CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

adobe/adobe-analytics

Practitioner-focused agent skills for Adobe Analytics via the AA MCP server — KPI pulse, top movers, conversion funnel analysis, segment performance comparator, and executive briefing.

Quality

83%

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

Overview
Quality
Evals
Security
Files

README.mdskills/

Skills Framework

Overview

This folder contains the Adobe Analytics agent skills shipped with this plugin. Each skill packages instructions, references, and helper assets for a focused Adobe Analytics workflow. This README is for human maintainers; agents should start from each skill's SKILL.md.

Skills inventory

NamePurposeStatus
aa-kpi-pulseKPI digest with period-over-period change and top mover callout.Active
aa-top-movers-watchlistRanks dimension items by biggest gain or loss for a metric.Active
aa-conversion-funnel-analysisStep-by-step fallout analysis across a multi-step conversion funnel.Active
aa-segment-performance-comparatorSide-by-side KPI comparison across two or more audience segments.Active
aa-executive-briefingNarrative performance summary ready for leadership or QBR.Active

Architecture

Each skill lives in skills/<skill-name>/ and is organized as:

  • SKILL.md — canonical skill entry point with frontmatter (name, description, metadata)
  • evals/ — sample prompts and expected outputs used to validate skill behavior
  • scripts/ — helper automation (Python) where the workflow benefits from deterministic processing

Spec compliance

These skills follow the Agent Skills spec at agentskills.io. In practice, that means each skill is centered on a SKILL.md file with YAML frontmatter and keeps supporting materials close by in standard subdirectories.

Adding a new skill

  1. Create a new directory at skills/<new-skill-name>/.
  2. Add SKILL.md with the required frontmatter (name, description, metadata.author, metadata.version) and a phased workflow body.
  3. Add evals/evals.json with at least one representative prompt and expected output.
  4. Put deterministic automation in scripts/ when needed; otherwise keep files local to the skill.
  5. Check the finished layout against the Agent Skills spec before merging.

skills

README.md

.mcp.json

README.md

tile.json