% of the content should be moved to the referenced files, leaving the main skill as a concise overview with the 3-line framework, key decision points, and the 'Before Starting' checklist.

Suggestions

Move the detailed comparison tables (Instantly vs Smartlead, infrastructure sizing, signal types, reply categories) into the referenced files and keep only the decision frameworks and key thresholds in the main skill body.

Add explicit validation checkpoints to the workflow: e.g., 'Verify bounce rate is under 2% before scaling beyond 100/day' and 'Confirm 3%+ reply rate on first 200 sends before expanding to full volume.'

Cut explanatory text that Claude already knows — e.g., remove the Bombora paragraph explaining what a data cooperative is, the explanation of what SPF/DKIM/DMARC do, and the 'Why the bad example fails' breakdown. Keep the checklist items and examples, drop the explanations.

DimensionReasoningScore

Conciseness

This is extremely verbose at 400+ lines. It explains concepts Claude already knows (what DMARC is, what SPF does, what a waterfall is), includes extensive comparison tables that could be in a reference file, and repeats information across sections. The Bombora explanation, the full enrichment waterfall diagram, and the detailed Instantly vs Smartlead comparison table all belong in reference files, not the main skill body.

1 / 3

Actionability

The skill provides highly specific, concrete guidance throughout: exact sending limits per mailbox, domain math formulas, warmup schedules by week, email frameworks with good/bad examples, specific tool recommendations with decision trees, and precise metrics. The 3-line email framework with concrete examples is copy-paste ready.

3 / 3

Workflow Clarity

The six-stage pipeline is clearly sequenced and the domain warmup protocol has week-by-week steps. However, there are no explicit validation checkpoints or feedback loops in the overall workflow. The DMARC rollout has a good sequence, but the main outreach build process lacks 'verify before proceeding' gates — e.g., no step to validate deliverability before scaling volume, no checkpoint to confirm ICP targeting is working before increasing sends.

2 / 3

Progressive Disclosure

The skill references two external files (references/benchmarks-deliverability-tactics.md and references/quick-reference.md) and lists related skills, which is good. However, the main body contains massive amounts of detail that should be in those reference files — the full Instantly vs Smartlead comparison, the complete enrichment waterfall, the infrastructure sizing guide, and the reply handling table all bloat the main file when they could be offloaded.

2 / 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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
tech-leads-club/agent-skills
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.