Initial commit

commands/audit-provider-health.md

@@ -0,0 +1,35 @@
+---
+name: audit-provider-health
+description: Evaluates enrichment provider performance, coverage, and compliance posture.
+usage: /data-signal-enrichment:audit-provider-health --providers apollo,hunter --window 30d --metrics success,latency,credits
+---
+
+# Command: audit-provider-health
+
+## Inputs
+- **providers** – comma-separated provider IDs (optional, defaults to all).
+- **window** – lookback window (7d, 30d, quarter).
+- **metrics** – success | latency | credits | quality (single or multi-select).
+- **include-incidents** – true/false to append incident log details.
+- **format** – dashboard | memo | csv.
+
+## Workflow
+1. **Data Pull** – aggregate success logs, latency metrics, credit usage, and quality flags.
+2. **Benchmarking** – compare against SLA targets, cost thresholds, and historical averages.
+3. **Incident Review** – attach outages, compliance issues, or ticket history (if requested).
+4. **Recommendation Engine** – flag providers for scale-up, optimization, or pause.
+5. **Packaging** – compile memo/dashboard plus Jira-ready action list.
+
+## Outputs
+- Provider scorecard per vendor with KPIs and SLA deltas.
+- Optimization recommendations (route changes, contract updates, new tests).
+- Incident appendix with remediation owners and due dates.
+
+## Agent/Skill Invocations
+- `provider-ops-lead` – owns analysis + recommendations.
+- `data-quality-steward` – confirms quality/compliance findings.
+- `signal-integrator` – ensures logging/telemetry coverage.
+- `provider-scorecard` skill – standardizes scorecard layout.
+- `waterfall-blueprint` skill – updates workflows based on findings.
+
+---

commands/normalize-signals.md

@@ -0,0 +1,35 @@
+---
+name: normalize-signals
+description: Processes enriched datasets into unified schemas with identity resolution and tagging.
+usage: /data-signal-enrichment:normalize-signals --source warehouse --outputs crm,cdp --taxonomy intent_v2
+---
+
+# Command: normalize-signals
+
+## Inputs
+- **source** – data origin (warehouse, csv, api, webhook).
+- **outputs** – comma-separated destinations (crm, cdp, lake, orchestration).
+- **taxonomy** – schema/taxonomy version to enforce.
+- **window** – time window or batch ID to process.
+- **dry-run** – true/false toggle for validation-only runs.
+
+## Workflow
+1. **Schema Detection** – inspect incoming fields, compare to taxonomy, flag gaps.
+2. **Identity Resolution** – match accounts/contacts/opps using rules + heuristics.
+3. **Normalization** – standardize values, units, topics, and metadata.
+4. **Tagging & Scoring** – add freshness, confidence, and signal-type tags.
+5. **Distribution** – publish to requested destinations with lineage + control tables.
+
+## Outputs
+- Normalized dataset (per destination) with schema compliance report.
+- Identity resolution summary (matches, conflicts, unresolved records).
+- Taxonomy drift log + remediation checklist.
+
+## Agent/Skill Invocations
+- `signal-integrator` – runs normalization + distribution.
+- `data-quality-steward` – validates schema + scores.
+- `provider-ops-lead` – supplies provider metadata for lineage.
+- `signal-taxonomy` skill – enforces schema + naming rules.
+- `identity-resolution` skill – handles matching heuristics.
+
+---

commands/run-waterfall-enrichment.md

@@ -0,0 +1,35 @@
+---
+name: run-waterfall-enrichment
+description: Executes provider waterfalls with credit governance, failover rules, and delivery targets.
+usage: /data-signal-enrichment:run-waterfall-enrichment --type contact --input "Taylor Reed, Nimbus" --sequence apollo,hunter,rocketreach --max-credits 5
+---
+
+# Command: run-waterfall-enrichment
+
+## Inputs
+- **type** – contact | company | technographic | intent.
+- **input** – record payload (name/company/email/domain/file).
+- **sequence** – optional ordered provider list; default uses ops config.
+- **max-credits** – ceiling for total credits to consume.
+- **delivery** – crm | csv | warehouse specifying output target.
+
+## Workflow
+1. **Request Validation** – confirm fields, dedupe against recent runs, and enforce rate limits.
+2. **Sequence Selection** – pull provider order from configs, adjust for overrides or outages.
+3. **Execution Loop** – call providers, capture response metadata, apply validation logic.
+4. **Aggregation & Scoring** – merge best data, attach confidence + provenance tags.
+5. **Delivery & Logging** – push to destination, log credits, update success dashboards, trigger alerts if thresholds exceeded.
+
+## Outputs
+- Enrichment payload (JSON/CSV/CRM payload) with fields, provider, timestamp, confidence.
+- Credit + latency report appended to provider utilization table.
+- Alert entries when max-credits hit or providers fail.
+
+## Agent/Skill Invocations
+- `provider-ops-lead` – supplies sequence + credit policy.
+- `signal-integrator` – handles normalization + delivery.
+- `data-quality-steward` – validates results before release.
+- `waterfall-blueprint` skill – enforces sequencing template.
+- `provider-scorecard` skill – logs performance + cost metrics.
+
+---