search-term-miner

Use when the user asks to "mine my search terms", "find new keywords from converting queries", "build a negative-keyword list", or "cut wasted paid spend"; harvests converting queries into new keywords/ad-groups, builds a standing negative-keyword list and an n-gram waste report from the search-terms export, and delivers a maintenance diff (add / negate / move). Not for account structure — use campaign-architect; not for budget split — use budget-optimizer; not for computing the final RQS — use ad-account-auditor. 付费广告搜索词挖掘/否定关键词/浪费词清单

Quality

92%

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

85%Weight 40%Scale 1-3

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

The content is a well-structured, actionable instruction set with a clear sequenced workflow, validation gate, completion checklist, and appropriately signaled external references. Its only weakness is mild redundancy in re-stating the scope/delegation boundaries across multiple sections.

Suggestions

Consolidate the scope/delegation carve-outs into a single 'Scope guard' section and reference it from the intro and 'Next Best Skill' instead of restating the campaign-architect/budget-optimizer/ad-account-auditor boundaries three times.

Move the relative-path-heavy cross-skill links (campaign-architect, budget-optimizer, ad-account-auditor) into the existing 'Reference Materials' / 'Next Best Skill' sections only, removing duplicates from the intro and Skill Contract to tighten token use.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the scope/delegation statement is repeated across the intro, the 'Scope guard' block, 'Reference Materials', and 'Next Best Skill', so it could be tightened.	2 / 3
Actionability	Each instruction step gives concrete, specific guidance (e.g. 'tokenize the non-converting queries into 1-/2-/3-grams, sum Measured cost per token', 'assign each a match type (exact/phrase negative) and the level (ad-group vs campaign vs shared list)'); for an instruction-only skill this is fully actionable.	3 / 3
Workflow Clarity	A clear 7-step sequence is paired with an explicit validation gate ('If the conversion column is missing, stop and ask') and a 'Done when' completion checklist, satisfying the 'clear sequence with explicit validation steps; checklists for complex processes' anchor.	3 / 3
Progressive Disclosure	The body is a concise overview split into well-organized sections with one-level-deep, clearly signaled markdown references (skill-contract.md, roas-benchmark.md, CONNECTORS.md, SECURITY.md) and no bundle files to validate, matching the 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a strong, third-person statement with explicit natural-language triggers, multiple concrete capabilities, and explicit disambiguation from adjacent skills. It cleanly satisfies the what/when/which-skill requirements.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'harvests converting queries into new keywords/ad-groups, builds a standing negative-keyword list and an n-gram waste report', and 'delivers a maintenance diff (add / negate / move)' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It explicitly states what it does (harvest/n-gram/diff) and when to use it via an explicit 'Use when...' clause, satisfying the 'clearly answers both what AND when' anchor.	3 / 3
Trigger Term Quality	The 'Use when the user asks to "mine my search terms", "find new keywords from converting queries", "build a negative-keyword list", or "cut wasted paid spend"' phrasing gives natural terms a user would actually say, matching the 'good coverage of natural terms' anchor.	3 / 3
Distinctiveness Conflict Risk	Explicit 'Not for account structure — use campaign-architect; not for budget split — use budget-optimizer; not for computing the final RQS — use ad-account-auditor' carve-outs give it a clear niche unlikely to conflict with sibling skills.	3 / 3
	Total	12 / 12 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: 19 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: ad/research/search-term-miner/SKILL.md
Commit: 4a77c48

Reviewed: 9 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.