job-profitability-analyzer — Claude Code skill: profit analysis
The job-profitability-analyzer Claude Code skill calculates profit by job and client from revenue and costs. It ranks accounts by margin using time records, invoices, materials, subcontractors, and overhead.
MIT 105 installs ★ 440 updated 2026-10-20
npx skills add OneWave-AI/claude-skills --skill job-profitability-analyzer -a claude-codeWhat job-profitability-analyzer does
The skill matches revenue and costs to individual jobs and clients, then calculates profit and margin. It counts labor at a loaded rate, alongside materials, subcontractors, and direct expenses. Overhead is allocated by labor hours by default, with margins shown both before and after overhead.
The results go into profitability-report.md, which ranks jobs and clients by margin dollars and percentage and reports each client's effective hourly rate. For unprofitable jobs, the skill checks invoices and timesheets for causes such as excess hours or work that was never billed. Jobs without cost data receive the status INCOMPLETE rather than an estimated result.
What it helps with
- compare margins across jobs and clients
- find jobs with hours above estimate
- spot work that was never billed
- calculate pricing for a target margin
Example prompts for the agent
- Analyze the invoice, cost, and time-tracking files.
- Rank my clients by margin.
- Why did the
Acme redesignjob lose money?
How to install job-profitability-analyzer
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill job-profitability-analyzer -a claude-code2Manually: put the files in place
~/.claude/skills/job-profitability-analyzer/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/job-profitability-analyzer/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill job-profitability-analyzer -a codex2Manually: put the files in place
.agents/skills/job-profitability-analyzer/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill job-profitability-analyzer -a cursor2Manually: put the files in place
.cursor/skills/job-profitability-analyzer/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install OneWave-AI/claude-skills job-profitability-analyzer2Manually: put the files in place
.github/skills/job-profitability-analyzer/SKILL.md1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill job-profitability-analyzer -a gemini-cli2Platform CLI
gemini skills install https://github.com/OneWave-AI/claude-skills --path job-profitability-analyzerManually: put the files in place
.devin/skills/job-profitability-analyzer/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill job-profitability-analyzer -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about job-profitability-analyzer
How do I install job-profitability-analyzer in Claude Code?
Run npx skills add OneWave-AI/claude-skills --skill job-profitability-analyzer -a claude-code. The skill file is at ~/.claude/skills/job-profitability-analyzer/SKILL.md.
What does job-profitability-analyzer do?
It assigns costs to jobs and clients, calculates margins, and writes rankings to profitability-report.md. It also uses invoice and timesheet evidence to investigate losses.
How does the skill allocate overhead?
By default, it spreads overhead across jobs in proportion to labor hours. The report separates margins before and after overhead and flags a ranking that changes under another allocation method.
Source text
SKILL.md · MIT
--- name: job-profitability-analyzer description: Find out which clients and jobs actually make money -- allocate real costs (labor hours, materials, subs, overhead) against what each job billed, and rank every client by true margin. Most service businesses discover their biggest client is their least profitable. tools: Read, Glob, Grep, Write, Bash model: inherit --- # Job Profitability Analyzer Revenue is vanity, margin per job is survival. Service businesses (agencies, contractors, consultancies, trades) routinely lose money on their "best" clients because nobody allocates the hours. Input: invoices/revenue by job or client, time tracking exports, materials/sub costs, payroll rates, and a rough overhead number. Output: profit per job, per client, per service line -- with receipts. ## Workflow 1. **Build the job ledger.** Match every revenue line to a job/client. Match every cost: labor (hours x loaded rate -- wages plus taxes/benefits, ~1.25-1.4x base, confirmed with the user), materials and subcontractors from bills, and direct expenses (travel, software attributed to one client). 2. **Allocate overhead.** Rent, admin, insurance, tools spread across jobs -- by labor hours by default (state the method). Show margins both before and after overhead so the user sees direct profitability and true profitability separately. 3. **Rank.** `profitability-report.md`: every job and client ranked by margin dollars and margin percent, with the effective hourly rate each client actually pays (revenue minus non-labor costs, divided by hours). This one column reorders most people's client list. 4. **Diagnose the losers.** For bottom-quartile jobs: was it underpricing, scope creep (hours ballooned past estimate), expensive labor mix, or unbilled work? Cite the timesheet and invoice evidence per diagnosis. 5. **Prescribe.** Per problem client: the raise-price number that hits target margin, the scope boundary to enforce, or the fire-the-client math (hours freed x effective rate of the best clients). Pair with `pricing-strategy` for the repricing conversation. ## Rules - Loaded labor rates or nothing -- wages alone understate labor cost 25-40% and flatter every margin. - Unbilled hours are the finding, not noise: track estimated vs. actual vs. billed hours per job explicitly. - State the overhead allocation method and run the sensitivity: if the ranking flips under a different method, say so. - No cost data for a job means `INCOMPLETE`, not a guess -- and chronic time-tracking gaps get called out as the root problem. - Small samples get honesty: one bad job does not condemn a client; three do. Note the n per client. - Effective hourly rate is the universal translator -- report it everywhere. ## Quick Commands - "Analyze [files]" -- full workflow - "Rank my clients" -- client-level table only - "Why did [job] lose money?" -- single-job autopsy - "What should I charge [client]?" -- the repricing math
© OneWave-AI · MIT · OneWave-AI/claude-skills