performance-report skill
✓ VerifiedGenerates affiliate performance reports with KPI dashboards, program rankings, and actionable optimization recommendations.
- GitHub stars
- 779
- Files
- 4
- Last commit
- Oct 19, 2026
- License
- MIT
- Allowed tools
- —
What does the performance-report skill do?
performance-report generates affiliate performance reports with KPI dashboards, program rankings, and actionable optimization recommendations.
Summary generated from the skill's SKILL.md.
About the performance-report skill
Analyzing affiliate earnings and program efficiency is what this skill enables for professional marketers. It transforms raw data like clicks, conversions, and revenue into structured Markdown reports containing KPI dashboards and program rankings. When an agent loads this skill, it can process program-specific metrics to calculate essential values such as Earnings Per Click (EPC), conversion rates, and Return on Ad Spend (ROAS).
Users provide program names alongside their performance metrics for a specific period, such as a week or a month. The tool identifies high-performing stars and underperforming dogs, providing specific recommendations like doubling down on high EPC programs or phasing out low-volume ones. It is particularly useful when chained with conversion tracking tools to turn collected link data into actionable business intelligence. The output includes trend analysis if previous period data is provided, helping users understand if their revenue or conversion rates are moving up or down.
What an agent can do with it
- 1Generate monthly performance summariesCreate a comprehensive Markdown report detailing total revenue, blended EPC, and conversion rates for all active affiliate programs.
- 2Rank affiliate programs by ROISort a list of programs by their efficiency to identify which ones should be scaled and which should be dropped.
- 3Compare period-over-period trendsAnalyze how revenue and click trends have changed compared to the previous month or week.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the performance-report skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the performance-report skill in Plugin
/plugin marketplace add Affitor/affiliate-skills /plugin install analytics-skills@affiliate-skills
Install the performance-report skill in Claude Code
~/.claude/skills/performance-report/SKILL.md
$ npx degit Affitor/affiliate-skills/skills/analytics/performance-report ~/.claude/skills/performance-reportInstall the performance-report skill in Claude Code (project)
.claude/skills/performance-report/SKILL.md
$ npx degit Affitor/affiliate-skills/skills/analytics/performance-report .claude/skills/performance-reportInstall the performance-report skill in Codex
~/.agents/skills/performance-report/SKILL.md
$ npx degit Affitor/affiliate-skills/skills/analytics/performance-report ~/.agents/skills/performance-reportInstall the performance-report skill in Gemini CLI
~/.gemini/skills/performance-report/SKILL.md
$ npx degit Affitor/affiliate-skills/skills/analytics/performance-report ~/.gemini/skills/performance-reportInstall the performance-report skill in Claude.ai
npx degit Affitor/affiliate-skills/skills/analytics/performance-report performance-report && zip -r performance-report.zip performance-report # claude.ai → Customize → Skills → + → Create skill → Upload a skill → performance-report.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachableaffitor/affiliate-skills/skills/analytics/performance-report is public and reachablegithub.com/affitor/affiliate-skills/tree/HEAD/skills/analyti ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-10-19github.com/affitor/affiliate-skills/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/affitor/affiliate-skills/blob/HEAD/skills/analyti ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/affitor/affiliate-skills/blob/HEAD/skills/analyti ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 226 linesgithub.com/affitor/affiliate-skills/blob/HEAD/skills/analyti ↗Pass
SKILL.md
View on GitHubPerformance Report
Generate weekly or monthly affiliate performance reports — earnings, clicks, conversions, EPC, top performers, underperformers, and trend analysis. Output is a Markdown report with KPI dashboard, program rankings, and actionable recommendations.
Stage
S6: Analytics — Data without analysis is just noise. This skill transforms raw affiliate numbers into insights — which programs are worth your time, which are dragging your portfolio down, and where to focus next. Professional affiliates review performance weekly.
When to Use
- User wants to review their affiliate earnings for a period
- User asks "how are my programs doing?" or "show me my affiliate report"
- User has click/conversion/revenue data and wants analysis
- User wants to compare performance across multiple programs
- User says "weekly report", "monthly report", "earnings breakdown"
- Chaining from S6.1 (conversion-tracker) — analyze the data those links collected
Input Schema
programs:
- name: string # REQUIRED — program name (e.g., "HeyGen")
clicks: number # OPTIONAL — total clicks this period
conversions: number # OPTIONAL — total conversions
revenue: number # OPTIONAL — total commission earned ($)
commission: number # OPTIONAL — commission per sale ($)
spend: number # OPTIONAL — money spent on ads/promotion ($)
period: string # OPTIONAL — "week" | "month" | "quarter"
# Default: "month"
goals:
revenue_target: number # OPTIONAL — target revenue for the period ($)
conversion_target: number # OPTIONAL — target conversions
previous_period: # OPTIONAL — last period's data for trend analysis
- name: string
clicks: number
conversions: number
revenue: number
notes: string # OPTIONAL — context about the period
# (e.g., "launched new blog post week 2")
Chaining context: If S1 program data or S6.1 tracking data exists in conversation, pull program names and any available metrics.
Workflow
Step 1: Collect Program Data
Gather data from user input. If data is incomplete, work with what's available and note gaps:
- "You provided revenue but not clicks — I can calculate revenue per program but not EPC or conversion rate."
Step 2: Calculate KPIs
For each program:
- EPC (Earnings Per Click): revenue / clicks
- Conversion Rate: conversions / clicks × 100
- Revenue Share: program revenue / total revenue × 100
- CPA (Cost Per Acquisition): spend / conversions (if spend provided)
- ROAS (Return on Ad Spend): revenue / spend (if spend provided)
- Commission Per Sale: revenue / conversions
Portfolio-level:
- Total Revenue: sum of all program revenue
- Blended EPC: total revenue / total clicks
- Blended Conversion Rate: total conversions / total clicks × 100
- Top Performer: highest EPC program
- Underperformer: lowest EPC program
Step 3: Rank Programs
Sort programs by ROI efficiency:
- EPC (primary sort)
- Total revenue (secondary)
- Conversion rate (tertiary)
Assign labels:
- Star: High EPC + high volume → double down
- Cash Cow: Moderate EPC + high volume → maintain
- Question Mark: High EPC + low volume → scale up
- Dog: Low EPC + low volume → consider dropping
Step 4: Identify Trends
If previous_period data is provided:
- Revenue trend: up/down/flat (with percentage)
- Click trend: up/down/flat
- Conversion trend: up/down/flat
- Per-program trends
Step 5: Generate Recommendations
Based on data:
- Double down: Programs with high EPC that need more traffic
- Optimize: Programs with high traffic but low conversion (content issue)
- Phase out: Programs with low EPC and low volume
- Investigate: Programs with unusual patterns (sudden drops)
Step 6: Self-Validation
Before presenting output, verify:
- EPC calculation correct: revenue ÷ clicks
- Conversion rate percentages are accurate
- Revenue shares across programs sum to ~100%
- Labels match metrics: Star (high EPC + growth), Cash Cow (high revenue + stable), Question Mark (low data), Dog (declining)
- Recommendations are specific and reference concrete next steps
If any check fails, fix the output before delivering. Do not flag the checklist to the user — just ensure the output passes.
Output Schema
output_schema_version: "1.0.0" # Semver — bump major on breaking changes
report:
period: string
total_revenue: number
total_clicks: number
total_conversions: number
blended_epc: number
blended_conversion_rate: number
goal_progress: string # "on_track" | "behind" | "ahead" | "no_goal"
programs:
- name: string
clicks: number
conversions: number
revenue: number
epc: number
conversion_rate: number
revenue_share: number # percentage of total
label: string # "star" | "cash_cow" | "question_mark" | "dog"
trend: string # "up" | "down" | "flat" | "new"
recommendations:
- program: string
action: string # "double_down" | "optimize" | "phase_out" | "investigate"
reason: string
next_step: string # specific action to take
Output Format
- KPI Dashboard — summary table with total revenue, clicks, conversions, blended EPC
- Program Rankings — table sorted by EPC with labels (Star/Cash Cow/Question Mark/Dog)
- Trend Analysis — period-over-period comparison (if previous data provided)
- Recommendations — prioritized list of actions per program
- Goal Progress — progress toward targets (if goals provided)
Error Handling
- No data provided: "I need your affiliate numbers to generate a report. At minimum, provide: program names and revenue. Ideally also clicks and conversions. You can get these from your affiliate dashboard or tracking tool."
- Only one program: Generate the report for one program. Note: "With only one program, I can't do comparative analysis. Consider adding more programs to diversify. Use S1 (affiliate-program-search) to find complementary programs."
- Missing clicks (revenue only): "Without click data, I can rank programs by revenue but can't calculate EPC or conversion rate. EPC is the most important affiliate metric — consider setting up tracking with S6.1 (conversion-tracker)."
Examples
Example 1: Monthly multi-program report
User: "Monthly report: HeyGen — 500 clicks, 15 conversions, $450. Semrush — 1200 clicks, 8 conversions, $320. Notion — 300 clicks, 25 conversions, $125." Action: Calculate KPIs. HeyGen: EPC $0.90, CR 3.0% (Star). Semrush: EPC $0.27, CR 0.7% (Question Mark — high traffic, low conversion). Notion: EPC $0.42, CR 8.3% (Cash Cow — high conversion, low revenue per sale). Recommend: Scale HeyGen traffic, optimize Semrush content (CTAs, landing page), maintain Notion.
Example 2: Week-over-week comparison
User: "This week vs last week: HeyGen clicks went from 100 to 150, but conversions dropped from 5 to 3." Action: Flag conversion rate drop (5% → 2%). Diagnose: more traffic but lower quality? New traffic source? Landing page change? Recommend: Check traffic sources, run S6.4 (seo-audit) on landing page, test CTAs with S6.2 (ab-test-generator).
Example 3: Revenue-only report
User: "My programs last month: HeyGen $450, Semrush $320, Notion $125, Canva $80." Action: Revenue-only analysis. Total $975. Revenue share: HeyGen 46%, Semrush 33%, Notion 13%, Canva 8%. Note concentration risk (79% from 2 programs). Recommend: Set up click tracking (S6.1) for deeper analysis, consider diversifying with S1 research.
References
references/benchmarks.md— KPI benchmarks by channel, program label thresholds, conversion rate benchmarks, timeline expectations, S1 scoring feedback loopshared/references/affiliate-glossary.md— KPI definitions (EPC, CTR, ROAS). Referenced in Step 2.shared/references/case-studies.md— Real-world case studies with conversion rates and timelines. Use as context for setting realistic expectations.shared/references/flywheel-connections.md— master flywheel connection map
Flywheel Connections
Feeds Into
niche-opportunity-finder(S1) — performance data identifies best-performing nichesaffiliate-program-search(S1) — which program types convert bestcontent-moat-calculator(S3) — content performance metrics for moat progresscontent-decay-detector(S3) — traffic decline data for decay detection
Fed By
conversion-tracker(S6) — conversion data for reportssocial-media-scheduler(S5) — scheduled posts to measureab-test-generator(S6) — test results to include
Feedback Loop
- Performance insights feed back to S1 Research (which niches/programs to pursue) and S2-S4 (which content types and formats perform best) — the analytics-to-research flywheel
chain_metadata:
skill_slug: "performance-report"
stage: "analytics"
timestamp: string
suggested_next:
- "affiliate-program-search"
- "niche-opportunity-finder"
- "content-decay-detector"
Files in this skill
4performance-report skill questions
How do I install the performance-report skill in Claude Code?
Run npx degit Affitor/affiliate-skills/skills/analytics/performance-report ~/.claude/skills/performance-report. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the performance-report skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
How are affiliate programs categorized in the report?
Programs are assigned labels based on EPC and volume: Star (high EPC/high volume), Cash Cow (moderate EPC/high volume), Question Mark (high EPC/low volume), or Dog (low EPC/low volume).
Can I generate a report if I only have revenue data?
Yes, but the analysis will be limited. Without click data, the agent can rank programs by revenue but cannot calculate EPC or conversion rates.