client-communication-standards
Skill72 starsChanged 4 months agoMITView on GitHub
Client-facing report formatting standards. Auto-invoke when creating client summaries, investigation reports, monthly reviews, performance analyses, or any communication for stakeholders. Applies mandatory Background → Analysis → Conclusions framework with required "What We Looked At" data source attribution for all findings.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Vibha-Ramprakash/automate-google-adsword for word, first seen Sep 14, 2026
Other versions1 project uses a version of this.
Word for word · 1
- Vibha-Ramprakash/automate-google-ads★ 0100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository41 other files it gives its agents.
- account-diagnosticSkill
- ad-copy-generation-frameworkSkill
- ad-copy-verification-standardSkill
- add-account-negative-keywordsSkill
- ads-checkerSkill
- budget-guardianSkill
- budget-recommendation-calculatorSkill
- change-history-checkerSkill
- competitor-analysis-v2Skill
- conversion-tracking-healthSkill
- dgen-automation-disableSkill
- fair-housing-complianceSkill
- ga4-campaign-cross-referenceSkill
- ga4-cross-analysisSkill
- ga4-lead-quality-investigationSkill
- gaql-query-patternsSkill
- geo-conflict-analyzerSkill
- google-ads-api-setupSkill
- google-ads-querySkill
- google-ads-samplesSkill
- impression-share-diagnosticsSkill
- investigation-methodologySkill
- lead-quality-pattern-analysisSkill
- lead-quality-recommendation-prioritizationSkill
- markdown-to-sheets-presenterSkill
- mcc-hack-auditSkill
- mutation-safetySkill
- neg-conflict-finderSkill
- non-serving-keyword-scannerSkill
- pmax-asset-automationSkill
- pmax-builderSkill
- portfolio-health-prioritizationSkill
- portfolio-pacing-rulesSkill
- rsa-bulk-editSkill
- rsa-refreshSkill
- rsa-single-accountSkill
- shared-budget-updaterSkill
- sqr-classifierSkill
- sqr-pipelineSkill
- underspending-investigationSkill
- youtube-placement-auditSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
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
- Distinctive: line 28
CRITICAL: Use EXACTLY 3 sections (no more, no less)
- Distinctive: line 39
Keep concise (2-3 paragraphs maximum)
- Distinctive: line 127
Use tables for clarity:
- Distinctive: line 206
When client should expect changes
- Distinctive: line 207
When to review/reassess
- Distinctive: line 257
Add extra sections beyond the 3 (keep to exactly 3)
- Distinctive: line 261
Use jargon without explanation (ROAS, CPC, CTR need context for some clients)
- Distinctive: line 265
Keep it concise (Background = 2-3 paragraphs)
- Distinctive: line 268
Use tables for data comparisons (improves readability)
- Distinctive: line 337
Before sending any client communication, verify:
≈ “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.
Files
Client Communication Standards Skill
Purpose: Ensures all client-facing communications follow the "Background → Analysis → Conclusions" framework with proper data transparency.
Type: Communication standards skill (auto-invoked for client reports)
What This Skill Deliberately Does NOT Do
- Do the analysis. The framework structures what you found — the investigation itself happens upstream (see
investigation-methodology). If the analysis is thin, this framework exposes that; it can't fix it. - Verify the data. "What We Looked At" makes every data source transparent; it doesn't audit whether the numbers are right. Attribution is not verification.
- Apply to internal docs. This is for client-facing deliverables only — technical implementation details deliberately stay out of the report (they're for internal notes).
- Deliver the report. Output is the formatted communication; sending, presenting, or scheduling it is yours.
Core Framework: Background → Analysis → Conclusions
When to use: Investigation summaries, monthly reviews, strategy presentations, performance reports for client stakeholders
CRITICAL: Use EXACTLY 3 sections (no more, no less)
Section 1: Background
Purpose: Set context for the reader
What to include:
- Client concern (what they're seeing/experiencing)
- Investigation scope (what we analyzed and why)
- Keep concise (2-3 paragraphs maximum)
Example:
## Background
Example Account PMAX campaign performance declined from 23x ROAS in August to
16x ROAS in October, prompting client concern about campaign efficiency.
The client wanted to understand whether this decline was campaign-related
or market-driven.
We conducted a comprehensive analysis of search demand trends, competitive
landscape, and campaign performance metrics across multiple time periods
to identify root causes.Section 2: Analysis
Purpose: Present data findings with full transparency
REQUIRED for every finding:
- "What We Looked At:" statement showing data source
- Logical sequence of findings
- Data presented in tables when comparing periods/channels
- Each subsection ends with "Finding:" statement (key insight)
"What We Looked At" Requirements
MUST specify:
- Which report/tool (Search term reports, Google Trends, Google Ads API, GA4, etc.)
- Time period analyzed (last 30 days, Sep 1 - Oct 1, year-over-year, etc.)
- Methodology used (categorization, statistical analysis, correlation, etc.)
- Any filters/segments applied
Format:
**What We Looked At:** [Data source], [time period], [methodology]✅ Good Examples:
**What We Looked At:** Search term reports from Google Ads for three time
periods (March-April 2025, August-September 2025, September-October 2025),
categorizing each query as high-intent, informational, or brand.
**Finding:** High-intent search queries decreased 35% from August to October.**What We Looked At:** Google Trends data for apartment-related searches
in the NYC market over a 5-year period to identify seasonal demand patterns.
**Finding:** Apartment search demand follows predictable seasonal decline
of 25-50% from peak (March-August) to low season (October-January).**What We Looked At:** GA4 conversion data for Example Account PMAX campaign
(last 30 days), analyzing landing page distribution, user geography, and
device patterns to identify lead quality signals.
**Finding:** 70% of conversions originated from blog/informational pages
rather than property listing pages, indicating potential traffic quality issues.❌ Bad Examples:
Search CPC increased 274%❌ Missing: What data source? What time period? How calculated?
We found that conversions dropped significantly.❌ Missing: What data? What time period? How much is "significantly"?
Campaign performance declined due to seasonality.❌ Missing: What data proved this? What analysis was done?
Data Presentation Format
When comparing periods: Use tables for clarity:
| Metric | August | October | Change |
|--------|--------|---------|--------|
| ROAS | 23.1x | 16.9x | -27% |
| CPC | $2.10 | $5.75 | +274% |
| Conversions | 245 | 180 | -27% |When presenting multi-dimensional data: Break into subsections with clear headers:
### Search Demand Analysis
**What We Looked At:** [data source]
[Present findings]
**Finding:** [key insight]
### Competitive Landscape Analysis
**What We Looked At:** [data source]
[Present findings]
**Finding:** [key insight]Section 3: Conclusions
Purpose: Tie everything together with action plan
REQUIRED subsections:
What's Happening (The Dynamics)
- Explain cause-and-effect relationships
- Connect findings from Analysis section
- Show how different factors interact
- Tell the complete story
Example:
## Conclusions
### What's Happening
Example Account's 27% ROAS decline is primarily driven by seasonal market shifts,
not campaign issues. Apartment search demand declined 25% from August to
October (Google Trends), while competitive pressure increased (274% CPC
increase). The campaign is performing as expected given market conditions.What We're Doing About It
- Actions already taken (if any)
- Recommended next steps
- Specific, actionable items
- Owner/timeline for each action
Example:
### What We're Doing About It
**Immediate Actions (Already Implemented):**
1. Reduced daily budget from $750 to $600 to align with lower demand
2. Paused underperforming ad variants in brand campaign
**Recommended Next Steps:**
1. Monitor weekly through November for further seasonal decline
2. Prepare for demand recovery in January-February (budget increase)
3. Consider increasing brand campaign cap to 20% during low season
(brand maintains 35x ROAS vs 17x for PMAX)Expected Timeline
- When client should expect changes
- When to review/reassess
- Key dates or milestones
Example:
### Expected Timeline
- **Through November:** Continued ROAS pressure (expect 15-18x range)
- **December-January:** Seasonal low point (12-15x ROAS expected)
- **February-March:** Demand recovery begins (return to 20x+ ROAS)
- **Next Review:** Mid-November (assess if additional adjustments needed)Key Takeaways for Client
- 3-5 bullet points summarizing everything
- Written for non-technical stakeholders
- Focus on business impact, not technical details
Example:
### Key Takeaways
- Example Account PMAX is performing as expected given seasonal market decline
- ROAS drop is market-driven (25% demand decrease), not campaign quality
- Budget reduced proactively to maintain efficiency during low season
- Performance will recover naturally in Q1 2026 as demand returns
- No major campaign restructuring needed - this is normal seasonalityWhy This Framework Works
For Clients:
- Matches how they think (problem → evidence → solution)
- Data transparency builds credibility ("What We Looked At")
- Clear action plan reduces anxiety
- Timeline sets expectations
For You:
- Consistent format across all reports
- Forces rigorous analysis (must show data sources)
- Prevents unsupported claims
- Creates reproducible methodology
What NOT to Do
❌ Don't:
- Add extra sections beyond the 3 (keep to exactly 3)
- Present data without source attribution (always include "What We Looked At")
- Include technical implementation details (save for internal notes)
- Make recommendations without supporting data
- Use jargon without explanation (ROAS, CPC, CTR need context for some clients)
- Skip the "Expected Timeline" (clients need to know when things will improve)
✅ Do:
- Keep it concise (Background = 2-3 paragraphs)
- Show your work (Analysis = transparent methodology)
- Be specific (Conclusions = actionable steps with owners/timelines)
- Use tables for data comparisons (improves readability)
- End with Key Takeaways (executives read this first)
Templates & Examples
Template Location:
templates/client_summary_template.md (ships with this skill — copy it as the starting point for each report)
Example Reports:
Save your example client reports in your project's documents/output folder for reference.
Format Variations by Report Type
Investigation Summary (Most Common)
- Background: Issue description + scope
- Analysis: Data findings with "What We Looked At" for each
- Conclusions: Root cause + action plan + timeline
Monthly Performance Review
- Background: Month overview + KPIs checked
- Analysis: Performance vs targets (with data sources)
- Conclusions: What changed + why + what's next
Strategy Presentation
- Background: Current state + strategic question
- Analysis: Options evaluated (with supporting data)
- Conclusions: Recommended strategy + implementation plan
Data Transparency Best Practices
Always Attribute:
- Google Ads reports (specify which report, time period)
- GA4 data (property, conversion events, date range)
- Google Trends (search terms, geography, time period)
- Third-party tools (Semrush, Google Search Console, etc.)
- Internal spreadsheets (specify tab name, date updated)
Methodology Clarity:
- Categorization: "categorizing each query as high-intent, informational, or brand"
- Statistical: "calculating year-over-year change for each metric"
- Correlation: "correlating CPC increases with impression share changes"
- Segmentation: "segmenting conversions by landing page type"
Integration with Agents
This skill auto-loads when:
- Creating client summaries or reports
- Writing investigation findings
- Documenting performance reviews
- Generating monthly reports
- User asks to "create a summary for the client"
- User mentions "client-facing" or "stakeholder report"
Agents that use this skill:
- Any agent creating client-deliverable output (investigation agents, performance review agents, monthly reporting agents)
- Replace with your own agents as needed — this skill is protocol-only and works with any agent setup
Quality Checklist
Before sending any client communication, verify:
- Exactly 3 sections (Background, Analysis, Conclusions)
- Every data finding has "What We Looked At" statement
- "What We Looked At" specifies: data source, time period, methodology
- Analysis section uses tables for comparisons
- Each analysis subsection ends with "Finding:" statement
- Conclusions include: What's Happening + What We're Doing + Timeline + Key Takeaways
- Key Takeaways has 3-5 bullet points
- No technical jargon without explanation
- Action items are specific with owners/timelines
- Timeline sets realistic expectations
When to Load Other Skills
| Skill | When |
investigation-methodology | Upstream, during the investigation itself — its Step 4 (Present Findings) hands root cause + evidence to this framework whenever the audience is a client |
| Reporting-stage producing skills | Skills that generate client-deliverable findings route here for formatting — in this repo: conversion-tracking-health, ga4-lead-quality-investigation, lead-quality-recommendation-prioritization |
Related Documentation
- Your own CLAUDE.md — for any project-specific reporting conventions
templates/client_summary_template.md— blank template (ships with this skill)- Your own examples folder — store delivered client reports for reference
Created: 2025-10-28 Based On: Client communication best practices Status: Active - MANDATORY FOR CLIENT REPORTS
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
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.

