FrancyJGLisboa/agent-skills-platform / references/examples/weekly-crm-report
weekly-crm-report
UnverifiedCleans a weekly CRM export and produces a regional sales summary. Activates when the user asks to clean a CRM export, deduplicate sales rows, calculate regional totals, or generate a weekly sales report from a CSV.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 1.7 KB |
| SKILL.md | skill md | 2.4 KB |
| VERIFICATION.md | markdown | 845 B |
| contracts/data_contract_crm_export/.contract_id | other | 10 B |
| contracts/data_contract_crm_export/code/contract_health.py | script | 386 B |
| discovery.json | config | 2.2 KB |
| evals/golden/case-1/expected.json | config | 126 B |
| evals/golden/case-1/input.csv | other | 62 B |
| evals/golden/case-2/expected.json | config | 129 B |
| evals/golden/case-2/input.csv | other | 46 B |
| evals/golden/case-3/expected.json | config | 106 B |
| evals/golden/case-3/input.csv | other | 39 B |
| evals/weekly-crm-report.eval.md | markdown | 1.8 KB |
| scripts/dependency_health.py | script | 3.9 KB |
| scripts/evolve.pyexecutable | script | 10.2 KB |
| scripts/review_staleness.py | script | 6.2 KB |
| scripts/run_evals.pyexecutable | script | 49.4 KB |
| scripts/run_pipeline.pyexecutable | script | 2.3 KB |
| scripts/schema_drift.py | script | 7.3 KB |
| scripts/skill_document.py | script | 9.8 KB |
| scripts/staleness_check.py | script | 7.5 KB |
| scripts/success_ledger.py | script | 16.5 KB |
evals/weekly-crm-report.eval.md
View on GitHub# Eval Spec: weekly-crm-report
The skill's loss function: structural binary checks plus golden CRM exports. Run
`python3 scripts/run_evals.py` (scores the golden baseline) or
`python3 scripts/run_evals.py --rollout` (runs the skill on each input and scores
the real output).
## Criteria
1. **valid-json** (command) — the summary parses as JSON.
2. **has-grand-total** (command) — a numeric `grand_total` is present.
3. **dedup-happened** (command) — `rows_after_dedup` ≤ `rows_in`.
## Golden cases
Three CRM exports with intentional duplicates. Output totals are computed at
runtime, so cases are `pending-first-green`; capture a baseline with
`python3 scripts/run_evals.py --rollout --promote`.
## Spec
```json
{
"skill": "weekly-crm-report",
"run": "python3 scripts/run_pipeline.py --input {input} --output {output}",
"criteria": [
{"id": "valid-json", "text": "Summary parses as JSON", "type": "command", "cmd": "python3 -c \"import json,sys; json.load(open(sys.argv[1]))\" {output}"},
{"id": "has-grand-total", "text": "Numeric grand_total present", "type": "command", "cmd": "python3 -c \"import json,sys; d=json.load(open(sys.argv[1])); assert isinstance(d['grand_total'],(int,float))\" {output}"},
{"id": "dedup-happened", "text": "rows_after_dedup <= rows_in", "type": "command", "cmd": "python3 -c \"import json,sys; d=json.load(open(sys.argv[1])); assert d['rows_after_dedup'] <= d['rows_in']\" {output}"}
],
"golden": [
{"id": "case-1", "input": "golden/case-1/input.csv", "expected": null, "split": "val", "expected_status": "pending-first-green"},
{"id": "case-2", "input": "golden/case-2/input.csv", "expected": null, "split": "test", "expected_status": "pending-first-green"},
{"id": "case-3", "input": "golden/case-3/input.csv", "expected": null, "split": "val", "expected_status": "pending-first-green"}
]
}
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |