ln-820-dependency-optimization-coordinator
Upgrades dependencies across all detected package managers. Use when updating npm, NuGet, or pip packages project-wide.
What this skill does
> **Paths:** File paths (`references/`, `../ln-*`) are relative to this skill directory.
# ln-820-dependency-optimization-coordinator
**Type:** L2 Domain Coordinator
**Category:** 8XX Optimization
Runtime-backed coordinator for cross-stack dependency upgrades. Detects package managers, delegates to one worker per manager, records machine-readable worker summaries, and emits a final coordinator summary.
---
## Overview
| Aspect | Details |
|--------|---------|
| **Input** | Project path plus optional upgrade policy |
| **Output** | Aggregated dependency upgrade report with per-worker results |
| **Workers** | ln-821 (npm), ln-822 (nuget), ln-823 (pip) |
| **Runtime** | `.hex-skills/dependency/runtime/runs/{run_id}/` |
---
## Workflow
**Phases:** Pre-flight -> Detect Package Managers -> Security Audit -> Delegate Upgrades -> Collect Results -> Verify Summary -> Report
---
## Runtime Contract
**MANDATORY READ:** Load `references/ci_tool_detection.md`
**MANDATORY READ:** Load `references/coordinator_runtime_contract.md`, `references/dependency_runtime_contract.md`, `references/coordinator_summary_contract.md`
Runtime CLI:
```bash
node references/scripts/dependency-runtime/cli.mjs start --identifier repo-deps --manifest-file <file>
node references/scripts/dependency-runtime/cli.mjs status --identifier repo-deps
node references/scripts/dependency-runtime/cli.mjs checkpoint --phase PHASE_3_DELEGATE_UPGRADES --payload '{...}'
node references/scripts/dependency-runtime/cli.mjs record-worker-result --payload '{...}'
node references/scripts/dependency-runtime/cli.mjs record-summary --payload '{...}'
node references/scripts/dependency-runtime/cli.mjs advance --to PHASE_4_COLLECT_RESULTS
node references/scripts/dependency-runtime/cli.mjs complete
```
Required state fields:
- `worker_plan`
- `worker_results`
- `child_runs`
- `verification_passed`
- `report_ready`
- `summary_recorded`
Domain checkpoints:
- `PHASE_1_DETECT_PACKAGE_MANAGERS`: detected managers, indicator files, skipped managers
- `PHASE_2_SECURITY_AUDIT`: per-manager audit verdicts, blocking findings, release-age policy
- `PHASE_3_DELEGATE_UPGRADES`: one `child_run` per delegated worker with worker name, identifier, `runId`, and `summaryArtifactPath`
- `PHASE_4_COLLECT_RESULTS`: recorded worker summaries plus unresolved failures or warnings
- `PHASE_5_VERIFY_SUMMARY`: final report path, verification verdict, summary readiness
Guard rules:
- do not advance from `PHASE_3_DELEGATE_UPGRADES` until every planned worker emitted a valid `dependency-worker` summary
- do not complete until the final report checkpoint exists and the `dependency-coordinator` summary was recorded
- consume worker JSON summaries only; never infer worker status from prose output
---
## Phase 0: Pre-flight
Confirm the project is a valid candidate for dependency work before starting the runtime.
| Check | Method | Block if |
|-------|--------|----------|
| Manifest exists | Runtime `start` validation | Missing |
| Project path exists | File inspection | Missing |
| Upgrade policy provided | Manifest or defaults | No |
| Existing active run for identifier | Runtime active pointer | Conflicting active run |
Default options:
| Option | Default | Meaning |
|--------|---------|---------|
| `upgradeType` | `major` | major, minor, or patch |
| `allowBreaking` | `true` | allow major-version migrations |
| `minimumReleaseAge` | `14` | skip very recent releases unless security requires them |
| `testAfterUpgrade` | `true` | workers verify build/tests after changes |
---
## Phase 1: Detect Package Managers
Detect one worker target per package-manager family.
| Package Manager | Indicator Files | Worker |
|-----------------|-----------------|--------|
| npm | `package.json` + `package-lock.json` | ln-821 |
| yarn | `package.json` + `yarn.lock` | ln-821 |
| pnpm | `package.json` + `pnpm-lock.yaml` | ln-821 |
| nuget | `*.csproj` or `*.sln` | ln-822 |
| pip | `requirements.txt` | ln-823 |
| poetry | `pyproject.toml` + `poetry.lock` | ln-823 |
| pipenv | `Pipfile` + `Pipfile.lock` | ln-823 |
Checkpoint payload must include:
- `detected_managers`
- `indicator_paths`
- `worker_plan`
- `skipped_reasons`
---
## Phase 2: Security Audit
Perform lightweight pre-flight security and freshness checks before delegating heavy upgrade work.
| Manager Family | Command | Block Condition |
|----------------|---------|-----------------|
| Node.js | `npm audit --audit-level=high` or manager equivalent | Critical vulnerability with no allowed override |
| NuGet | `dotnet list package --vulnerable` | Critical vulnerability with no allowed override |
| Python | `pip-audit --json` or manager equivalent | Critical vulnerability with no allowed override |
Release-age gate:
| Option | Default | Description |
|--------|---------|-------------|
| `minimumReleaseAge` | `14 days` | Skip packages released too recently |
| `ignoreReleaseAge` | `false` | Override for urgent security patches |
Checkpoint payload must include:
- `audit_results`
- `blocking_findings`
- `release_age_policy`
- `managers_cleared_for_delegation`
---
## Phase 3: Delegate Upgrades
Delegate one child run per worker family. Child runs must be deterministic and artifact-driven.
Delegate using the concrete worker identities selected by the routing table below. Do not synthesize family placeholders or guessed skill IDs in prompts.
Delegation context:
| Field | Type | Description |
|-------|------|-------------|
| `projectPath` | string | Absolute path to target project |
| `packageManager` | enum | npm, yarn, pnpm, nuget, pip, poetry, pipenv |
| `identifier` | string | Stable worker identifier inside the run |
| `runId` | string | Deterministic child run id |
| `summaryArtifactPath` | string | Exact JSON path for the worker summary |
| `options` | object | Upgrade policy, verification flags, safety flags |
Worker selection:
| Manager Family | Worker | Notes |
|----------------|--------|-------|
| npm, yarn, pnpm | ln-821-npm-upgrader | One child run per detected Node manager |
| nuget | ln-822-nuget-upgrader | One child run for .NET |
| pip, poetry, pipenv | ln-823-pip-upgrader | One child run per detected Python manager |
After launching each worker:
1. Checkpoint `child_run` under `PHASE_3_DELEGATE_UPGRADES`.
2. Wait for the emitted `dependency-worker` summary envelope.
3. Record the worker summary with `record-worker-result`.
---
## Phase 4: Collect Results
Aggregate validated worker summaries only.
Worker summary fields consumed by the coordinator:
| Field | Description |
|-------|-------------|
| `producer_skill` | worker identity (`ln-821`, `ln-822`, `ln-823`) |
| `summary_kind` | must be `dependency-worker` |
| `identifier` | stable worker identifier |
| `payload.status` | completed, partial, or failed |
| `payload.upgrades` | applied upgrades with before/after versions |
| `payload.warnings` | non-blocking issues |
| `payload.verification` | build/test verification result |
| `payload.artifact_path` | worker-owned durable report path, if any |
Collection output:
- `worker_results`
- `success_count`
- `partial_count`
- `failed_count`
- `blocking_failures`
---
## Phase 5: Verify Summary
Prepare the final durable report and verify the coordinator can finish deterministically.
Verification checklist:
- every planned worker produced one valid summary envelope
- aggregate counts match recorded worker results
- final report path exists or is ready to be written
- `report_ready` and `verification_passed` are true before completion
Failure handling:
1. Keep successful worker results intact.
2. Mark failed workers explicitly in the coordinator report.
3. Do not invent rollback actions beyond what workers already verified.
---
## Phase 6: Report
Coordinator report schema:
| Field | Description |
|-------|-------------|
| `package_managers` | detected managers handled in this run |
| `workers_activated` | delegated workers |
| `total_packages` | packagRelated in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.