CtrlK
BlogDocsLog inGet started
Tessl Logo

performance-analyzer

Use when the user asks to "analyze influencer campaign performance", "compare influencers", or "find what content worked"; produces metric scorecards vs target and benchmark, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion-attribution breakdowns, and ranked learnings. Not for dollar-level return math — use roi-calculator. 达人营销效果分析/投放复盘

70

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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 a well-sequenced, validation-gated workflow with clean progressive disclosure to a real reference file. Its main weakness is conciseness: guardrail and authorization prose is restated across several sections and could be consolidated without losing safety guarantees.

Suggestions

Consolidate the repeated creator_ref / 'never becomes a saved identity' authorization rules into one Skill Contract stanza and reference it from later steps instead of restating the full constraint each time.

Fold the cross-discipline paid-ads note into a brief pointer (one line) and move the connector-by-connector detail to CONNECTORS.md, which is already referenced.

Inline a compact full worked example (or the Step 2/7 templates) so the analysis can be executed without opening the reference file, raising actionability toward copy-paste ready.

DimensionReasoningScore

Conciseness

Procedural and free of basic-concept padding, but the Skill Contract, cross-discipline note, and Retro-decision paragraphs repeatedly restate identity/authorization guardrails ('never becomes a saved identity', 'do not simulate or carry forward one'), so it could be tightened.

3 / 5

Actionability

An 8-step workflow, one concrete executable command (youtube.py), and an abridged worked example give mostly executable guidance, though the core analytical templates and a full worked example live in the reference file rather than inline.

4 / 5

Workflow Clarity

A clear numbered 8-step sequence with explicit dependency ordering ('run Step 7 before populating Step 2') and concrete validation gates (comparability, complete-scope, preregistered-rule, significance) with Unknown/NEEDS_INPUT fallbacks and retry loops.

5 / 5

Progressive Disclosure

Well-structured overview with a real, present one-level-deep reference (references/analysis-templates.md) and a dedicated 'Reference Materials' section; external sibling pointers are repo-root navigation rather than nested detail layers.

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.

The description is specific, trigger-rich, and complete, answering both what it produces and when to use it with natural user phrasing and an explicit boundary to a sibling skill. It is a strong, low-conflict trigger description.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'metric scorecards vs target and benchmark, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion-attribution breakdowns, and ranked learnings' — matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicit 'Use when...' clause answers when and the 'produces...' clause answers what, with concrete trigger phrases and a negative boundary — both fully and explicitly answered.

5 / 5

Trigger Term Quality

Quotes natural user phrases ('analyze influencer campaign performance', 'compare influencers', 'find what content worked') plus a boundary trigger ('Not for dollar-level return math'), giving comprehensive natural-term coverage.

5 / 5

Distinctiveness Conflict Risk

Clear influencer-performance niche with an explicit handoff boundary to roi-calculator, minimizing overlap and wrong-skill triggering.

5 / 5

Total

20

/

20

Passed

Validation

75%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

referenced_paths_exist

Referenced path issues: 2 missing, 1 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository
aaron-he-zhu/aaron-marketing-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.