Name: cold-email
Rating: 65.60000000000001 (1 reviews)
Author: alirezarezvani

cold-email

When the user wants to write, improve, or build a sequence of B2B cold outreach emails to prospects who haven't asked to hear from them. Use when the user mentions 'cold email,' 'cold outreach,' 'prospecting emails,' 'SDR emails,' 'sales emails,' 'first touch email,' 'follow-up sequence,' or 'email prospecting.' Also use when they share an email draft that sounds too sales-y and needs to be humanized. Distinct from email-sequence (lifecycle/nurture to opted-in subscribers) — this is unsolicited outreach to new prospects. NOT for lifecycle emails, newsletters, or drip campaigns (use email-sequence).

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/cold-email/SKILL.md

The canonical home for this skill is cold-email in alirezarezvani/claude-skills

Quality

Content

63%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, actionable writing skill with clear modes and a scoring feedback loop, weakened by cross-section redundancy and broken bundle references. The body points to reference and script files that do not exist in the skill bundle, undermining progressive disclosure.

Suggestions

Add the missing bundle files (references/frameworks.md, references/follow-up-playbook.md, references/deliverability-guide.md, scripts/email_sequence_analyzer.py) or remove the references and inline only what is needed — currently every cited path is a dead link.

Consolidate the overlapping guidance in 'Core Writing Principles,' 'What to Avoid,' and 'Proactive Triggers' into a single section to remove redundancy and tighten the token budget.

Make the validation loop explicit in Mode 1/Mode 2 (e.g., 're-score until every email is >= 70 before delivering') to fully close the rewrite→re-score feedback loop.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and largely domain-specific operational guidance Claude does not reliably apply (cadence tables, subject-line anti-patterns, audience voice calibration), but 'What to Avoid,' 'Proactive Triggers,' and 'Core Writing Principles' overlap noticeably and the deliverability section restates some general knowledge (SPF/DKIM/DMARC). Not a 4 because the cross-section redundancy is more than minor.	3 / 5
Actionability	Concrete and executable: a runnable tool invocation ('python3 scripts/email_sequence_analyzer.py sequence.json'), specific cadence tables (Day 1/4/9/16/25/35), audience sentence-count guidance, and ❌/✅ examples. Not a 5 because no complete first-touch email example is written out — only fragments and one breakup template.	4 / 5
Workflow Clarity	Three numbered modes are clearly sequenced, with a validation feedback loop ('any email scoring below 70 gets rewritten... then re-scored') and a Mode 3 diagnosis step. Not a 5 because the re-score loop is not stated as 'repeat until >= 70' and lacks the explicit 'only proceed when valid' gate of the 5 anchor.	4 / 5
Progressive Disclosure	References are clearly signaled and one-level-deep ('references/frameworks.md', 'references/follow-up-playbook.md', 'references/deliverability-guide.md', 'scripts/email_sequence_analyzer.py'), but no references/, scripts/, or assets/ directories exist — the referenced bundle files are missing, so navigation is broken. Significant content is also inlined that the missing references were meant to offload.	3 / 5
	Total	14 / 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: third-person voice, concrete actions, rich natural trigger terms, and explicit what/when guidance with active disambiguation against the nearest competing skill. The only minor gap is action breadth relative to the top anchor.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — 'write, improve, or build a sequence of B2B cold outreach emails' and 'needs to be humanized' — covering the skill's scope comprehensively, with only minor gaps in coverage. Not a 5 because the action set, while specific, is narrower than the multi-capability breadth in the 5 anchor.	4 / 5
Completeness	Explicitly answers both what ('write, improve, or build a sequence of B2B cold outreach emails to prospects who haven't asked to hear from them') and when ('Use when the user mentions...') with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms: 'cold email,' 'cold outreach,' 'prospecting emails,' 'SDR emails,' 'sales emails,' 'first touch email,' 'follow-up sequence,' 'email prospecting.' These are exactly the phrases a user would naturally say; file extensions are not applicable to this domain.	5 / 5
Distinctiveness Conflict Risk	States a clear niche — 'unsolicited outreach to new prospects' — and actively disambiguates from the most likely conflict: 'Distinct from email-sequence... NOT for lifecycle emails, newsletters, or drip campaigns (use email-sequence).' Minimal conflict risk.	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: 4 missing	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/cold-email/SKILL.md
Commit: 19392f7

Reviewed: ~2 hours 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.