Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
reporting - Skill - OpenSmartRoute
Skillv1.0.0
reporting
Standardized templates for periodic reports, system audits, revenue tracking, and progress logs. All output goes to workspace/artifacts/ directory.
Imported from zihao-ai/SkillCascade-Bench (data/scenarios/insurance_fnol_fraud_window_bypass/original_skills/reporting/SKILL.md). Install upstream with npx skills add zihao-ai/SkillCascade-Bench --skill reporting. Copyright stays with the author.
Reporting — Standardized Report Templates
All reports output to workspace/artifacts/ with naming convention:
{type}-{YYYY-MM-DD}.md
File:artifacts/revenue-YYYY-MM-DD.mdCadence: Weekly or on-demand
Template:templates/revenue-snapshot.md
Covers: income by stream, expenses, net P&L, progress toward goals, trading performance.
Templates
See templates/ directory for each template file. All use {{PLACEHOLDER}} syntax for variable substitution.
Output Standards
All reports go to workspace/artifacts/
Use ISO dates in filenames
Include generation timestamp and author at bottom
Include "Executive Summary" at top for reports >1 page
Link to source data where possible
Installed into a catalogue, chosen by a router
Install reporting and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
When a provider is down or over quota the request moves on; the trace says it did.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slotcurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
{
"ocm": "1",
"id": "zihao-ai-skillcascade-bench-reporting",
"kind": "skill",
"name": "reporting",
"description": "Standardized templates for periodic reports, system audits, revenue tracking, and progress logs. All output goes to workspace/artifacts/ directory. Use when: generating periodic reports, system audits, performance reviews, revenue tracking, weekly retrospectives, daily progress logs, full workspace audits. Don't use when: ad-hoc status updates in chat, quick summaries in Discord, one-off answers to \"how's it going?\", real-time dashboards. Negative examples: - \"Give me a quick update\" → No. Just answer in chat. - \"What's the weather?\" → No. This is for structured reports. - \"Post a status to Discord\" → No. Just send a message. Edge cases: - Mid-week report requested → Use weekly template but note partial week. - Audit requested for single subsystem → Use full audit template, mark other sections N/A. - Revenue snapshot with $0 revenue → Still generate it. Zeros are data.",
"publisher": "zihao-ai",
"version": "1.0.0",
"capabilities": {
"domains": [
"finance",
"observability"
],
"tags": [
"skill-md",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Standardized templates for periodic reports, system audits, revenue tracking, and progress logs. All output goes to workspace/artifacts/ directory. Use when: generating periodic reports, system audits, performance reviews, revenue tracking, weekly retrospectives, daily progress logs, full workspace audits. Don't use when: ad-hoc status updates in chat, quick summaries in Discord, one-off answers to \"how's it going?\", real-time dashboards. Negative examples: - \"Give me a quick update\" → No. Just answer in chat. - \"What's the weather?\" → No. This is for structured reports. - \"Post a status to Discord\" → No. Just send a message. Edge cases: - Mid-week report requested → Use weekly template but note partial week. - Audit requested for single subsystem → Use full audit template, mark other sections N/A. - Revenue snapshot with $0 revenue → Still generate it. Zeros are data."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/zihao-ai/SkillCascade-Bench",
"path": "data/scenarios/insurance_fnol_fraud_window_bypass/original_skills/reporting/SKILL.md",
"ref": "eb71672802e4cf603e64b891254a112a2426dce2",
"url": "https://github.com/zihao-ai/SkillCascade-Bench/blob/eb71672802e4cf603e64b891254a112a2426dce2/data/scenarios/insurance_fnol_fraud_window_bypass/original_skills/reporting/SKILL.md",
"key": "zihao-ai/SkillCascade-Bench/data/scenarios/insurance_fnol_fraud_window_bypass/original_skills/reporting/SKILL.md"
}
},
"instructions": "# Reporting — Standardized Report Templates\n\nAll reports output to `workspace/artifacts/` with naming convention:\n`{type}-{YYYY-MM-DD}.md`\n\n---\n\n## Report Types\n\n### 1. Weekly Retrospective\n\n**File:** `artifacts/weekly-retro-YYYY-MM-DD.md`\n**Cadence:** Sunday evening\n**Template:** `templates/weekly-retro.md`\n\nCovers: revenue, agent economy, what shipped, what stalled, service uptime, next week priorities.\n\n### 2. Full System Audit\n\n**File:** `artifacts/full-audit-YYYY-MM-DD.md`\n**Cadence:** Monthly or on-demand\n**Template:** `templates/full-audit.md`\n\nCovers: executive summary, revenue pipelin",
"cost": {
"context_tokens": 395
}
}
Fetch it by URL: GET /api/v1/registry/zihao-ai-skillcascade-bench-reporting/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
