inbox-placement-monitor

Use when the user asks to "track where my emails are actually landing after I send", "read my seed-list inbox vs spam vs promotions results", "trend my Gmail Postmaster / Microsoft SNDS reputation", or "did placement drop after my last send"; produces a per-provider inbox/spam/promotions placement read, a domain/IP reputation trend from Postmaster + SNDS, a send-over-send delta with named regressions, and a reusable SEND-S placement snapshot on your own exported telemetry. Not for the pre-send SPF/DKIM/DMARC auth pre-flight — use deliverability-qa; not for computing the EQS or running the vetoes — use email-quality-auditor. 邮件收件箱落点监测/收件箱vs垃圾邮件/Postmaster声誉趋势

Quality

85%

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

Quality

Content

77%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, action-oriented skill body with a clear sequenced workflow and good one-level-deep reference split. Its main weakness is conciseness — the scope guard and jargon repeat across sections rather than being stated once.

Suggestions

State the scope guard (not S1 auth pre-flight, not EQS/vetoes) once and reference it by anchor instead of repeating it verbatim in the intro, Instructions, and the standalone Scope guard block.

Replace the abstract "≥ threshold" inbox-placement comparison with the concrete numeric threshold per profile, or point clearly to where the threshold lives in send-benchmark.md.

Trim repeated SEND-S / EQS / S1-S2-N1-D1 jargon in prose where a single mention would carry the same meaning.

Dimension	Reasoning	Score
Conciseness	Largely substantive but padded: the scope guard ("does NOT run S1 auth pre-flight / does NOT compute EQS") is repeated verbatim three times and the SEND-S / EQS / S1-S2-N1-D1 jargon recurs heavily, which are unnecessary tokens.	3 / 5
Actionability	Concrete guidance with named exports, per-provider table, the 0.1% complaint threshold, NEEDS_INPUT semantics, and memory file paths; minor gaps include the inbox-placement threshold left as an abstract "≥ threshold" with no concrete number and only one executable command.	4 / 5
Workflow Clarity	The 8-step Instructions sequence is clearly ordered with explicit guardrails at each step (NEEDS_INPUT / never pass-by-default, binding_status: incomplete, no-baseline rule) and a "Done when" checklist closing the process.	5 / 5
Progressive Disclosure	The body is a clear overview pointing one level deep to references/placement-telemetry-checklist.md (a real file holding the per-provider tables and delta procedure) and sibling docs, each listed with a one-line purpose; content is appropriately split and easy to navigate.	5 / 5
	Total	17 / 20 Passed

Description

92%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, highly specific description with explicit trigger phrases, clear what/when structure, and deliberate boundary-setting against sibling skills. Its only weakness is the trailing non-English SEO keywords and slightly narrow synonym coverage on the trigger side.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete outputs — "per-provider inbox/spam/promotions placement read", "domain/IP reputation trend from Postmaster + SNDS", "send-over-send delta with named regressions", and "a reusable SEND-S placement snapshot" — giving comprehensive coverage of what the skill produces.	5 / 5
Completeness	Explicitly answers both — "Use when the user asks to ..." gives concrete trigger phrases (when) and "produces ..." lists the deliverables (what), satisfying the top anchor.	5 / 5
Trigger Term Quality	Four verbatim natural-user phrases ("track where my emails are actually landing after I send", "did placement drop after my last send") plus named vendor nouns users say (Gmail Postmaster, Microsoft SNDS, seed-list), but the trailing Chinese SEO keywords are not natural triggers and synonym coverage is narrower than the anchor.	4 / 5
Distinctiveness Conflict Risk	Explicit de-confliction clauses ("Not for the pre-send SPF/DKIM/DMARC auth pre-flight — use deliverability-qa; not for computing the EQS or running the vetoes — use email-quality-auditor") carve a clear niche with minimal overlap risk.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 25 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: email/deliver/inbox-placement-monitor/SKILL.md
Commit: 888dd38

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.