SLA Reports Plugin

Version: 1.0 | Author: Plugin Factory | Domain: IT-MSP

Generate polished monthly SLA performance reports for MSP clients from PSA ticket CSV exports — as an alternative to BrightGauge for small MSPs at Included with your subscription.

Installation

1. Download the pf-sla-reports.plugin file
2. Open Claude Desktop and navigate to Settings > Plugins
3. Click Install Plugin and select the downloaded .plugin file
4. The plugin will be installed and available immediately

Note: All data stays local on your machine. No external API calls or cloud storage required.

What It Does

SLA Reports turns a 2-hour monthly reporting process into a 15-minute workflow:

1. Export tickets from ConnectWise, Autotask, or any PSA tool as CSV
2. Drop the file in inbound/ and run one command
3. Get a professional DOCX report + email-ready executive summary

Target SaaS Alternative: BrightGauge / ConnectWise Reports & Dashboards ($3,600–7,200/yr)

Quick Start

/sla:sla-setup        ← Run once to configure your MSP profile

Then for each reporting period:

# 1. Drop your PSA export in inbound/tickets.csv
/sla:sla-run "Client Name" 2026-02    ← Full pipeline in one command

Commands

Command	Description
/sla:sla-setup	Initialize workspace and configure MSP profile
/sla:sla-run	Run the complete pipeline end-to-end
/sla:sla-ingest	Parse and normalize PSA ticket CSV
/sla:sla-calculate	Compute all SLA KPIs and compliance metrics
/sla:sla-generate	Generate the DOCX client report
/sla:sla-summary	Generate the email-ready executive summary
/sla:sla-dashboard	Interactive visual dashboard — "show me"
/sla:sla-status	View pipeline progress and workspace health
/sla:sla-config	View or update MSP SLA configuration

Supported PSA Formats

• ConnectWise Manage — auto-detected from column headers
• Autotask PSA — auto-detected from column headers
• Generic CSV — flexible column header matching (7+ aliases per field)

Export instructions:

• ConnectWise: Reports → Service Tickets → Export CSV
• Autotask: Reports → Ticket Report → Export

Metrics Generated

• Response compliance % (if first_response_at column present)
• Resolution compliance %
• MTTR (Mean Time to Resolve)
• MTTFR (Mean Time to First Response)
• SLA breach count and breach detail table
• Per-priority breakdown (P1/P2/P3)
• Month-over-month trend flags (if prior period archive exists)
• Uptime % (if inbound/uptime.csv provided)

Folder Structure

After setup, your workspace contains:

inbound/        ← Drop tickets.csv here before running
processing/     ← Intermediate JSON files (do not edit)
outbound/       ← Final DOCX report and summary (deliver to client)
archive/        ← Prior period archives (auto-managed)
templates/      ← Report template (customizable)
.sla/           ← Plugin config and state files

Workflow

inbound/tickets.csv
    ↓ /sla:sla-ingest
processing/sla-tickets-normalized.json
    ↓ /sla:sla-calculate
processing/sla-metrics.json
    ↓ /sla:sla-generate          ↓ /sla:sla-summary
outbound/sla-report-*.docx    outbound/sla-summary-*.md

AI-Powered Features

• Ticket Normalization & Parsing: Auto-detects PSA format (ConnectWise, Autotask, or generic CSV) and normalizes ticket data with flexible column header matching
• SLA Metric Calculation: Computes per-ticket response times, resolution times, and aggregates compliance percentages, MTTR, and MTTFR using timezone-aware calculations
• Performance Trend Analysis: Compares current period metrics against archived prior periods to identify compliance improvements or regressions
• Breach Breakdown Analysis: Categorizes SLA breaches by priority level and generates detailed tables showing which tickets missed targets and by how much

Estimated Cost per Use

Disclaimer: Token estimates are approximate and based on typical usage patterns measured from skill prompt sizes. Actual costs vary with input data size, conversation length, and complexity. Estimates use Claude Sonnet 4.6 pricing ($3/1M input, $15/1M output). Cowork and Claude Desktop subscription users (Pro/Max/Team) are not charged per-token — these estimates apply only to direct Anthropic API usage. Running stages individually in fresh sessions uses fewer input tokens than running the full pipeline sequentially, because pipeline mode accumulates conversation history across stages.

Per skill (run individually in a fresh session):

Stage	Skill Prompt	User Input	Total Input	Output	Est. Cost
sla-dashboard	~5.5K	~500	~8.9K	~8.0K	~$0.15
sla-ingest	~3.8K	~2.0K	~8.4K	~2.0K	~$0.06
sla-calculate	~5.8K	~800	~9.3K	~5.8K	~$0.11
sla-summary	~3.1K	~800	~6.6K	~6.0K	~$0.11
sla-generate	~4.7K	~800	~8.2K	~6.0K	~$0.11
Standalone total			~41.3K	~27.8K	~$0.54

Full pipeline (all stages in one session — context accumulates):

Stage	Base Input	+ History	Total Input	Output	Est. Cost
sla-dashboard	~9.0K	0	~9.0K	~8.0K	~$0.15
sla-ingest	~8.8K	~8.5K	~17.3K	~2.0K	~$0.08
sla-calculate	~9.6K	~12.5K	~22.1K	~5.8K	~$0.15
sla-summary	~6.9K	~19.1K	~26.0K	~6.0K	~$0.17
sla-generate	~8.5K	~25.9K	~34.4K	~6.0K	~$0.19
Pipeline total			~108.8K	~27.8K	~$0.74

Running the full pipeline once typically costs $0.52–$0.97 in API tokens (Claude Sonnet 4.6).

Known Limitations

1. No live API integration: Requires a manual CSV export from the PSA tool. Real-time data is not supported — this is intentional to avoid complex API credential management.

2. No business-hours SLA calculation: All response and resolution times are computed in calendar minutes/hours. Business-hours-only SLA (e.g., 9am–5pm weekdays) is not supported in v1.0.

3. Uptime calculation is simple averaging: If inbound/uptime.csv contains per-device uptime rows, the plugin computes a simple average. Weighted uptime (by device criticality) is not supported.

4. Single client per run: Each pipeline run processes one client's tickets. To run multiple clients, run the pipeline once per client with different inbound/tickets.csv files.

5. P3 and Unknown priorities use P2 targets: If your SLA contract defines separate P3 targets, configure them by extending the config manually after setup (P3 support in the UI is planned for v0.2.0).

6. No automated report delivery: The plugin saves reports to outbound/ — emailing or uploading to client portals is not automated.

Requirements

• Python 3.8+
• python-docx (auto-installed by setup)
• openpyxl (auto-installed by setup — for XLSX input support)
• python-dateutil (auto-installed by sla-calculate)
• pytz (auto-installed by sla-calculate)

Version History

See CHANGELOG.md for version history.

Important Disclaimers

• AI-Generated Content: This plugin uses AI (LLM) technology which can produce inaccurate or incomplete outputs. All content should be treated as a starting point and reviewed for accuracy before use.
• Not Professional Advice: Outputs do not constitute legal, financial, tax, medical, or other professional advice. Consult qualified professionals before making decisions based on generated content.
• No Compliance Guarantee: References to industry standards, regulations, or guidelines are for informational purposes only. This plugin does not guarantee compliance with any law or regulation. Users are responsible for verifying all outputs meet their specific regulatory requirements.
• No Endorsement or Affiliation: Mention of third-party products, standards, or organizations does not imply endorsement, partnership, or certification by those entities.