content-amplifier

Use when the user asks to "amplify influencer content with paid media", "set up whitelisting or Spark Ads", "decide which posts to boost", "repurpose influencer content", "turn one video into multiple ads", or "build a UGC asset library"; produces (paid mode) a content-selection scorecard, a paid amplification strategy (whitelisting/boosting/dark posts), audience targeting, and a budget+optimization plan, or (repurpose mode) a rights-tracked content inventory, a 1-video-to-10+-asset repurposing map, per-format transformation specs, and a 30-day distribution plan. Not for gating whether a deliverable is publishable or FTC-compliant — use creator-content-auditor; not for the always-on brand posting calendar — use social-calendar-builder; not for drafting a net-new idea into platform-native packages — use social-creative-builder. 复用达人内容 / 内容放量.

Quality

88%

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.

The body is well-structured with strong workflow validation and clean progressive disclosure to real bundle files. Its main weakness is conciseness: the compliance/rights-gating rules are repeated across many sections rather than defined once and referenced.

Suggestions

Define the rights-gating and NOT_SCORED/NEEDS_INPUT rules once in the Skill Contract, then reference them from the per-step Instructions, Decision Gates, and Example instead of restating them nearly verbatim each time.

Consolidate the repeated 'never substitute Estimated / never infer approval or rights' clauses into a single 'Evidence rules' subsection that downstream sections link to.

The Data Sources and Instructions sections both restate the missing-evidence handling; keep the canonical version in Instructions and prune the duplicate from Data Sources.

Dimension	Reasoning	Score
Conciseness	Mostly efficient procedural content with no general-knowledge padding, but the same gating rules (NOT_SCORED/NEEDS_INPUT, rights-must-be-active+dated+evidenced, never-substitute-Estimated) are restated near-verbatim across Skill Contract, Data Sources, Instructions, Decision Gates, Example, and Save Results — could be tightened by stating once and referencing.	3 / 5
Actionability	Concrete numbered steps per mode with specific field names, status enums ('active\|expired\|revoked\|disputed\|unknown'), a naming convention, and a KPI list (CPM/CTR/CPC/CVR/ROAS); the fill-in execution is delegated to templates.md anchors rather than inlined, a minor gap.	4 / 5
Workflow Clarity	Both modes have clear 1-7 sequences with explicit validation checkpoints — Step 7 fail-closed rights verification, 'Stop and ask'/'Continue silently' gates, per-mode 'Done when' criteria, and NEEDS_INPUT → request evidence → re-evaluate feedback loops for these batch/paid-spend operations.	5 / 5
Progressive Disclosure	Clear overview body points one level deep to the 646-line references/templates.md (verified present) and references/atom-extraction.md (verified present), with well-signaled per-step anchors and a consolidated Reference Materials section for easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

100%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: it states concrete capabilities for both modes, uses natural trigger phrases, answers what and when explicitly, and clearly delineates from three sibling skills. No verbosity or fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions across both modes — 'content-selection scorecard', 'amplification strategy (whitelisting/boosting/dark posts)', 'audience targeting', 'budget+optimization plan', 'rights-tracked inventory', '1-video-to-10+-asset repurposing map', 'per-format transformation specs', '30-day distribution plan' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (the two mode deliverables) and when ('Use when the user asks to...') with concrete trigger phrases, and adds 'Not for...' boundary clauses.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural phrases users would actually say — 'amplify influencer content with paid media', 'set up whitelisting or Spark Ads', 'decide which posts to boost', 'repurpose influencer content', 'turn one video into multiple ads', 'build a UGC asset library' — including synonyms and a Chinese trigger pair.	5 / 5
Distinctiveness Conflict Risk	Clear niche with explicit conflict avoidance — 'Not for gating... use creator-content-auditor; not for the always-on brand posting calendar... use social-calendar-builder; not for drafting a net-new idea... use social-creative-builder' — minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

75%

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 — 12 / 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: 1 missing, 31 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: influencer/activate/content-amplifier/SKILL.md
Commit: 64562bc

Reviewed: 1 day 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.