agentleFS
Sign inStart free
Eugenevdm01Eugenevdm01/eugenes-meta-agent/skills/performance-reporting/SKILL.md

performance-reporting

Skill4 starsChanged 6 months agoMITView on GitHub

Produce clean daily and weekly reports, summarize what to do next, and spot trends. Use when generating executive summaries and action-oriented recommendations.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When generating daily or weekly performance reports for active campaigns.

    line 12
  2. Distinctive:

    When summarizing the results of split tests or new creative launches.

    line 13
  3. Distinctive:

    When identifying trends in CPL, CTR, conversion rates, and downstream quality.

    line 14
  4. Distinctive:

    When providing executive summaries and action-oriented recommendations.

    line 15
  5. Distinctive:

    Summarize Findings: Create a concise overview of the data, highlighting key takeaways.

    line 27
  6. Distinctive:

    Use clear, concise language and avoid jargon where possible.

    line 42
  7. Distinctive:

    Ensure all recommendations are supported by evidence from the data.

    line 43
  8. Distinctive:

    If a critical issue arises (e.g., broken tracking, sudden drop in conversion rate), escalate immediately to the user.

    line 46
  9. Distinctive:

    If a recommendation requires significant resources or time, request approval before proceeding.

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Performance Reporting Agent

Purpose

Produce clean daily and weekly reports, summarize what to do next, and spot trends. Ensure all stakeholders have a clear understanding of campaign performance and actionable insights.

When to Use This Skill

  • When generating daily or weekly performance reports for active campaigns.
  • When summarizing the results of split tests or new creative launches.
  • When identifying trends in CPL, CTR, conversion rates, and downstream quality.
  • When providing executive summaries and action-oriented recommendations.

Inputs Required

  • Daily or weekly performance data (spend, impressions, CPM, CTR, CPC, leads, CPL, etc.).
  • Downstream funnel data (landing page views, form completions, booked calls, qualified leads).
  • Any significant changes or tests launched during the reporting period.
  • The target KPIs for the campaigns.

Step-by-Step Workflow

  1. Gather Data: Collect all relevant performance metrics for the reporting period.
  2. Analyze Trends: Identify any significant shifts in performance (e.g., rising CPL, declining CTR).
  3. Summarize Findings: Create a concise overview of the data, highlighting key takeaways.
  4. Develop Recommendations: Formulate actionable steps based on the findings (e.g., pause losing ads, scale winning ones, test new creatives).
  5. Format Report: Structure the report for clarity and readability, using tables and charts where appropriate.
  6. Distribute Report: Share the report with the relevant stakeholders.

Output Format

Provide a structured performance report containing:

  • Executive Summary: High-level overview of performance trends.
  • Key Metrics: A table or chart showing the most important KPIs.
  • Trend Analysis: A detailed breakdown of any significant shifts in performance.
  • Actionable Recommendations: A prioritized list of steps to take next.
  • Appendix: Any supporting data or charts.

Decision Rules

  • Always focus on actionable insights, not just raw data.
  • Use clear, concise language and avoid jargon where possible.
  • Ensure all recommendations are supported by evidence from the data.

Escalation Rules

  • If a critical issue arises (e.g., broken tracking, sudden drop in conversion rate), escalate immediately to the user.
  • If a recommendation requires significant resources or time, request approval before proceeding.

Templates & Resources

  • report-templates/daily-report.md: Template for daily performance reports.
  • report-templates/weekly-report.md: Template for weekly performance reports.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free